chore: trigger build

[avik-pal]

Don't Merge triggering build with new Enzyme release

[github-actions]

LuxLib Benchmarks

Benchmark suite	Current: 9b7286d	Previous: 604783f	Ratio
layernorm(2, act=gelu, affine=false)(4 x 32)/forward/CPU/2 thread(s)	5042 ns	5375 ns	0.94
layernorm(2, act=gelu, affine=false)(4 x 32)/forward/CPU/4 thread(s)	5125 ns	5250 ns	0.98
layernorm(2, act=gelu, affine=false)(4 x 32)/forward/CPU/8 thread(s)	6583 ns	7708.5 ns	0.85
layernorm(2, act=gelu, affine=false)(4 x 32)/forward/CPU/1 thread(s)	5125 ns	5416 ns	0.95
layernorm(2, act=gelu, affine=false)(4 x 32)/forward/GPU/CUDA	106934 ns	113361 ns	0.94
layernorm(2, act=gelu, affine=false)(4 x 32)/forward/GPU/oneAPI	2903264 ns	2795172 ns	1.04
layernorm(2, act=gelu, affine=false)(4 x 32)/forward/GPU/AMDGPU	418904 ns	601544 ns	0.70
layernorm(2, act=gelu, affine=false)(4 x 32)/zygote/CPU/2 thread(s)	10042 ns	9729.5 ns	1.03
layernorm(2, act=gelu, affine=false)(4 x 32)/zygote/CPU/4 thread(s)	9875 ns	9938 ns	0.99
layernorm(2, act=gelu, affine=false)(4 x 32)/zygote/CPU/8 thread(s)	10333 ns	10167 ns	1.02
layernorm(2, act=gelu, affine=false)(4 x 32)/zygote/CPU/1 thread(s)	9750 ns	11063 ns	0.88
layernorm(2, act=gelu, affine=false)(4 x 32)/zygote/GPU/CUDA	509431 ns	544547 ns	0.94
layernorm(2, act=gelu, affine=false)(4 x 32)/zygote/GPU/oneAPI	18145309 ns	17852957 ns	1.02
layernorm(2, act=gelu, affine=false)(4 x 32)/zygote/GPU/AMDGPU	664847 ns	629346 ns	1.06
bias_activation(32, act=relu)(32 x 128)/forward/CPU/2 thread(s)	1312.5 ns	1500 ns	0.88
bias_activation(32, act=relu)(32 x 128)/forward/CPU/4 thread(s)	1604 ns	1458 ns	1.10
bias_activation(32, act=relu)(32 x 128)/forward/CPU/8 thread(s)	1917 ns	1771 ns	1.08
bias_activation(32, act=relu)(32 x 128)/forward/CPU/1 thread(s)	1312.5 ns	1583 ns	0.83
bias_activation(32, act=relu)(32 x 128)/forward/GPU/CUDA	20523 ns	20770 ns	0.99
bias_activation(32, act=relu)(32 x 128)/forward/GPU/oneAPI	1336257 ns	1342503 ns	1.00
bias_activation(32, act=relu)(32 x 128)/forward/GPU/AMDGPU	31420 ns	30997 ns	1.01
bias_activation(32, act=relu)(32 x 128)/zygote/CPU/2 thread(s)	3521 ns	4104 ns	0.86
bias_activation(32, act=relu)(32 x 128)/zygote/CPU/4 thread(s)	3959 ns	4500 ns	0.88
bias_activation(32, act=relu)(32 x 128)/zygote/CPU/8 thread(s)	4333 ns	4500 ns	0.96
bias_activation(32, act=relu)(32 x 128)/zygote/CPU/1 thread(s)	3833.5 ns	4333 ns	0.88
bias_activation(32, act=relu)(32 x 128)/zygote/GPU/CUDA	136761.5 ns	134970 ns	1.01
bias_activation(32, act=relu)(32 x 128)/zygote/GPU/oneAPI	9485308 ns	8677498 ns	1.09
bias_activation(32, act=relu)(32 x 128)/zygote/GPU/AMDGPU	147442 ns	138579 ns	1.06
batchnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	57417 ns	57666.5 ns	1.00
batchnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	47541 ns	46875 ns	1.01
batchnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	47542 ns	47125 ns	1.01
batchnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	80541 ns	81458 ns	0.99
batchnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/CUDA	37101 ns	36587 ns	1.01
batchnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	559661 ns	582336 ns	0.96
batchnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	79531 ns	69420 ns	1.15
batchnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	2034750 ns	2030375 ns	1.00
batchnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	2084521.5 ns	2088625 ns	1.00
batchnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	2070833 ns	2086625 ns	0.99
batchnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	2000729 ns	1998562 ns	1.00
batchnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	219850 ns	217216 ns	1.01
batchnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	8230111 ns	8077777 ns	1.02
batchnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1184482 ns	930850 ns	1.27
layernorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	148042 ns	175083 ns	0.85
layernorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	169209 ns	147291 ns	1.15
layernorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	175125 ns	150021 ns	1.17
layernorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	147208 ns	151750 ns	0.97
layernorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/GPU/CUDA	167624 ns	166825 ns	1.00
layernorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	8071401.5 ns	7358467.5 ns	1.10
layernorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	187542 ns	262570 ns	0.71
layernorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	1108854.5 ns	1115103.5 ns	0.99
layernorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	1109542 ns	1110771 ns	1.00
layernorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	1126333 ns	1113771 ns	1.01
layernorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	1112291 ns	1136250 ns	0.98
layernorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	648435 ns	639845.5 ns	1.01
layernorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	34776278 ns	33057102 ns	1.05
layernorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1012710 ns	864075 ns	1.17
layernorm(2, act=relu, affine=true)(4 x 32)/forward/CPU/2 thread(s)	4917 ns	3792 ns	1.30
layernorm(2, act=relu, affine=true)(4 x 32)/forward/CPU/4 thread(s)	4812.5 ns	4479 ns	1.07
layernorm(2, act=relu, affine=true)(4 x 32)/forward/CPU/8 thread(s)	5666.5 ns	6583 ns	0.86
layernorm(2, act=relu, affine=true)(4 x 32)/forward/CPU/1 thread(s)	3875 ns	6375 ns	0.61
layernorm(2, act=relu, affine=true)(4 x 32)/forward/GPU/CUDA	84692.5 ns	85209.5 ns	0.99
layernorm(2, act=relu, affine=true)(4 x 32)/forward/GPU/oneAPI	5745043.5 ns	5875726.5 ns	0.98
layernorm(2, act=relu, affine=true)(4 x 32)/forward/GPU/AMDGPU	61061 ns	59531 ns	1.03
layernorm(2, act=relu, affine=true)(4 x 32)/zygote/CPU/2 thread(s)	8666 ns	8417 ns	1.03
layernorm(2, act=relu, affine=true)(4 x 32)/zygote/CPU/4 thread(s)	8708 ns	8750 ns	1.00
layernorm(2, act=relu, affine=true)(4 x 32)/zygote/CPU/8 thread(s)	9041 ns	9042 ns	1.00
layernorm(2, act=relu, affine=true)(4 x 32)/zygote/CPU/1 thread(s)	8500 ns	8958 ns	0.95
layernorm(2, act=relu, affine=true)(4 x 32)/zygote/GPU/CUDA	567531 ns	557500.5 ns	1.02
layernorm(2, act=relu, affine=true)(4 x 32)/zygote/GPU/oneAPI	36159388.5 ns	34838164 ns	1.04
layernorm(2, act=relu, affine=true)(4 x 32)/zygote/GPU/AMDGPU	390569 ns	370833 ns	1.05
groupnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	17125 ns	17958 ns	0.95
groupnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	17542 ns	16458 ns	1.07
groupnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	19917 ns	21125 ns	0.94
groupnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	17437 ns	17292 ns	1.01
groupnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/GPU/CUDA	63455.5 ns	63776.5 ns	0.99
groupnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	3109889.5 ns	2927491.5 ns	1.06
groupnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	75491 ns	82870 ns	0.91
groupnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	218459 ns	212625 ns	1.03
groupnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	212021 ns	213042 ns	1.00
groupnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	224041.5 ns	212771 ns	1.05
groupnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	214917 ns	212291 ns	1.01
groupnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	330824 ns	329859 ns	1.00
groupnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	14581752 ns	12611094 ns	1.16
groupnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	471355 ns	405232 ns	1.16
bias_activation(2, act=relu)(2 x 128)/forward/CPU/2 thread(s)	583 ns	667 ns	0.87
bias_activation(2, act=relu)(2 x 128)/forward/CPU/4 thread(s)	666 ns	625 ns	1.07
bias_activation(2, act=relu)(2 x 128)/forward/CPU/8 thread(s)	916 ns	875 ns	1.05
bias_activation(2, act=relu)(2 x 128)/forward/CPU/1 thread(s)	583 ns	709 ns	0.82
bias_activation(2, act=relu)(2 x 128)/forward/GPU/CUDA	19184 ns	19101 ns	1.00
bias_activation(2, act=relu)(2 x 128)/forward/GPU/oneAPI	1196032.5 ns	1145778 ns	1.04
bias_activation(2, act=relu)(2 x 128)/forward/GPU/AMDGPU	30790 ns	26409 ns	1.17
bias_activation(2, act=relu)(2 x 128)/zygote/CPU/2 thread(s)	1417 ns	1458 ns	0.97
bias_activation(2, act=relu)(2 x 128)/zygote/CPU/4 thread(s)	1375 ns	1334 ns	1.03
bias_activation(2, act=relu)(2 x 128)/zygote/CPU/8 thread(s)	1583 ns	1583 ns	1
bias_activation(2, act=relu)(2 x 128)/zygote/CPU/1 thread(s)	1375 ns	1375 ns	1
bias_activation(2, act=relu)(2 x 128)/zygote/GPU/CUDA	118015 ns	117126.5 ns	1.01
bias_activation(2, act=relu)(2 x 128)/zygote/GPU/oneAPI	8426159.5 ns	8850213 ns	0.95
bias_activation(2, act=relu)(2 x 128)/zygote/GPU/AMDGPU	123561 ns	115676 ns	1.07
batchnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	7416.5 ns	7375 ns	1.01
batchnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	6041 ns	6041 ns	1
batchnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	6000 ns	6084 ns	0.99
batchnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	9875 ns	9958 ns	0.99
batchnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/CUDA	24050 ns	23587 ns	1.02
batchnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	1274308.5 ns	1261233 ns	1.01
batchnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	47100 ns	52723 ns	0.89
batchnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	230291 ns	229167 ns	1.00
batchnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	232000 ns	230667 ns	1.01
batchnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	266667 ns	267875 ns	1.00
batchnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	212979 ns	257458 ns	0.83
batchnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	190269 ns	182744 ns	1.04
batchnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	30917862 ns	32590762.5 ns	0.95
batchnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	603736 ns	548449.5 ns	1.10
dense(32, bias=false, act=relu)(32 x 128)/forward/CPU/2 thread(s)	3917 ns	3917 ns	1
dense(32, bias=false, act=relu)(32 x 128)/forward/CPU/4 thread(s)	3917 ns	3958 ns	0.99
dense(32, bias=false, act=relu)(32 x 128)/forward/CPU/8 thread(s)	3958 ns	3958 ns	1
dense(32, bias=false, act=relu)(32 x 128)/forward/CPU/1 thread(s)	3917 ns	3917 ns	1
dense(32, bias=false, act=relu)(32 x 128)/forward/GPU/CUDA	23276 ns	22860 ns	1.02
dense(32, bias=false, act=relu)(32 x 128)/forward/GPU/oneAPI	2010135 ns	1933593 ns	1.04
dense(32, bias=false, act=relu)(32 x 128)/forward/GPU/AMDGPU	48340 ns	39504 ns	1.22
dense(32, bias=false, act=relu)(32 x 128)/zygote/CPU/2 thread(s)	16833 ns	17042 ns	0.99
dense(32, bias=false, act=relu)(32 x 128)/zygote/CPU/4 thread(s)	16875 ns	16875 ns	1
dense(32, bias=false, act=relu)(32 x 128)/zygote/CPU/8 thread(s)	17209 ns	17083 ns	1.01
dense(32, bias=false, act=relu)(32 x 128)/zygote/CPU/1 thread(s)	17166 ns	16875 ns	1.02
dense(32, bias=false, act=relu)(32 x 128)/zygote/GPU/CUDA	187223 ns	185787.5 ns	1.01
dense(32, bias=false, act=relu)(32 x 128)/zygote/GPU/oneAPI	10116574 ns	10029430 ns	1.01
dense(32, bias=false, act=relu)(32 x 128)/zygote/GPU/AMDGPU	177062 ns	162052 ns	1.09
dense(512, bias=false, act=gelu)(512 x 128)/forward/CPU/2 thread(s)	491333 ns	491583 ns	1.00
dense(512, bias=false, act=gelu)(512 x 128)/forward/CPU/4 thread(s)	385750 ns	385625 ns	1.00
dense(512, bias=false, act=gelu)(512 x 128)/forward/CPU/8 thread(s)	385833 ns	386458 ns	1.00
dense(512, bias=false, act=gelu)(512 x 128)/forward/CPU/1 thread(s)	847083.5 ns	844083 ns	1.00
dense(512, bias=false, act=gelu)(512 x 128)/forward/GPU/CUDA	113452 ns	113763 ns	1.00
dense(512, bias=false, act=gelu)(512 x 128)/forward/GPU/oneAPI	401173 ns	418213 ns	0.96
dense(512, bias=false, act=gelu)(512 x 128)/forward/GPU/AMDGPU	244572 ns	388657 ns	0.63
dense(512, bias=false, act=gelu)(512 x 128)/zygote/CPU/2 thread(s)	2152291.5 ns	2155583 ns	1.00
dense(512, bias=false, act=gelu)(512 x 128)/zygote/CPU/4 thread(s)	1860958 ns	1863374.5 ns	1.00
dense(512, bias=false, act=gelu)(512 x 128)/zygote/CPU/8 thread(s)	1862458 ns	1865167 ns	1.00
dense(512, bias=false, act=gelu)(512 x 128)/zygote/CPU/1 thread(s)	3118353.5 ns	3377520.5 ns	0.92
dense(512, bias=false, act=gelu)(512 x 128)/zygote/GPU/CUDA	230368 ns	229580 ns	1.00
dense(512, bias=false, act=gelu)(512 x 128)/zygote/GPU/oneAPI	10676380 ns	9922983 ns	1.08
dense(512, bias=false, act=gelu)(512 x 128)/zygote/GPU/AMDGPU	743078 ns	610962 ns	1.22
layernorm(2, act=relu, affine=false)(32 x 32)/forward/CPU/2 thread(s)	6354 ns	6500 ns	0.98
layernorm(2, act=relu, affine=false)(32 x 32)/forward/CPU/4 thread(s)	6437.5 ns	5500 ns	1.17
layernorm(2, act=relu, affine=false)(32 x 32)/forward/CPU/8 thread(s)	6958 ns	7667 ns	0.91
layernorm(2, act=relu, affine=false)(32 x 32)/forward/CPU/1 thread(s)	5875 ns	5167 ns	1.14
layernorm(2, act=relu, affine=false)(32 x 32)/forward/GPU/CUDA	84550.5 ns	84720.5 ns	1.00
layernorm(2, act=relu, affine=false)(32 x 32)/forward/GPU/oneAPI	5551475 ns	5300415 ns	1.05
layernorm(2, act=relu, affine=false)(32 x 32)/forward/GPU/AMDGPU	59440 ns	59932 ns	0.99
layernorm(2, act=relu, affine=false)(32 x 32)/zygote/CPU/2 thread(s)	11459 ns	11229 ns	1.02
layernorm(2, act=relu, affine=false)(32 x 32)/zygote/CPU/4 thread(s)	11666.5 ns	11395.5 ns	1.02
layernorm(2, act=relu, affine=false)(32 x 32)/zygote/CPU/8 thread(s)	12000 ns	12334 ns	0.97
layernorm(2, act=relu, affine=false)(32 x 32)/zygote/CPU/1 thread(s)	11438 ns	10667 ns	1.07
layernorm(2, act=relu, affine=false)(32 x 32)/zygote/GPU/CUDA	610257 ns	602168 ns	1.01
layernorm(2, act=relu, affine=false)(32 x 32)/zygote/GPU/oneAPI	37918559 ns	38613143.5 ns	0.98
layernorm(2, act=relu, affine=false)(32 x 32)/zygote/GPU/AMDGPU	410225 ns	383917 ns	1.07
dense(2, bias=true, act=relu)(2 x 128)/forward/CPU/2 thread(s)	541 ns	500 ns	1.08
dense(2, bias=true, act=relu)(2 x 128)/forward/CPU/4 thread(s)	500 ns	500 ns	1
dense(2, bias=true, act=relu)(2 x 128)/forward/CPU/8 thread(s)	542 ns	542 ns	1
dense(2, bias=true, act=relu)(2 x 128)/forward/CPU/1 thread(s)	500 ns	500 ns	1
dense(2, bias=true, act=relu)(2 x 128)/forward/GPU/CUDA	23314 ns	23328 ns	1.00
dense(2, bias=true, act=relu)(2 x 128)/forward/GPU/oneAPI	2245583 ns	2178076 ns	1.03
dense(2, bias=true, act=relu)(2 x 128)/forward/GPU/AMDGPU	49110 ns	41367 ns	1.19
dense(2, bias=true, act=relu)(2 x 128)/zygote/CPU/2 thread(s)	2125 ns	2084 ns	1.02
dense(2, bias=true, act=relu)(2 x 128)/zygote/CPU/4 thread(s)	2125 ns	2166 ns	0.98
dense(2, bias=true, act=relu)(2 x 128)/zygote/CPU/8 thread(s)	2167 ns	2167 ns	1
dense(2, bias=true, act=relu)(2 x 128)/zygote/CPU/1 thread(s)	2125 ns	2084 ns	1.02
dense(2, bias=true, act=relu)(2 x 128)/zygote/GPU/CUDA	229615 ns	228927.5 ns	1.00
dense(2, bias=true, act=relu)(2 x 128)/zygote/GPU/oneAPI	11471919 ns	11774524 ns	0.97
dense(2, bias=true, act=relu)(2 x 128)/zygote/GPU/AMDGPU	180602 ns	165900 ns	1.09
groupnorm(2, act=relu, affine=true)(32 x 32)/forward/CPU/2 thread(s)	8083 ns	9584 ns	0.84
groupnorm(2, act=relu, affine=true)(32 x 32)/forward/CPU/4 thread(s)	9000 ns	8333 ns	1.08
groupnorm(2, act=relu, affine=true)(32 x 32)/forward/CPU/8 thread(s)	10771 ns	9895.5 ns	1.09
groupnorm(2, act=relu, affine=true)(32 x 32)/forward/CPU/1 thread(s)	8833 ns	8542 ns	1.03
groupnorm(2, act=relu, affine=true)(32 x 32)/forward/GPU/CUDA	109160 ns	105241 ns	1.04
groupnorm(2, act=relu, affine=true)(32 x 32)/forward/GPU/oneAPI	3234020 ns	3103348.5 ns	1.04
groupnorm(2, act=relu, affine=true)(32 x 32)/forward/GPU/AMDGPU	72921 ns	71955 ns	1.01
groupnorm(2, act=relu, affine=true)(32 x 32)/zygote/CPU/2 thread(s)	18542 ns	17688 ns	1.05
groupnorm(2, act=relu, affine=true)(32 x 32)/zygote/CPU/4 thread(s)	17250 ns	16666.5 ns	1.04
groupnorm(2, act=relu, affine=true)(32 x 32)/zygote/CPU/8 thread(s)	18770.5 ns	18708 ns	1.00
groupnorm(2, act=relu, affine=true)(32 x 32)/zygote/CPU/1 thread(s)	19146 ns	17562 ns	1.09
groupnorm(2, act=relu, affine=true)(32 x 32)/zygote/GPU/CUDA	601629.5 ns	595171 ns	1.01
groupnorm(2, act=relu, affine=true)(32 x 32)/zygote/GPU/oneAPI	18001662.5 ns	16252508 ns	1.11
groupnorm(2, act=relu, affine=true)(32 x 32)/zygote/GPU/AMDGPU	380179 ns	358129 ns	1.06
batchnorm(2, act=identity, affine=false)(32 x 32)/forward/CPU/2 thread(s)	500 ns	542 ns	0.92
batchnorm(2, act=identity, affine=false)(32 x 32)/forward/CPU/4 thread(s)	500 ns	458 ns	1.09
batchnorm(2, act=identity, affine=false)(32 x 32)/forward/CPU/8 thread(s)	625 ns	583 ns	1.07
batchnorm(2, act=identity, affine=false)(32 x 32)/forward/CPU/1 thread(s)	500 ns	458 ns	1.09
batchnorm(2, act=identity, affine=false)(32 x 32)/forward/GPU/CUDA	34903 ns	34578 ns	1.01
batchnorm(2, act=identity, affine=false)(32 x 32)/forward/GPU/oneAPI	1280813.5 ns	1237584 ns	1.03
batchnorm(2, act=identity, affine=false)(32 x 32)/forward/GPU/AMDGPU	47631 ns	41387 ns	1.15
batchnorm(2, act=identity, affine=false)(32 x 32)/zygote/CPU/2 thread(s)	8958 ns	9229 ns	0.97
batchnorm(2, act=identity, affine=false)(32 x 32)/zygote/CPU/4 thread(s)	8812 ns	8958.5 ns	0.98
batchnorm(2, act=identity, affine=false)(32 x 32)/zygote/CPU/8 thread(s)	9937.5 ns	9750 ns	1.02
batchnorm(2, act=identity, affine=false)(32 x 32)/zygote/CPU/1 thread(s)	9250 ns	8104 ns	1.14
batchnorm(2, act=identity, affine=false)(32 x 32)/zygote/GPU/CUDA	260309 ns	257823 ns	1.01
batchnorm(2, act=identity, affine=false)(32 x 32)/zygote/GPU/oneAPI	20391796 ns	18331589 ns	1.11
batchnorm(2, act=identity, affine=false)(32 x 32)/zygote/GPU/AMDGPU	367584 ns	349944 ns	1.05
dense(512, bias=false, act=identity)(512 x 128)/forward/CPU/2 thread(s)	396708 ns	397270.5 ns	1.00
dense(512, bias=false, act=identity)(512 x 128)/forward/CPU/4 thread(s)	288333 ns	288083 ns	1.00
dense(512, bias=false, act=identity)(512 x 128)/forward/CPU/8 thread(s)	288042 ns	288666.5 ns	1.00
dense(512, bias=false, act=identity)(512 x 128)/forward/CPU/1 thread(s)	750541 ns	751792 ns	1.00
dense(512, bias=false, act=identity)(512 x 128)/forward/GPU/CUDA	111691.5 ns	112022 ns	1.00
dense(512, bias=false, act=identity)(512 x 128)/forward/GPU/oneAPI	332135 ns	349915 ns	0.95
dense(512, bias=false, act=identity)(512 x 128)/forward/GPU/AMDGPU	74831 ns	74609 ns	1.00
dense(512, bias=false, act=identity)(512 x 128)/zygote/CPU/2 thread(s)	1459375 ns	1454270.5 ns	1.00
dense(512, bias=false, act=identity)(512 x 128)/zygote/CPU/4 thread(s)	1133375 ns	1130500 ns	1.00
dense(512, bias=false, act=identity)(512 x 128)/zygote/CPU/8 thread(s)	1131542 ns	1131583 ns	1.00
dense(512, bias=false, act=identity)(512 x 128)/zygote/CPU/1 thread(s)	2439208 ns	2437959 ns	1.00
dense(512, bias=false, act=identity)(512 x 128)/zygote/GPU/CUDA	201195 ns	200057 ns	1.01
dense(512, bias=false, act=identity)(512 x 128)/zygote/GPU/oneAPI	10334858 ns	7687949 ns	1.34
dense(512, bias=false, act=identity)(512 x 128)/zygote/GPU/AMDGPU	324153 ns	302285 ns	1.07
layernorm(2, act=relu, affine=true)(32 x 32)/forward/CPU/2 thread(s)	6917 ns	7750 ns	0.89
layernorm(2, act=relu, affine=true)(32 x 32)/forward/CPU/4 thread(s)	6875 ns	7083.5 ns	0.97
layernorm(2, act=relu, affine=true)(32 x 32)/forward/CPU/8 thread(s)	7542 ns	8312.5 ns	0.91
layernorm(2, act=relu, affine=true)(32 x 32)/forward/CPU/1 thread(s)	6667 ns	6687.5 ns	1.00
layernorm(2, act=relu, affine=true)(32 x 32)/forward/GPU/CUDA	134405 ns	139766 ns	0.96
layernorm(2, act=relu, affine=true)(32 x 32)/forward/GPU/oneAPI	5807519.5 ns	5685169 ns	1.02
layernorm(2, act=relu, affine=true)(32 x 32)/forward/GPU/AMDGPU	59841 ns	60383 ns	0.99
layernorm(2, act=relu, affine=true)(32 x 32)/zygote/CPU/2 thread(s)	14750 ns	13479.5 ns	1.09
layernorm(2, act=relu, affine=true)(32 x 32)/zygote/CPU/4 thread(s)	14500 ns	12750 ns	1.14
layernorm(2, act=relu, affine=true)(32 x 32)/zygote/CPU/8 thread(s)	15625 ns	15125 ns	1.03
layernorm(2, act=relu, affine=true)(32 x 32)/zygote/CPU/1 thread(s)	15708 ns	14625.5 ns	1.07
layernorm(2, act=relu, affine=true)(32 x 32)/zygote/GPU/CUDA	889477 ns	923489 ns	0.96
layernorm(2, act=relu, affine=true)(32 x 32)/zygote/GPU/oneAPI	43796054 ns	42519536.5 ns	1.03
layernorm(2, act=relu, affine=true)(32 x 32)/zygote/GPU/AMDGPU	430555 ns	407432 ns	1.06
layernorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	23625 ns	25625 ns	0.92
layernorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	24834 ns	23666 ns	1.05
layernorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	25000 ns	29417 ns	0.85
layernorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	23896 ns	24041 ns	0.99
layernorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/GPU/CUDA	185493.5 ns	186240.5 ns	1.00
layernorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	7687837.5 ns	7554376 ns	1.02
layernorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	115711.5 ns	120505 ns	0.96
layernorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	153209 ns	152187 ns	1.01
layernorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	145583.5 ns	145250 ns	1.00
layernorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	153291 ns	146917 ns	1.04
layernorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	104333 ns	103958 ns	1.00
layernorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	1016908 ns	1013659 ns	1.00
layernorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	42426309 ns	44493070 ns	0.95
layernorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	578946 ns	535240 ns	1.08
layernorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	74292 ns	74583 ns	1.00
layernorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	74354.5 ns	79584 ns	0.93
layernorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	78334 ns	76791.5 ns	1.02
layernorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	74375 ns	76083 ns	0.98
layernorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/CUDA	191164.5 ns	190594.5 ns	1.00
layernorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	7963971 ns	7364811 ns	1.08
layernorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	123771 ns	121316.5 ns	1.02
layernorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	319458 ns	273562.5 ns	1.17
layernorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	311000 ns	304084 ns	1.02
layernorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	304750 ns	303333 ns	1.00
layernorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	274792 ns	307583 ns	0.89
layernorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	1022252 ns	1045024 ns	0.98
layernorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	41781714 ns	39473308 ns	1.06
layernorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	691217 ns	624192 ns	1.11
layernorm(2, act=gelu, affine=true)(32 x 32)/forward/CPU/2 thread(s)	13104.5 ns	12417 ns	1.06
layernorm(2, act=gelu, affine=true)(32 x 32)/forward/CPU/4 thread(s)	13020.5 ns	12896 ns	1.01
layernorm(2, act=gelu, affine=true)(32 x 32)/forward/CPU/8 thread(s)	14062.5 ns	14000 ns	1.00
layernorm(2, act=gelu, affine=true)(32 x 32)/forward/CPU/1 thread(s)	13375 ns	12500 ns	1.07
layernorm(2, act=gelu, affine=true)(32 x 32)/forward/GPU/CUDA	137424.5 ns	138416 ns	0.99
layernorm(2, act=gelu, affine=true)(32 x 32)/forward/GPU/oneAPI	5742536 ns	5479910 ns	1.05
layernorm(2, act=gelu, affine=true)(32 x 32)/forward/GPU/AMDGPU	235003 ns	226152 ns	1.04
layernorm(2, act=gelu, affine=true)(32 x 32)/zygote/CPU/2 thread(s)	26520.5 ns	27792 ns	0.95
layernorm(2, act=gelu, affine=true)(32 x 32)/zygote/CPU/4 thread(s)	25209 ns	26458 ns	0.95
layernorm(2, act=gelu, affine=true)(32 x 32)/zygote/CPU/8 thread(s)	26625 ns	28437.5 ns	0.94
layernorm(2, act=gelu, affine=true)(32 x 32)/zygote/CPU/1 thread(s)	27062.5 ns	33937.5 ns	0.80
layernorm(2, act=gelu, affine=true)(32 x 32)/zygote/GPU/CUDA	932532.5 ns	924126.5 ns	1.01
layernorm(2, act=gelu, affine=true)(32 x 32)/zygote/GPU/oneAPI	41660148 ns	42086872 ns	0.99
layernorm(2, act=gelu, affine=true)(32 x 32)/zygote/GPU/AMDGPU	697632 ns	610976 ns	1.14
groupnorm(2, act=gelu, affine=true)(32 x 32)/forward/CPU/2 thread(s)	11875 ns	11124.5 ns	1.07
groupnorm(2, act=gelu, affine=true)(32 x 32)/forward/CPU/4 thread(s)	10584 ns	10333 ns	1.02
groupnorm(2, act=gelu, affine=true)(32 x 32)/forward/CPU/8 thread(s)	12791 ns	12479.5 ns	1.02
groupnorm(2, act=gelu, affine=true)(32 x 32)/forward/CPU/1 thread(s)	11125 ns	11125 ns	1
groupnorm(2, act=gelu, affine=true)(32 x 32)/forward/GPU/CUDA	118662.5 ns	118543.5 ns	1.00
groupnorm(2, act=gelu, affine=true)(32 x 32)/forward/GPU/oneAPI	3679682 ns	3443799.5 ns	1.07
groupnorm(2, act=gelu, affine=true)(32 x 32)/forward/GPU/AMDGPU	237602 ns	233176 ns	1.02
groupnorm(2, act=gelu, affine=true)(32 x 32)/zygote/CPU/2 thread(s)	23209 ns	22291.5 ns	1.04
groupnorm(2, act=gelu, affine=true)(32 x 32)/zygote/CPU/4 thread(s)	23041 ns	22417 ns	1.03
groupnorm(2, act=gelu, affine=true)(32 x 32)/zygote/CPU/8 thread(s)	23208.5 ns	24167 ns	0.96
groupnorm(2, act=gelu, affine=true)(32 x 32)/zygote/CPU/1 thread(s)	22084 ns	28562.5 ns	0.77
groupnorm(2, act=gelu, affine=true)(32 x 32)/zygote/GPU/CUDA	677613.5 ns	668341 ns	1.01
groupnorm(2, act=gelu, affine=true)(32 x 32)/zygote/GPU/oneAPI	22594824 ns	21034051 ns	1.07
groupnorm(2, act=gelu, affine=true)(32 x 32)/zygote/GPU/AMDGPU	677387 ns	569113 ns	1.19
groupnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	63854.5 ns	68709 ns	0.93
groupnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	64000 ns	62750 ns	1.02
groupnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	67208 ns	67520.5 ns	1.00
groupnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	62958 ns	64417 ns	0.98
groupnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/CUDA	102574 ns	102389 ns	1.00
groupnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	3618527 ns	3441143 ns	1.05
groupnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	236212 ns	230751 ns	1.02
groupnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	466729 ns	506375 ns	0.92
groupnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	477417 ns	510167 ns	0.94
groupnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	503895.5 ns	475209 ns	1.06
groupnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	474459 ns	647896 ns	0.73
groupnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	492357 ns	492781 ns	1.00
groupnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	21057710 ns	20664230 ns	1.02
groupnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	717612.5 ns	593680 ns	1.21
layernorm(2, act=identity, affine=true)(32 x 32)/forward/CPU/2 thread(s)	7437.5 ns	7958 ns	0.93
layernorm(2, act=identity, affine=true)(32 x 32)/forward/CPU/4 thread(s)	7291 ns	6750 ns	1.08
layernorm(2, act=identity, affine=true)(32 x 32)/forward/CPU/8 thread(s)	8500 ns	8208 ns	1.04
layernorm(2, act=identity, affine=true)(32 x 32)/forward/CPU/1 thread(s)	7187 ns	7562.5 ns	0.95
layernorm(2, act=identity, affine=true)(32 x 32)/forward/GPU/CUDA	136181.5 ns	137965 ns	0.99
layernorm(2, act=identity, affine=true)(32 x 32)/forward/GPU/oneAPI	5536801 ns	5508177.5 ns	1.01
layernorm(2, act=identity, affine=true)(32 x 32)/forward/GPU/AMDGPU	59160 ns	62687 ns	0.94
layernorm(2, act=identity, affine=true)(32 x 32)/zygote/CPU/2 thread(s)	13125 ns	16125 ns	0.81
layernorm(2, act=identity, affine=true)(32 x 32)/zygote/CPU/4 thread(s)	13542 ns	16250 ns	0.83
layernorm(2, act=identity, affine=true)(32 x 32)/zygote/CPU/8 thread(s)	15625 ns	16250 ns	0.96
layernorm(2, act=identity, affine=true)(32 x 32)/zygote/CPU/1 thread(s)	15041 ns	14833 ns	1.01
layernorm(2, act=identity, affine=true)(32 x 32)/zygote/GPU/CUDA	898966 ns	900927 ns	1.00
layernorm(2, act=identity, affine=true)(32 x 32)/zygote/GPU/oneAPI	39073495 ns	39349971 ns	0.99
layernorm(2, act=identity, affine=true)(32 x 32)/zygote/GPU/AMDGPU	401324 ns	388286 ns	1.03
batchedmm(512, Bsize=4)/forward/CPU/2 thread(s)	6152896 ns	6150354 ns	1.00
batchedmm(512, Bsize=4)/forward/CPU/4 thread(s)	6373625 ns	6368167 ns	1.00
batchedmm(512, Bsize=4)/forward/CPU/8 thread(s)	6374875 ns	6373937.5 ns	1.00
batchedmm(512, Bsize=4)/forward/CPU/1 thread(s)	11911750 ns	11915167 ns	1.00
batchedmm(512, Bsize=4)/forward/GPU/CUDA	348505 ns	345749 ns	1.01
batchedmm(512, Bsize=4)/forward/GPU/oneAPI	52576961 ns	49052559 ns	1.07
batchedmm(512, Bsize=4)/forward/GPU/AMDGPU	305468.5 ns	388426 ns	0.79
batchedmm(512, Bsize=4)/zygote/CPU/2 thread(s)	19051437.5 ns	19083437.5 ns	1.00
batchedmm(512, Bsize=4)/zygote/CPU/4 thread(s)	19952875 ns	19960479.5 ns	1.00
batchedmm(512, Bsize=4)/zygote/CPU/8 thread(s)	20023416.5 ns	19966834 ns	1.00
batchedmm(512, Bsize=4)/zygote/CPU/1 thread(s)	36511083.5 ns	37142104 ns	0.98
batchedmm(512, Bsize=4)/zygote/GPU/CUDA	1017592 ns	1072087 ns	0.95
batchedmm(512, Bsize=4)/zygote/GPU/oneAPI	77843031 ns	78467188 ns	0.99
batchedmm(512, Bsize=4)/zygote/GPU/AMDGPU	1167942 ns	1035750.5 ns	1.13
dense(2, bias=true, act=gelu)(2 x 128)/forward/CPU/2 thread(s)	959 ns	958 ns	1.00
dense(2, bias=true, act=gelu)(2 x 128)/forward/CPU/4 thread(s)	1041 ns	1000 ns	1.04
dense(2, bias=true, act=gelu)(2 x 128)/forward/CPU/8 thread(s)	1000 ns	1042 ns	0.96
dense(2, bias=true, act=gelu)(2 x 128)/forward/CPU/1 thread(s)	959 ns	958 ns	1.00
dense(2, bias=true, act=gelu)(2 x 128)/forward/GPU/CUDA	23689.5 ns	23415 ns	1.01
dense(2, bias=true, act=gelu)(2 x 128)/forward/GPU/oneAPI	2126340 ns	2079171 ns	1.02
dense(2, bias=true, act=gelu)(2 x 128)/forward/GPU/AMDGPU	210263 ns	200906 ns	1.05
dense(2, bias=true, act=gelu)(2 x 128)/zygote/CPU/2 thread(s)	3958 ns	3917 ns	1.01
dense(2, bias=true, act=gelu)(2 x 128)/zygote/CPU/4 thread(s)	4083 ns	4000 ns	1.02
dense(2, bias=true, act=gelu)(2 x 128)/zygote/CPU/8 thread(s)	4125 ns	4041 ns	1.02
dense(2, bias=true, act=gelu)(2 x 128)/zygote/CPU/1 thread(s)	3917 ns	5458 ns	0.72
dense(2, bias=true, act=gelu)(2 x 128)/zygote/GPU/CUDA	284075 ns	270573.5 ns	1.05
dense(2, bias=true, act=gelu)(2 x 128)/zygote/GPU/oneAPI	10799500.5 ns	10484095 ns	1.03
dense(2, bias=true, act=gelu)(2 x 128)/zygote/GPU/AMDGPU	625312 ns	486775 ns	1.28
groupnorm(2, act=relu, affine=true)(4 x 32)/forward/CPU/2 thread(s)	7583 ns	8687 ns	0.87
groupnorm(2, act=relu, affine=true)(4 x 32)/forward/CPU/4 thread(s)	7750.5 ns	7459 ns	1.04
groupnorm(2, act=relu, affine=true)(4 x 32)/forward/CPU/8 thread(s)	9500 ns	9334 ns	1.02
groupnorm(2, act=relu, affine=true)(4 x 32)/forward/CPU/1 thread(s)	7562.5 ns	7834 ns	0.97
groupnorm(2, act=relu, affine=true)(4 x 32)/forward/GPU/CUDA	117941 ns	116220 ns	1.01
groupnorm(2, act=relu, affine=true)(4 x 32)/forward/GPU/oneAPI	3465578 ns	3435001.5 ns	1.01
groupnorm(2, act=relu, affine=true)(4 x 32)/forward/GPU/AMDGPU	66261 ns	71133 ns	0.93
groupnorm(2, act=relu, affine=true)(4 x 32)/zygote/CPU/2 thread(s)	13125 ns	12125 ns	1.08
groupnorm(2, act=relu, affine=true)(4 x 32)/zygote/CPU/4 thread(s)	11834 ns	11958 ns	0.99
groupnorm(2, act=relu, affine=true)(4 x 32)/zygote/CPU/8 thread(s)	13208 ns	13000 ns	1.02
groupnorm(2, act=relu, affine=true)(4 x 32)/zygote/CPU/1 thread(s)	12229.5 ns	11750 ns	1.04
groupnorm(2, act=relu, affine=true)(4 x 32)/zygote/GPU/CUDA	624724 ns	609643.5 ns	1.02
groupnorm(2, act=relu, affine=true)(4 x 32)/zygote/GPU/oneAPI	22359924 ns	21784602 ns	1.03
groupnorm(2, act=relu, affine=true)(4 x 32)/zygote/GPU/AMDGPU	355344 ns	341729 ns	1.04
dense(2, bias=false, act=relu)(2 x 128)/forward/CPU/2 thread(s)	292 ns	292 ns	1
dense(2, bias=false, act=relu)(2 x 128)/forward/CPU/4 thread(s)	292 ns	292 ns	1
dense(2, bias=false, act=relu)(2 x 128)/forward/CPU/8 thread(s)	333 ns	292 ns	1.14
dense(2, bias=false, act=relu)(2 x 128)/forward/CPU/1 thread(s)	333 ns	291 ns	1.14
dense(2, bias=false, act=relu)(2 x 128)/forward/GPU/CUDA	22660.5 ns	22413 ns	1.01
dense(2, bias=false, act=relu)(2 x 128)/forward/GPU/oneAPI	2090808 ns	2035110 ns	1.03
dense(2, bias=false, act=relu)(2 x 128)/forward/GPU/AMDGPU	46931 ns	44053 ns	1.07
dense(2, bias=false, act=relu)(2 x 128)/zygote/CPU/2 thread(s)	3000 ns	3000 ns	1
dense(2, bias=false, act=relu)(2 x 128)/zygote/CPU/4 thread(s)	3042 ns	2917 ns	1.04
dense(2, bias=false, act=relu)(2 x 128)/zygote/CPU/8 thread(s)	3334 ns	3208 ns	1.04
dense(2, bias=false, act=relu)(2 x 128)/zygote/CPU/1 thread(s)	3167 ns	2916 ns	1.09
dense(2, bias=false, act=relu)(2 x 128)/zygote/GPU/CUDA	202209.5 ns	194923.5 ns	1.04
dense(2, bias=false, act=relu)(2 x 128)/zygote/GPU/oneAPI	9381105 ns	9225861.5 ns	1.02
dense(2, bias=false, act=relu)(2 x 128)/zygote/GPU/AMDGPU	156911.5 ns	154488.5 ns	1.02
groupnorm(2, act=gelu, affine=false)(32 x 32)/forward/CPU/2 thread(s)	11917 ns	11625 ns	1.03
groupnorm(2, act=gelu, affine=false)(32 x 32)/forward/CPU/4 thread(s)	11708 ns	10500 ns	1.12
groupnorm(2, act=gelu, affine=false)(32 x 32)/forward/CPU/8 thread(s)	12583 ns	12875 ns	0.98
groupnorm(2, act=gelu, affine=false)(32 x 32)/forward/CPU/1 thread(s)	11542 ns	11875 ns	0.97
groupnorm(2, act=gelu, affine=false)(32 x 32)/forward/GPU/CUDA	117102 ns	115370 ns	1.02
groupnorm(2, act=gelu, affine=false)(32 x 32)/forward/GPU/oneAPI	3369882 ns	3433218 ns	0.98
groupnorm(2, act=gelu, affine=false)(32 x 32)/forward/GPU/AMDGPU	234642.5 ns	231793 ns	1.01
groupnorm(2, act=gelu, affine=false)(32 x 32)/zygote/CPU/2 thread(s)	22229 ns	22667 ns	0.98
groupnorm(2, act=gelu, affine=false)(32 x 32)/zygote/CPU/4 thread(s)	21333 ns	22104.5 ns	0.97
groupnorm(2, act=gelu, affine=false)(32 x 32)/zygote/CPU/8 thread(s)	24542 ns	23625 ns	1.04
groupnorm(2, act=gelu, affine=false)(32 x 32)/zygote/CPU/1 thread(s)	21334 ns	26729 ns	0.80
groupnorm(2, act=gelu, affine=false)(32 x 32)/zygote/GPU/CUDA	575582 ns	555861 ns	1.04
groupnorm(2, act=gelu, affine=false)(32 x 32)/zygote/GPU/oneAPI	19911746 ns	20482208 ns	0.97
groupnorm(2, act=gelu, affine=false)(32 x 32)/zygote/GPU/AMDGPU	654527 ns	545740 ns	1.20
dense(32, bias=true, act=relu)(32 x 128)/forward/CPU/2 thread(s)	4208 ns	4334 ns	0.97
dense(32, bias=true, act=relu)(32 x 128)/forward/CPU/4 thread(s)	4209 ns	4333 ns	0.97
dense(32, bias=true, act=relu)(32 x 128)/forward/CPU/8 thread(s)	4291 ns	4208 ns	1.02
dense(32, bias=true, act=relu)(32 x 128)/forward/CPU/1 thread(s)	4208 ns	4250 ns	0.99
dense(32, bias=true, act=relu)(32 x 128)/forward/GPU/CUDA	24983 ns	23923 ns	1.04
dense(32, bias=true, act=relu)(32 x 128)/forward/GPU/oneAPI	2175425.5 ns	2205811 ns	0.99
dense(32, bias=true, act=relu)(32 x 128)/forward/GPU/AMDGPU	48880 ns	44864 ns	1.09
dense(32, bias=true, act=relu)(32 x 128)/zygote/CPU/2 thread(s)	16250 ns	16500 ns	0.98
dense(32, bias=true, act=relu)(32 x 128)/zygote/CPU/4 thread(s)	16250 ns	16333 ns	0.99
dense(32, bias=true, act=relu)(32 x 128)/zygote/CPU/8 thread(s)	16250 ns	16166 ns	1.01
dense(32, bias=true, act=relu)(32 x 128)/zygote/CPU/1 thread(s)	16083 ns	16292 ns	0.99
dense(32, bias=true, act=relu)(32 x 128)/zygote/GPU/CUDA	326969 ns	319806 ns	1.02
dense(32, bias=true, act=relu)(32 x 128)/zygote/GPU/oneAPI	12126578 ns	10190777 ns	1.19
dense(32, bias=true, act=relu)(32 x 128)/zygote/GPU/AMDGPU	210562 ns	186077 ns	1.13
batchnorm(2, act=gelu, affine=false)(32 x 32)/forward/CPU/2 thread(s)	2000 ns	2125 ns	0.94
batchnorm(2, act=gelu, affine=false)(32 x 32)/forward/CPU/4 thread(s)	2083 ns	2084 ns	1.00
batchnorm(2, act=gelu, affine=false)(32 x 32)/forward/CPU/8 thread(s)	2167 ns	2209 ns	0.98
batchnorm(2, act=gelu, affine=false)(32 x 32)/forward/CPU/1 thread(s)	2125 ns	2000 ns	1.06
batchnorm(2, act=gelu, affine=false)(32 x 32)/forward/GPU/CUDA	36547 ns	35327 ns	1.03
batchnorm(2, act=gelu, affine=false)(32 x 32)/forward/GPU/oneAPI	1188039 ns	1213779 ns	0.98
batchnorm(2, act=gelu, affine=false)(32 x 32)/forward/GPU/AMDGPU	208582 ns	199242 ns	1.05
batchnorm(2, act=gelu, affine=false)(32 x 32)/zygote/CPU/2 thread(s)	18500 ns	17104 ns	1.08
batchnorm(2, act=gelu, affine=false)(32 x 32)/zygote/CPU/4 thread(s)	16624.5 ns	20167 ns	0.82
batchnorm(2, act=gelu, affine=false)(32 x 32)/zygote/CPU/8 thread(s)	17354.5 ns	19000 ns	0.91
batchnorm(2, act=gelu, affine=false)(32 x 32)/zygote/CPU/1 thread(s)	19688 ns	23083.5 ns	0.85
batchnorm(2, act=gelu, affine=false)(32 x 32)/zygote/GPU/CUDA	291021.5 ns	284984 ns	1.02
batchnorm(2, act=gelu, affine=false)(32 x 32)/zygote/GPU/oneAPI	19477895 ns	18211018 ns	1.07
batchnorm(2, act=gelu, affine=false)(32 x 32)/zygote/GPU/AMDGPU	687748 ns	583431 ns	1.18
batchedmm(16, Bsize=512)/forward/CPU/2 thread(s)	59437.5 ns	59458 ns	1.00
batchedmm(16, Bsize=512)/forward/CPU/4 thread(s)	64125 ns	65666 ns	0.98
batchedmm(16, Bsize=512)/forward/CPU/8 thread(s)	66375 ns	66125 ns	1.00
batchedmm(16, Bsize=512)/forward/CPU/1 thread(s)	51125 ns	52833 ns	0.97
batchedmm(16, Bsize=512)/forward/GPU/CUDA	66729 ns	66304 ns	1.01
batchedmm(16, Bsize=512)/forward/GPU/oneAPI	84867273.5 ns	87707222.5 ns	0.97
batchedmm(16, Bsize=512)/forward/GPU/AMDGPU	98541 ns	110241 ns	0.89
batchedmm(16, Bsize=512)/zygote/CPU/2 thread(s)	132875 ns	153041 ns	0.87
batchedmm(16, Bsize=512)/zygote/CPU/4 thread(s)	110729.5 ns	155229 ns	0.71
batchedmm(16, Bsize=512)/zygote/CPU/8 thread(s)	163458.5 ns	130209 ns	1.26
batchedmm(16, Bsize=512)/zygote/CPU/1 thread(s)	232750 ns	286334 ns	0.81
batchedmm(16, Bsize=512)/zygote/GPU/CUDA	214764 ns	210129.5 ns	1.02
batchedmm(16, Bsize=512)/zygote/GPU/oneAPI	145741629.5 ns	149924497 ns	0.97
batchedmm(16, Bsize=512)/zygote/GPU/AMDGPU	552656 ns	511145 ns	1.08
groupnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	81917 ns	106521 ns	0.77
groupnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	86646 ns	78958 ns	1.10
groupnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	89250 ns	84042 ns	1.06
groupnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	81916 ns	115521 ns	0.71
groupnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/GPU/CUDA	193747 ns	191513.5 ns	1.01
groupnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	5265023 ns	5334020 ns	0.99
groupnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	169752 ns	267630 ns	0.63
groupnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	1909063 ns	1894896 ns	1.01
groupnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	1910500 ns	1902375 ns	1.00
groupnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	1920458 ns	1878334 ns	1.02
groupnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	1930417 ns	1895250 ns	1.02
groupnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	515414.5 ns	507442 ns	1.02
groupnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	26285784 ns	28152566.5 ns	0.93
groupnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	918784.5 ns	825763 ns	1.11
dense(2, bias=true, act=identity)(2 x 128)/forward/CPU/2 thread(s)	292 ns	292 ns	1
dense(2, bias=true, act=identity)(2 x 128)/forward/CPU/4 thread(s)	292 ns	292 ns	1
dense(2, bias=true, act=identity)(2 x 128)/forward/CPU/8 thread(s)	292 ns	292 ns	1
dense(2, bias=true, act=identity)(2 x 128)/forward/CPU/1 thread(s)	291 ns	291 ns	1
dense(2, bias=true, act=identity)(2 x 128)/forward/GPU/CUDA	22081 ns	21516 ns	1.03
dense(2, bias=true, act=identity)(2 x 128)/forward/GPU/oneAPI	2134831.5 ns	2100524 ns	1.02
dense(2, bias=true, act=identity)(2 x 128)/forward/GPU/AMDGPU	40930 ns	35507 ns	1.15
dense(2, bias=true, act=identity)(2 x 128)/zygote/CPU/2 thread(s)	1833 ns	1792 ns	1.02
dense(2, bias=true, act=identity)(2 x 128)/zygote/CPU/4 thread(s)	1875 ns	1875 ns	1
dense(2, bias=true, act=identity)(2 x 128)/zygote/CPU/8 thread(s)	1834 ns	1834 ns	1
dense(2, bias=true, act=identity)(2 x 128)/zygote/CPU/1 thread(s)	1792 ns	1833 ns	0.98
dense(2, bias=true, act=identity)(2 x 128)/zygote/GPU/CUDA	252925 ns	245735 ns	1.03
dense(2, bias=true, act=identity)(2 x 128)/zygote/GPU/oneAPI	10692380.5 ns	9780504 ns	1.09
dense(2, bias=true, act=identity)(2 x 128)/zygote/GPU/AMDGPU	182692 ns	164548 ns	1.11
groupnorm(2, act=gelu, affine=false)(4 x 32)/forward/CPU/2 thread(s)	9458 ns	10916 ns	0.87
groupnorm(2, act=gelu, affine=false)(4 x 32)/forward/CPU/4 thread(s)	9188 ns	8291 ns	1.11
groupnorm(2, act=gelu, affine=false)(4 x 32)/forward/CPU/8 thread(s)	10792 ns	11146 ns	0.97
groupnorm(2, act=gelu, affine=false)(4 x 32)/forward/CPU/1 thread(s)	8417 ns	9500 ns	0.89
groupnorm(2, act=gelu, affine=false)(4 x 32)/forward/GPU/CUDA	117162 ns	114788 ns	1.02
groupnorm(2, act=gelu, affine=false)(4 x 32)/forward/GPU/oneAPI	3311573.5 ns	3351587 ns	0.99
groupnorm(2, act=gelu, affine=false)(4 x 32)/forward/GPU/AMDGPU	237482 ns	232004 ns	1.02
groupnorm(2, act=gelu, affine=false)(4 x 32)/zygote/CPU/2 thread(s)	9458 ns	8916 ns	1.06
groupnorm(2, act=gelu, affine=false)(4 x 32)/zygote/CPU/4 thread(s)	8875 ns	8854.5 ns	1.00
groupnorm(2, act=gelu, affine=false)(4 x 32)/zygote/CPU/8 thread(s)	11833 ns	10917 ns	1.08
groupnorm(2, act=gelu, affine=false)(4 x 32)/zygote/CPU/1 thread(s)	8584 ns	9583 ns	0.90
groupnorm(2, act=gelu, affine=false)(4 x 32)/zygote/GPU/CUDA	505476 ns	491693 ns	1.03
groupnorm(2, act=gelu, affine=false)(4 x 32)/zygote/GPU/oneAPI	19448705 ns	19969043 ns	0.97
groupnorm(2, act=gelu, affine=false)(4 x 32)/zygote/GPU/AMDGPU	634061.5 ns	536332 ns	1.18
batchnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	57667 ns	57958 ns	0.99
batchnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	47167 ns	46625 ns	1.01
batchnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	46458 ns	46750 ns	0.99
batchnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	81542 ns	83166 ns	0.98
batchnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/GPU/CUDA	39572.5 ns	38476.5 ns	1.03
batchnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	1348881 ns	1460287 ns	0.92
batchnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	77771 ns	71814 ns	1.08
batchnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	1918812 ns	1905145.5 ns	1.01
batchnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	1974208.5 ns	1949542 ns	1.01
batchnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	1982521 ns	1958500 ns	1.01
batchnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	1878771 ns	1874958 ns	1.00
batchnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	218975.5 ns	212675 ns	1.03
batchnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	31988008.5 ns	33332615 ns	0.96
batchnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1006995.5 ns	968925.5 ns	1.04
layernorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	267167 ns	267500 ns	1.00
layernorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	270042 ns	271479.5 ns	0.99
layernorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	270125 ns	271209 ns	1.00
layernorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	267500 ns	268209 ns	1.00
layernorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/CUDA	199236.5 ns	194219.5 ns	1.03
layernorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	7576739 ns	7638787 ns	0.99
layernorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	283863 ns	271267 ns	1.05
layernorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	601875 ns	585333.5 ns	1.03
layernorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	592188 ns	600292 ns	0.99
layernorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	688500 ns	671042 ns	1.03
layernorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	585896 ns	845604.5 ns	0.69
layernorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	1011793 ns	991966 ns	1.02
layernorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	43904369 ns	42952243 ns	1.02
layernorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	901014.5 ns	831153 ns	1.08
layernorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	2191333 ns	2211666 ns	0.99
layernorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	2189750 ns	2203958 ns	0.99
layernorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	2188208 ns	2229083 ns	0.98
layernorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	2218500 ns	2173792 ns	1.02
layernorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/CUDA	156704.5 ns	161646 ns	0.97
layernorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	8448752 ns	8668502.5 ns	0.97
layernorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	408114.5 ns	470965 ns	0.87
layernorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	5478916 ns	5493104.5 ns	1.00
layernorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	5506458.5 ns	5515875 ns	1.00
layernorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	5476312.5 ns	5526542 ns	0.99
layernorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	5505042 ns	6852458 ns	0.80
layernorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	932002 ns	959137 ns	0.97
layernorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	50568026 ns	49532486 ns	1.02
layernorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1719777 ns	1437405 ns	1.20
dense(512, bias=true, act=gelu)(512 x 128)/forward/CPU/2 thread(s)	478417 ns	478292 ns	1.00
dense(512, bias=true, act=gelu)(512 x 128)/forward/CPU/4 thread(s)	346417 ns	345625 ns	1.00
dense(512, bias=true, act=gelu)(512 x 128)/forward/CPU/8 thread(s)	346833 ns	346750 ns	1.00
dense(512, bias=true, act=gelu)(512 x 128)/forward/CPU/1 thread(s)	909416 ns	908542 ns	1.00
dense(512, bias=true, act=gelu)(512 x 128)/forward/GPU/CUDA	45620.5 ns	46909 ns	0.97
dense(512, bias=true, act=gelu)(512 x 128)/forward/GPU/oneAPI	849567 ns	871386 ns	0.97
dense(512, bias=true, act=gelu)(512 x 128)/forward/GPU/AMDGPU	245423 ns	393175 ns	0.62
dense(512, bias=true, act=gelu)(512 x 128)/zygote/CPU/2 thread(s)	2168937.5 ns	2137500 ns	1.01
dense(512, bias=true, act=gelu)(512 x 128)/zygote/CPU/4 thread(s)	1865604 ns	1869334 ns	1.00
dense(512, bias=true, act=gelu)(512 x 128)/zygote/CPU/8 thread(s)	1853875 ns	1859271 ns	1.00
dense(512, bias=true, act=gelu)(512 x 128)/zygote/CPU/1 thread(s)	3118125 ns	3380209 ns	0.92
dense(512, bias=true, act=gelu)(512 x 128)/zygote/GPU/CUDA	258815 ns	264095.5 ns	0.98
dense(512, bias=true, act=gelu)(512 x 128)/zygote/GPU/oneAPI	15172873 ns	13390420 ns	1.13
dense(512, bias=true, act=gelu)(512 x 128)/zygote/GPU/AMDGPU	774888 ns	632907.5 ns	1.22
batchnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	57916.5 ns	57458 ns	1.01
batchnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	46625 ns	46166 ns	1.01
batchnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	46417 ns	46250 ns	1.00
batchnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	83083 ns	78667 ns	1.06
batchnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/CUDA	28412 ns	28560 ns	0.99
batchnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	1440678 ns	1394875.5 ns	1.03
batchnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	77121 ns	73147 ns	1.05
batchnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	2032479.5 ns	2029292 ns	1.00
batchnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	2090834 ns	2078187.5 ns	1.01
batchnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	2093437.5 ns	2063250 ns	1.01
batchnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	1970145.5 ns	1963958 ns	1.00
batchnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	225176 ns	230846.5 ns	0.98
batchnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	36084585 ns	36347331 ns	0.99
batchnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1040890.5 ns	980522 ns	1.06
batchnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	58000 ns	58083.5 ns	1.00
batchnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	47250 ns	46584 ns	1.01
batchnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	47042 ns	46917 ns	1.00
batchnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	82500 ns	79958 ns	1.03
batchnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/GPU/CUDA	47929 ns	48944 ns	0.98
batchnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	802274 ns	829446 ns	0.97
batchnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	68761 ns	71428.5 ns	0.96
batchnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	1925083 ns	1871729 ns	1.03
batchnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	1980416.5 ns	1973604 ns	1.00
batchnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	1983458.5 ns	1944167 ns	1.02
batchnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	1899708 ns	1876792 ns	1.01
batchnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	232135.5 ns	238010 ns	0.98
batchnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	17785153 ns	18705710.5 ns	0.95
batchnorm(4, act=identity, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	917619.5 ns	881607.5 ns	1.04
batchnorm(2, act=identity, affine=false)(4 x 32)/forward/CPU/2 thread(s)	292 ns	292 ns	1
batchnorm(2, act=identity, affine=false)(4 x 32)/forward/CPU/4 thread(s)	292 ns	292 ns	1
batchnorm(2, act=identity, affine=false)(4 x 32)/forward/CPU/8 thread(s)	417 ns	375 ns	1.11
batchnorm(2, act=identity, affine=false)(4 x 32)/forward/CPU/1 thread(s)	292 ns	291 ns	1.00
batchnorm(2, act=identity, affine=false)(4 x 32)/forward/GPU/CUDA	34988 ns	34878 ns	1.00
batchnorm(2, act=identity, affine=false)(4 x 32)/forward/GPU/oneAPI	1197187 ns	1190778.5 ns	1.01
batchnorm(2, act=identity, affine=false)(4 x 32)/forward/GPU/AMDGPU	48631 ns	47028 ns	1.03
batchnorm(2, act=identity, affine=false)(4 x 32)/zygote/CPU/2 thread(s)	7166 ns	6270.5 ns	1.14
batchnorm(2, act=identity, affine=false)(4 x 32)/zygote/CPU/4 thread(s)	6229 ns	6187.5 ns	1.01
batchnorm(2, act=identity, affine=false)(4 x 32)/zygote/CPU/8 thread(s)	7375 ns	7375 ns	1
batchnorm(2, act=identity, affine=false)(4 x 32)/zygote/CPU/1 thread(s)	6833 ns	6125 ns	1.12
batchnorm(2, act=identity, affine=false)(4 x 32)/zygote/GPU/CUDA	204201 ns	211705.5 ns	0.96
batchnorm(2, act=identity, affine=false)(4 x 32)/zygote/GPU/oneAPI	20381663 ns	20119098 ns	1.01
batchnorm(2, act=identity, affine=false)(4 x 32)/zygote/GPU/AMDGPU	368334 ns	332741 ns	1.11
dense(2, bias=false, act=identity)(2 x 128)/forward/CPU/2 thread(s)	250 ns	250 ns	1
dense(2, bias=false, act=identity)(2 x 128)/forward/CPU/4 thread(s)	291 ns	291 ns	1
dense(2, bias=false, act=identity)(2 x 128)/forward/CPU/8 thread(s)	292 ns	292 ns	1
dense(2, bias=false, act=identity)(2 x 128)/forward/CPU/1 thread(s)	291 ns	250 ns	1.16
dense(2, bias=false, act=identity)(2 x 128)/forward/GPU/CUDA	31750 ns	32902 ns	0.96
dense(2, bias=false, act=identity)(2 x 128)/forward/GPU/oneAPI	1243003 ns	1224139 ns	1.02
dense(2, bias=false, act=identity)(2 x 128)/forward/GPU/AMDGPU	37010.5 ns	36327 ns	1.02
dense(2, bias=false, act=identity)(2 x 128)/zygote/CPU/2 thread(s)	2750 ns	2667 ns	1.03
dense(2, bias=false, act=identity)(2 x 128)/zygote/CPU/4 thread(s)	2708 ns	2667 ns	1.02
dense(2, bias=false, act=identity)(2 x 128)/zygote/CPU/8 thread(s)	3458 ns	4292 ns	0.81
dense(2, bias=false, act=identity)(2 x 128)/zygote/CPU/1 thread(s)	3292 ns	3167 ns	1.04
dense(2, bias=false, act=identity)(2 x 128)/zygote/GPU/CUDA	184588.5 ns	187662.5 ns	0.98
dense(2, bias=false, act=identity)(2 x 128)/zygote/GPU/oneAPI	8227541 ns	5673429 ns	1.45
dense(2, bias=false, act=identity)(2 x 128)/zygote/GPU/AMDGPU	149351 ns	136635 ns	1.09
groupnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	495354 ns	467208 ns	1.06
groupnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	492666 ns	469417 ns	1.05
groupnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	465708 ns	466875 ns	1.00
groupnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	459375 ns	464979.5 ns	0.99
groupnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/CUDA	135301 ns	137312 ns	0.99
groupnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	5838247 ns	5812904.5 ns	1.00
groupnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	324193 ns	361475 ns	0.90
groupnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	4083792 ns	4027749.5 ns	1.01
groupnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	4070187.5 ns	4071500 ns	1.00
groupnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	4078000 ns	4067417 ns	1.00
groupnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	4075916.5 ns	5516750 ns	0.74
groupnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	676920 ns	690445 ns	0.98
groupnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	32374547 ns	32063716 ns	1.01
groupnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1471415 ns	1091915 ns	1.35
batchedmm(512, Bsize=32)/forward/CPU/2 thread(s)	49815292 ns	49879250 ns	1.00
batchedmm(512, Bsize=32)/forward/CPU/4 thread(s)	35545937.5 ns	35487583 ns	1.00
batchedmm(512, Bsize=32)/forward/CPU/8 thread(s)	35523625 ns	35512833.5 ns	1.00
batchedmm(512, Bsize=32)/forward/CPU/1 thread(s)	96973125 ns	96974083 ns	1.00
batchedmm(512, Bsize=32)/forward/GPU/CUDA	1622419.5 ns	1622377 ns	1.00
batchedmm(512, Bsize=32)/forward/GPU/oneAPI	55438113 ns	55868634.5 ns	0.99
batchedmm(512, Bsize=32)/forward/GPU/AMDGPU	1055850.5 ns	1579230 ns	0.67
batchedmm(512, Bsize=32)/zygote/CPU/2 thread(s)	154508083.5 ns	154423062.5 ns	1.00
batchedmm(512, Bsize=32)/zygote/CPU/4 thread(s)	112410479 ns	112364750 ns	1.00
batchedmm(512, Bsize=32)/zygote/CPU/8 thread(s)	112319041 ns	112377416 ns	1.00
batchedmm(512, Bsize=32)/zygote/CPU/1 thread(s)	295571917 ns	299989812 ns	0.99
batchedmm(512, Bsize=32)/zygote/GPU/CUDA	6490301 ns	6468945 ns	1.00
batchedmm(512, Bsize=32)/zygote/GPU/oneAPI	129703825.5 ns	126761495 ns	1.02
batchedmm(512, Bsize=32)/zygote/GPU/AMDGPU	5576083 ns	7230228 ns	0.77
bias_activation(32, act=tanh)(32 x 128)/forward/CPU/2 thread(s)	18188 ns	19104.5 ns	0.95
bias_activation(32, act=tanh)(32 x 128)/forward/CPU/4 thread(s)	17500 ns	18375 ns	0.95
bias_activation(32, act=tanh)(32 x 128)/forward/CPU/8 thread(s)	17041 ns	17375.5 ns	0.98
bias_activation(32, act=tanh)(32 x 128)/forward/CPU/1 thread(s)	15083.5 ns	15083 ns	1.00
bias_activation(32, act=tanh)(32 x 128)/forward/GPU/CUDA	19789 ns	19621 ns	1.01
bias_activation(32, act=tanh)(32 x 128)/forward/GPU/oneAPI	1104141 ns	1223248 ns	0.90
bias_activation(32, act=tanh)(32 x 128)/forward/GPU/AMDGPU	26210 ns	28854 ns	0.91
bias_activation(32, act=tanh)(32 x 128)/zygote/CPU/2 thread(s)	10875.5 ns	11062.5 ns	0.98
bias_activation(32, act=tanh)(32 x 128)/zygote/CPU/4 thread(s)	8791 ns	8833 ns	1.00
bias_activation(32, act=tanh)(32 x 128)/zygote/CPU/8 thread(s)	9000 ns	9291 ns	0.97
bias_activation(32, act=tanh)(32 x 128)/zygote/CPU/1 thread(s)	17291.5 ns	17667 ns	0.98
bias_activation(32, act=tanh)(32 x 128)/zygote/GPU/CUDA	247103 ns	252067.5 ns	0.98
bias_activation(32, act=tanh)(32 x 128)/zygote/GPU/oneAPI	10458746 ns	9844493 ns	1.06
bias_activation(32, act=tanh)(32 x 128)/zygote/GPU/AMDGPU	146071.5 ns	138484 ns	1.05
groupnorm(2, act=gelu, affine=true)(4 x 32)/forward/CPU/2 thread(s)	9375 ns	7937.5 ns	1.18
groupnorm(2, act=gelu, affine=true)(4 x 32)/forward/CPU/4 thread(s)	8875 ns	8125 ns	1.09
groupnorm(2, act=gelu, affine=true)(4 x 32)/forward/CPU/8 thread(s)	9979.5 ns	10375 ns	0.96
groupnorm(2, act=gelu, affine=true)(4 x 32)/forward/CPU/1 thread(s)	8291.5 ns	8708 ns	0.95
groupnorm(2, act=gelu, affine=true)(4 x 32)/forward/GPU/CUDA	118486 ns	120230.5 ns	0.99
groupnorm(2, act=gelu, affine=true)(4 x 32)/forward/GPU/oneAPI	3549725 ns	3557828.5 ns	1.00
groupnorm(2, act=gelu, affine=true)(4 x 32)/forward/GPU/AMDGPU	236803 ns	235119 ns	1.01
groupnorm(2, act=gelu, affine=true)(4 x 32)/zygote/CPU/2 thread(s)	10771 ns	9708 ns	1.11
groupnorm(2, act=gelu, affine=true)(4 x 32)/zygote/CPU/4 thread(s)	9312.5 ns	9084 ns	1.03
groupnorm(2, act=gelu, affine=true)(4 x 32)/zygote/CPU/8 thread(s)	10125 ns	9792 ns	1.03
groupnorm(2, act=gelu, affine=true)(4 x 32)/zygote/CPU/1 thread(s)	10208.5 ns	10667 ns	0.96
groupnorm(2, act=gelu, affine=true)(4 x 32)/zygote/GPU/CUDA	587036 ns	599437 ns	0.98
groupnorm(2, act=gelu, affine=true)(4 x 32)/zygote/GPU/oneAPI	22177824 ns	22720103 ns	0.98
groupnorm(2, act=gelu, affine=true)(4 x 32)/zygote/GPU/AMDGPU	658231.5 ns	557070 ns	1.18
groupnorm(2, act=relu, affine=false)(32 x 32)/forward/CPU/2 thread(s)	9229 ns	9291.5 ns	0.99
groupnorm(2, act=relu, affine=false)(32 x 32)/forward/CPU/4 thread(s)	9791 ns	8812.5 ns	1.11
groupnorm(2, act=relu, affine=false)(32 x 32)/forward/CPU/8 thread(s)	10416 ns	9917 ns	1.05
groupnorm(2, act=relu, affine=false)(32 x 32)/forward/CPU/1 thread(s)	9208 ns	8958.5 ns	1.03
groupnorm(2, act=relu, affine=false)(32 x 32)/forward/GPU/CUDA	114121 ns	118821 ns	0.96
groupnorm(2, act=relu, affine=false)(32 x 32)/forward/GPU/oneAPI	3396921 ns	3465548.5 ns	0.98
groupnorm(2, act=relu, affine=false)(32 x 32)/forward/GPU/AMDGPU	71690 ns	71593 ns	1.00
groupnorm(2, act=relu, affine=false)(32 x 32)/zygote/CPU/2 thread(s)	15145.5 ns	13687.5 ns	1.11
groupnorm(2, act=relu, affine=false)(32 x 32)/zygote/CPU/4 thread(s)	13853.5 ns	13604.5 ns	1.02
groupnorm(2, act=relu, affine=false)(32 x 32)/zygote/CPU/8 thread(s)	16167 ns	14395.5 ns	1.12
groupnorm(2, act=relu, affine=false)(32 x 32)/zygote/CPU/1 thread(s)	14584 ns	14750 ns	0.99
groupnorm(2, act=relu, affine=false)(32 x 32)/zygote/GPU/CUDA	559358 ns	570663 ns	0.98
groupnorm(2, act=relu, affine=false)(32 x 32)/zygote/GPU/oneAPI	19846391.5 ns	20121784.5 ns	0.99
groupnorm(2, act=relu, affine=false)(32 x 32)/zygote/GPU/AMDGPU	345674 ns	323504 ns	1.07
batchnorm(2, act=gelu, affine=false)(4 x 32)/forward/CPU/2 thread(s)	542 ns	542 ns	1
batchnorm(2, act=gelu, affine=false)(4 x 32)/forward/CPU/4 thread(s)	583 ns	625 ns	0.93
batchnorm(2, act=gelu, affine=false)(4 x 32)/forward/CPU/8 thread(s)	667 ns	584 ns	1.14
batchnorm(2, act=gelu, affine=false)(4 x 32)/forward/CPU/1 thread(s)	541 ns	500 ns	1.08
batchnorm(2, act=gelu, affine=false)(4 x 32)/forward/GPU/CUDA	34284 ns	35088 ns	0.98
batchnorm(2, act=gelu, affine=false)(4 x 32)/forward/GPU/oneAPI	1180662 ns	1218149.5 ns	0.97
batchnorm(2, act=gelu, affine=false)(4 x 32)/forward/GPU/AMDGPU	209633 ns	203871 ns	1.03
batchnorm(2, act=gelu, affine=false)(4 x 32)/zygote/CPU/2 thread(s)	8520.5 ns	7562.5 ns	1.13
batchnorm(2, act=gelu, affine=false)(4 x 32)/zygote/CPU/4 thread(s)	7625 ns	7667 ns	0.99
batchnorm(2, act=gelu, affine=false)(4 x 32)/zygote/CPU/8 thread(s)	8167 ns	7875 ns	1.04
batchnorm(2, act=gelu, affine=false)(4 x 32)/zygote/CPU/1 thread(s)	10333.5 ns	8520.5 ns	1.21
batchnorm(2, act=gelu, affine=false)(4 x 32)/zygote/GPU/CUDA	228173.5 ns	227876 ns	1.00
batchnorm(2, act=gelu, affine=false)(4 x 32)/zygote/GPU/oneAPI	24272825 ns	22566032 ns	1.08
batchnorm(2, act=gelu, affine=false)(4 x 32)/zygote/GPU/AMDGPU	665251.5 ns	569945 ns	1.17
bias_activation(32, act=gelu)(32 x 128)/forward/CPU/2 thread(s)	15833 ns	16458 ns	0.96
bias_activation(32, act=gelu)(32 x 128)/forward/CPU/4 thread(s)	15792 ns	17041 ns	0.93
bias_activation(32, act=gelu)(32 x 128)/forward/CPU/8 thread(s)	14250 ns	16209 ns	0.88
bias_activation(32, act=gelu)(32 x 128)/forward/CPU/1 thread(s)	10604 ns	10979 ns	0.97
bias_activation(32, act=gelu)(32 x 128)/forward/GPU/CUDA	20654 ns	20941 ns	0.99
bias_activation(32, act=gelu)(32 x 128)/forward/GPU/oneAPI	1114936.5 ns	1150830 ns	0.97
bias_activation(32, act=gelu)(32 x 128)/forward/GPU/AMDGPU	189192 ns	182992 ns	1.03
bias_activation(32, act=gelu)(32 x 128)/zygote/CPU/2 thread(s)	35459 ns	35666 ns	0.99
bias_activation(32, act=gelu)(32 x 128)/zygote/CPU/4 thread(s)	35708.5 ns	35167 ns	1.02
bias_activation(32, act=gelu)(32 x 128)/zygote/CPU/8 thread(s)	35917 ns	36000 ns	1.00
bias_activation(32, act=gelu)(32 x 128)/zygote/CPU/1 thread(s)	35583 ns	57833 ns	0.62
bias_activation(32, act=gelu)(32 x 128)/zygote/GPU/CUDA	262047 ns	265749 ns	0.99
bias_activation(32, act=gelu)(32 x 128)/zygote/GPU/oneAPI	11306916 ns	12188303 ns	0.93
bias_activation(32, act=gelu)(32 x 128)/zygote/GPU/AMDGPU	587246 ns	534293 ns	1.10
groupnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	453583 ns	447500 ns	1.01
groupnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	451792 ns	488042 ns	0.93
groupnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	456541.5 ns	455709 ns	1.00
groupnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	443395.5 ns	496916 ns	0.89
groupnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/CUDA	194459 ns	195513 ns	0.99
groupnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	6038382.5 ns	5997948.5 ns	1.01
groupnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	348194 ns	328714 ns	1.06
groupnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	4066000 ns	4024209 ns	1.01
groupnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	4050916 ns	4055021 ns	1.00
groupnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	4067083.5 ns	4053917 ns	1.00
groupnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	4058792 ns	5501562.5 ns	0.74
groupnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	511129.5 ns	521631.5 ns	0.98
groupnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	27375780 ns	27256015 ns	1.00
groupnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1358564 ns	1059038 ns	1.28
batchedmm(512, Bsize=512)/forward/CPU/2 thread(s)	828745583 ns	836727208 ns	0.99
batchedmm(512, Bsize=512)/forward/CPU/4 thread(s)	540680709 ns	553913292 ns	0.98
batchedmm(512, Bsize=512)/forward/CPU/8 thread(s)	540688459 ns	540736625 ns	1.00
batchedmm(512, Bsize=512)/forward/CPU/1 thread(s)	1504191667 ns	1517196875 ns	0.99
batchedmm(512, Bsize=512)/forward/GPU/CUDA	22557615 ns	22767789 ns	0.99
batchedmm(512, Bsize=512)/forward/GPU/oneAPI	174343277 ns	174930068 ns	1.00
batchedmm(512, Bsize=512)/forward/GPU/AMDGPU	14523230.5 ns	10331681 ns	1.41
batchedmm(512, Bsize=512)/zygote/CPU/2 thread(s)	3007511084 ns	3773348667 ns	0.80
batchedmm(512, Bsize=512)/zygote/CPU/4 thread(s)	2962783167 ns	1782084291 ns	1.66
batchedmm(512, Bsize=512)/zygote/CPU/8 thread(s)	1774752667 ns	1780399750 ns	1.00
batchedmm(512, Bsize=512)/zygote/CPU/1 thread(s)	4717186625 ns	4786718666 ns	0.99
batchedmm(512, Bsize=512)/zygote/GPU/CUDA	119117244 ns	118657187 ns	1.00
batchedmm(512, Bsize=512)/zygote/GPU/oneAPI	944339444.5 ns	1332561794 ns	0.71
batchedmm(512, Bsize=512)/zygote/GPU/AMDGPU	87286346 ns	67063298 ns	1.30
layernorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	76833 ns	76542 ns	1.00
layernorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	80875 ns	76584 ns	1.06
layernorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	79667 ns	79583 ns	1.00
layernorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	76416 ns	76708.5 ns	1.00
layernorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/GPU/CUDA	193222 ns	195943.5 ns	0.99
layernorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	7583823.5 ns	5455658.5 ns	1.39
layernorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	108921 ns	123300.5 ns	0.88
layernorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	193250 ns	191292 ns	1.01
layernorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	280041.5 ns	252042 ns	1.11
layernorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	281104 ns	199562.5 ns	1.41
layernorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	198375 ns	225542 ns	0.88
layernorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	995796 ns	1004442 ns	0.99
layernorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	43132049 ns	43458500 ns	0.99
layernorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	631361 ns	590764 ns	1.07
batchedmm(512, Bsize=128)/forward/CPU/2 thread(s)	199538562.5 ns	199694520.5 ns	1.00
batchedmm(512, Bsize=128)/forward/CPU/4 thread(s)	139125625 ns	138856500 ns	1.00
batchedmm(512, Bsize=128)/forward/CPU/8 thread(s)	139078542 ns	139241166 ns	1.00
batchedmm(512, Bsize=128)/forward/CPU/1 thread(s)	394211084 ns	393790959 ns	1.00
batchedmm(512, Bsize=128)/forward/GPU/CUDA	5836169 ns	5842492 ns	1.00
batchedmm(512, Bsize=128)/forward/GPU/oneAPI	77966597 ns	78913006.5 ns	0.99
batchedmm(512, Bsize=128)/forward/GPU/AMDGPU	3607862.5 ns	4746717.5 ns	0.76
batchedmm(512, Bsize=128)/zygote/CPU/2 thread(s)	618106583 ns	617676375.5 ns	1.00
batchedmm(512, Bsize=128)/zygote/CPU/4 thread(s)	439744666 ns	439446917 ns	1.00
batchedmm(512, Bsize=128)/zygote/CPU/8 thread(s)	438674541.5 ns	439765166.5 ns	1.00
batchedmm(512, Bsize=128)/zygote/CPU/1 thread(s)	1195937583 ns	1174222000 ns	1.02
batchedmm(512, Bsize=128)/zygote/GPU/CUDA	26625423 ns	26723523 ns	1.00
batchedmm(512, Bsize=128)/zygote/GPU/oneAPI	274698573 ns	276392509 ns	0.99
batchedmm(512, Bsize=128)/zygote/GPU/AMDGPU	21854587 ns	15854720 ns	1.38
batchnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	7334 ns	7292 ns	1.01
batchnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	6208 ns	6125 ns	1.01
batchnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	6041 ns	5959 ns	1.01
batchnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	9833 ns	9834 ns	1.00
batchnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/GPU/CUDA	26860 ns	26896.5 ns	1.00
batchnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	1237975 ns	1173091 ns	1.06
batchnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	47461 ns	55173 ns	0.86
batchnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	220166.5 ns	213041.5 ns	1.03
batchnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	219875 ns	227729 ns	0.97
batchnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	229604 ns	220416.5 ns	1.04
batchnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	205791 ns	206125 ns	1.00
batchnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	215811 ns	219868 ns	0.98
batchnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	20823014 ns	20153337 ns	1.03
batchnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	524725 ns	541982 ns	0.97
groupnorm(2, act=relu, affine=false)(4 x 32)/forward/CPU/2 thread(s)	8459 ns	8521 ns	0.99
groupnorm(2, act=relu, affine=false)(4 x 32)/forward/CPU/4 thread(s)	9667 ns	7458 ns	1.30
groupnorm(2, act=relu, affine=false)(4 x 32)/forward/CPU/8 thread(s)	10167 ns	11167 ns	0.91
groupnorm(2, act=relu, affine=false)(4 x 32)/forward/CPU/1 thread(s)	6875 ns	9250 ns	0.74
groupnorm(2, act=relu, affine=false)(4 x 32)/forward/GPU/CUDA	112059.5 ns	115361 ns	0.97
groupnorm(2, act=relu, affine=false)(4 x 32)/forward/GPU/oneAPI	3481104 ns	3392154.5 ns	1.03
groupnorm(2, act=relu, affine=false)(4 x 32)/forward/GPU/AMDGPU	70541 ns	74069 ns	0.95
groupnorm(2, act=relu, affine=false)(4 x 32)/zygote/CPU/2 thread(s)	7395.5 ns	7562.5 ns	0.98
groupnorm(2, act=relu, affine=false)(4 x 32)/zygote/CPU/4 thread(s)	8000 ns	7958 ns	1.01
groupnorm(2, act=relu, affine=false)(4 x 32)/zygote/CPU/8 thread(s)	10208 ns	8167 ns	1.25
groupnorm(2, act=relu, affine=false)(4 x 32)/zygote/CPU/1 thread(s)	7583 ns	7395.5 ns	1.03
groupnorm(2, act=relu, affine=false)(4 x 32)/zygote/GPU/CUDA	489162 ns	495697 ns	0.99
groupnorm(2, act=relu, affine=false)(4 x 32)/zygote/GPU/oneAPI	18742318 ns	20965461 ns	0.89
groupnorm(2, act=relu, affine=false)(4 x 32)/zygote/GPU/AMDGPU	313343 ns	309298 ns	1.01
batchnorm(2, act=identity, affine=true)(32 x 32)/forward/CPU/2 thread(s)	417 ns	417 ns	1
batchnorm(2, act=identity, affine=true)(32 x 32)/forward/CPU/4 thread(s)	500 ns	459 ns	1.09
batchnorm(2, act=identity, affine=true)(32 x 32)/forward/CPU/8 thread(s)	583 ns	500 ns	1.17
batchnorm(2, act=identity, affine=true)(32 x 32)/forward/CPU/1 thread(s)	375 ns	375 ns	1
batchnorm(2, act=identity, affine=true)(32 x 32)/forward/GPU/CUDA	25812.5 ns	26124 ns	0.99
batchnorm(2, act=identity, affine=true)(32 x 32)/forward/GPU/oneAPI	1173150 ns	1243719 ns	0.94
batchnorm(2, act=identity, affine=true)(32 x 32)/forward/GPU/AMDGPU	46821 ns	45334 ns	1.03
batchnorm(2, act=identity, affine=true)(32 x 32)/zygote/CPU/2 thread(s)	8375 ns	9584 ns	0.87
batchnorm(2, act=identity, affine=true)(32 x 32)/zygote/CPU/4 thread(s)	9500 ns	9062.5 ns	1.05
batchnorm(2, act=identity, affine=true)(32 x 32)/zygote/CPU/8 thread(s)	11500 ns	9792 ns	1.17
batchnorm(2, act=identity, affine=true)(32 x 32)/zygote/CPU/1 thread(s)	9208 ns	9542 ns	0.96
batchnorm(2, act=identity, affine=true)(32 x 32)/zygote/GPU/CUDA	247400 ns	247606 ns	1.00
batchnorm(2, act=identity, affine=true)(32 x 32)/zygote/GPU/oneAPI	22760470 ns	24899790.5 ns	0.91
batchnorm(2, act=identity, affine=true)(32 x 32)/zygote/GPU/AMDGPU	393455 ns	382304 ns	1.03
bias_activation(512, act=gelu)(512 x 128)/forward/CPU/2 thread(s)	112333 ns	112312.5 ns	1.00
bias_activation(512, act=gelu)(512 x 128)/forward/CPU/4 thread(s)	103729.5 ns	103229 ns	1.00
bias_activation(512, act=gelu)(512 x 128)/forward/CPU/8 thread(s)	104458 ns	104104.5 ns	1.00
bias_activation(512, act=gelu)(512 x 128)/forward/CPU/1 thread(s)	154666 ns	155083 ns	1.00
bias_activation(512, act=gelu)(512 x 128)/forward/GPU/CUDA	23375 ns	23501 ns	0.99
bias_activation(512, act=gelu)(512 x 128)/forward/GPU/oneAPI	817681 ns	811475 ns	1.01
bias_activation(512, act=gelu)(512 x 128)/forward/GPU/AMDGPU	189652 ns	192539 ns	0.99
bias_activation(512, act=gelu)(512 x 128)/zygote/CPU/2 thread(s)	586396 ns	536562 ns	1.09
bias_activation(512, act=gelu)(512 x 128)/zygote/CPU/4 thread(s)	583374.5 ns	554250 ns	1.05
bias_activation(512, act=gelu)(512 x 128)/zygote/CPU/8 thread(s)	585896 ns	535291.5 ns	1.09
bias_activation(512, act=gelu)(512 x 128)/zygote/CPU/1 thread(s)	534334 ns	910854 ns	0.59
bias_activation(512, act=gelu)(512 x 128)/zygote/GPU/CUDA	218992 ns	221242 ns	0.99
bias_activation(512, act=gelu)(512 x 128)/zygote/GPU/oneAPI	11923370.5 ns	11751092 ns	1.01
bias_activation(512, act=gelu)(512 x 128)/zygote/GPU/AMDGPU	607266 ns	560216.5 ns	1.08
batchedmm(16, Bsize=32)/forward/CPU/2 thread(s)	5333 ns	5416.5 ns	0.98
batchedmm(16, Bsize=32)/forward/CPU/4 thread(s)	6625 ns	6208.5 ns	1.07
batchedmm(16, Bsize=32)/forward/CPU/8 thread(s)	7625 ns	6021 ns	1.27
batchedmm(16, Bsize=32)/forward/CPU/1 thread(s)	6166.5 ns	4000 ns	1.54
batchedmm(16, Bsize=32)/forward/GPU/CUDA	16902 ns	17520 ns	0.96
batchedmm(16, Bsize=32)/forward/GPU/oneAPI	72702442 ns	72849606 ns	1.00
batchedmm(16, Bsize=32)/forward/GPU/AMDGPU	78091 ns	73648 ns	1.06
batchedmm(16, Bsize=32)/zygote/CPU/2 thread(s)	12479 ns	11562.5 ns	1.08
batchedmm(16, Bsize=32)/zygote/CPU/4 thread(s)	11166.5 ns	11062 ns	1.01
batchedmm(16, Bsize=32)/zygote/CPU/8 thread(s)	11625 ns	11000 ns	1.06
batchedmm(16, Bsize=32)/zygote/CPU/1 thread(s)	16625 ns	16666 ns	1.00
batchedmm(16, Bsize=32)/zygote/GPU/CUDA	203795.5 ns	207455.5 ns	0.98
batchedmm(16, Bsize=32)/zygote/GPU/oneAPI	98168072 ns	97442684 ns	1.01
batchedmm(16, Bsize=32)/zygote/GPU/AMDGPU	377594 ns	330387 ns	1.14
batchedmm(16, Bsize=128)/forward/CPU/2 thread(s)	39833 ns	39667 ns	1.00
batchedmm(16, Bsize=128)/forward/CPU/4 thread(s)	51500 ns	51291 ns	1.00
batchedmm(16, Bsize=128)/forward/CPU/8 thread(s)	52563 ns	52958.5 ns	0.99
batchedmm(16, Bsize=128)/forward/CPU/1 thread(s)	13583 ns	13625 ns	1.00
batchedmm(16, Bsize=128)/forward/GPU/CUDA	19687 ns	20356 ns	0.97
batchedmm(16, Bsize=128)/forward/GPU/oneAPI	76051886 ns	76663129 ns	0.99
batchedmm(16, Bsize=128)/forward/GPU/AMDGPU	87971 ns	98364 ns	0.89
batchedmm(16, Bsize=128)/zygote/CPU/2 thread(s)	36458 ns	36375.5 ns	1.00
batchedmm(16, Bsize=128)/zygote/CPU/4 thread(s)	32395.5 ns	31417 ns	1.03
batchedmm(16, Bsize=128)/zygote/CPU/8 thread(s)	32104 ns	31229.5 ns	1.03
batchedmm(16, Bsize=128)/zygote/CPU/1 thread(s)	57167 ns	57000 ns	1.00
batchedmm(16, Bsize=128)/zygote/GPU/CUDA	181544 ns	184178 ns	0.99
batchedmm(16, Bsize=128)/zygote/GPU/oneAPI	111712645 ns	111708023 ns	1.00
batchedmm(16, Bsize=128)/zygote/GPU/AMDGPU	408524.5 ns	355254 ns	1.15
bias_activation(2, act=tanh)(2 x 128)/forward/CPU/2 thread(s)	1854 ns	1750 ns	1.06
bias_activation(2, act=tanh)(2 x 128)/forward/CPU/4 thread(s)	1875 ns	2042 ns	0.92
bias_activation(2, act=tanh)(2 x 128)/forward/CPU/8 thread(s)	2250 ns	2208 ns	1.02
bias_activation(2, act=tanh)(2 x 128)/forward/CPU/1 thread(s)	1667 ns	1875 ns	0.89
bias_activation(2, act=tanh)(2 x 128)/forward/GPU/CUDA	19104 ns	19575 ns	0.98
bias_activation(2, act=tanh)(2 x 128)/forward/GPU/oneAPI	1153845 ns	1219758.5 ns	0.95
bias_activation(2, act=tanh)(2 x 128)/forward/GPU/AMDGPU	27270 ns	29099.5 ns	0.94
bias_activation(2, act=tanh)(2 x 128)/zygote/CPU/2 thread(s)	2208 ns	2208 ns	1
bias_activation(2, act=tanh)(2 x 128)/zygote/CPU/4 thread(s)	2291 ns	2167 ns	1.06
bias_activation(2, act=tanh)(2 x 128)/zygote/CPU/8 thread(s)	2375 ns	2375 ns	1
bias_activation(2, act=tanh)(2 x 128)/zygote/CPU/1 thread(s)	2291 ns	2208 ns	1.04
bias_activation(2, act=tanh)(2 x 128)/zygote/GPU/CUDA	196068 ns	198996.5 ns	0.99
bias_activation(2, act=tanh)(2 x 128)/zygote/GPU/oneAPI	9312847 ns	8766738.5 ns	1.06
bias_activation(2, act=tanh)(2 x 128)/zygote/GPU/AMDGPU	136721 ns	128571 ns	1.06
layernorm(2, act=identity, affine=true)(4 x 32)/forward/CPU/2 thread(s)	5375 ns	4583 ns	1.17
layernorm(2, act=identity, affine=true)(4 x 32)/forward/CPU/4 thread(s)	4750 ns	4417 ns	1.08
layernorm(2, act=identity, affine=true)(4 x 32)/forward/CPU/8 thread(s)	6250 ns	6729 ns	0.93
layernorm(2, act=identity, affine=true)(4 x 32)/forward/CPU/1 thread(s)	4500 ns	3958 ns	1.14
layernorm(2, act=identity, affine=true)(4 x 32)/forward/GPU/CUDA	140814.5 ns	143699.5 ns	0.98
layernorm(2, act=identity, affine=true)(4 x 32)/forward/GPU/oneAPI	5579238.5 ns	5704411.5 ns	0.98
layernorm(2, act=identity, affine=true)(4 x 32)/forward/GPU/AMDGPU	59971 ns	61955.5 ns	0.97
layernorm(2, act=identity, affine=true)(4 x 32)/zygote/CPU/2 thread(s)	8604.5 ns	8334 ns	1.03
layernorm(2, act=identity, affine=true)(4 x 32)/zygote/CPU/4 thread(s)	8417 ns	8083.5 ns	1.04
layernorm(2, act=identity, affine=true)(4 x 32)/zygote/CPU/8 thread(s)	9250 ns	8709 ns	1.06
layernorm(2, act=identity, affine=true)(4 x 32)/zygote/CPU/1 thread(s)	8417 ns	8583 ns	0.98
layernorm(2, act=identity, affine=true)(4 x 32)/zygote/GPU/CUDA	827700 ns	836045.5 ns	0.99
layernorm(2, act=identity, affine=true)(4 x 32)/zygote/GPU/oneAPI	40495109.5 ns	39725172 ns	1.02
layernorm(2, act=identity, affine=true)(4 x 32)/zygote/GPU/AMDGPU	387884 ns	364891 ns	1.06
batchnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	55208 ns	54833 ns	1.01
batchnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	55916 ns	55833 ns	1.00
batchnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	55708 ns	55583 ns	1.00
batchnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	56375 ns	56000 ns	1.01
batchnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/CUDA	36532 ns	36570 ns	1.00
batchnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	1228814.5 ns	1345223 ns	0.91
batchnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	206372 ns	202568 ns	1.02
batchnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	523646 ns	476729 ns	1.10
batchnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	535916.5 ns	494500 ns	1.08
batchnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	504166.5 ns	494208 ns	1.02
batchnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	460541 ns	641625 ns	0.72
batchnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	256291 ns	259886 ns	0.99
batchnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	27542751 ns	28017517.5 ns	0.98
batchnorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	802518 ns	705894 ns	1.14
batchedmm(128, Bsize=128)/forward/CPU/2 thread(s)	3314917 ns	3310333 ns	1.00
batchedmm(128, Bsize=128)/forward/CPU/4 thread(s)	2332896 ns	2334062.5 ns	1.00
batchedmm(128, Bsize=128)/forward/CPU/8 thread(s)	2330833 ns	2333375 ns	1.00
batchedmm(128, Bsize=128)/forward/CPU/1 thread(s)	6314521 ns	6300479 ns	1.00
batchedmm(128, Bsize=128)/forward/GPU/CUDA	204455 ns	204581.5 ns	1.00
batchedmm(128, Bsize=128)/forward/GPU/oneAPI	76381388 ns	77398976 ns	0.99
batchedmm(128, Bsize=128)/forward/GPU/AMDGPU	216403 ns	373097 ns	0.58
batchedmm(128, Bsize=128)/zygote/CPU/2 thread(s)	11460833 ns	11459729 ns	1.00
batchedmm(128, Bsize=128)/zygote/CPU/4 thread(s)	8303937.5 ns	8305729.5 ns	1.00
batchedmm(128, Bsize=128)/zygote/CPU/8 thread(s)	8310083.5 ns	8342854 ns	1.00
batchedmm(128, Bsize=128)/zygote/CPU/1 thread(s)	21101249.5 ns	21088292 ns	1.00
batchedmm(128, Bsize=128)/zygote/GPU/CUDA	734685 ns	744676 ns	0.99
batchedmm(128, Bsize=128)/zygote/GPU/oneAPI	119951330 ns	121497637 ns	0.99
batchedmm(128, Bsize=128)/zygote/GPU/AMDGPU	1068321.5 ns	1994797.5 ns	0.54
layernorm(2, act=identity, affine=false)(4 x 32)/forward/CPU/2 thread(s)	5250 ns	4833 ns	1.09
layernorm(2, act=identity, affine=false)(4 x 32)/forward/CPU/4 thread(s)	5146 ns	4646 ns	1.11
layernorm(2, act=identity, affine=false)(4 x 32)/forward/CPU/8 thread(s)	6958.5 ns	7520.5 ns	0.93
layernorm(2, act=identity, affine=false)(4 x 32)/forward/CPU/1 thread(s)	3917 ns	4917 ns	0.80
layernorm(2, act=identity, affine=false)(4 x 32)/forward/GPU/CUDA	132062.5 ns	133339 ns	0.99
layernorm(2, act=identity, affine=false)(4 x 32)/forward/GPU/oneAPI	5633249 ns	5450569.5 ns	1.03
layernorm(2, act=identity, affine=false)(4 x 32)/forward/GPU/AMDGPU	55811 ns	61520 ns	0.91
layernorm(2, act=identity, affine=false)(4 x 32)/zygote/CPU/2 thread(s)	7479.5 ns	7083 ns	1.06
layernorm(2, act=identity, affine=false)(4 x 32)/zygote/CPU/4 thread(s)	7375 ns	7291.5 ns	1.01
layernorm(2, act=identity, affine=false)(4 x 32)/zygote/CPU/8 thread(s)	7333 ns	7500 ns	0.98
layernorm(2, act=identity, affine=false)(4 x 32)/zygote/CPU/1 thread(s)	7187.5 ns	7416.5 ns	0.97
layernorm(2, act=identity, affine=false)(4 x 32)/zygote/GPU/CUDA	726722 ns	725863 ns	1.00
layernorm(2, act=identity, affine=false)(4 x 32)/zygote/GPU/oneAPI	36533131 ns	33872141 ns	1.08
layernorm(2, act=identity, affine=false)(4 x 32)/zygote/GPU/AMDGPU	371459 ns	353680 ns	1.05
groupnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	122208 ns	100459 ns	1.22
groupnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	98583 ns	123042 ns	0.80
groupnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	102750 ns	102417 ns	1.00
groupnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	95458 ns	121458.5 ns	0.79
groupnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/CUDA	149588 ns	151940.5 ns	0.98
groupnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	5726109 ns	5695179 ns	1.01
groupnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	185537 ns	233346 ns	0.80
groupnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	2029833 ns	2033271 ns	1.00
groupnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	2026979 ns	2026417 ns	1.00
groupnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	2027208 ns	1997458.5 ns	1.01
groupnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	2030625 ns	2041833 ns	0.99
groupnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	673368 ns	678763 ns	0.99
groupnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	31179443 ns	31810809 ns	0.98
groupnorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1113991.5 ns	931831 ns	1.20
batchedmm(2, Bsize=4)/forward/CPU/2 thread(s)	32417 ns	32666 ns	0.99
batchedmm(2, Bsize=4)/forward/CPU/4 thread(s)	35792 ns	36562.5 ns	0.98
batchedmm(2, Bsize=4)/forward/CPU/8 thread(s)	34917 ns	36167 ns	0.97
batchedmm(2, Bsize=4)/forward/CPU/1 thread(s)	500 ns	667 ns	0.75
batchedmm(2, Bsize=4)/forward/GPU/CUDA	14705 ns	15627 ns	0.94
batchedmm(2, Bsize=4)/forward/GPU/oneAPI	72130343.5 ns	72187220 ns	1.00
batchedmm(2, Bsize=4)/forward/GPU/AMDGPU	85381 ns	70121 ns	1.22
batchedmm(2, Bsize=4)/zygote/CPU/2 thread(s)	2625 ns	2604.5 ns	1.01
batchedmm(2, Bsize=4)/zygote/CPU/4 thread(s)	2917 ns	2958 ns	0.99
batchedmm(2, Bsize=4)/zygote/CPU/8 thread(s)	3042 ns	2937.5 ns	1.04
batchedmm(2, Bsize=4)/zygote/CPU/1 thread(s)	2209 ns	2167 ns	1.02
batchedmm(2, Bsize=4)/zygote/GPU/CUDA	137484 ns	139744 ns	0.98
batchedmm(2, Bsize=4)/zygote/GPU/oneAPI	92342967 ns	92749943 ns	1.00
batchedmm(2, Bsize=4)/zygote/GPU/AMDGPU	354874 ns	289641 ns	1.23
batchnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	7250 ns	7208 ns	1.01
batchnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	6000 ns	6000 ns	1
batchnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	5916 ns	5916 ns	1
batchnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	9875 ns	9917 ns	1.00
batchnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/GPU/CUDA	35660 ns	35855 ns	0.99
batchnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	1282087 ns	1252207 ns	1.02
batchnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	49651 ns	53911 ns	0.92
batchnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	213312.5 ns	212958.5 ns	1.00
batchnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	252999.5 ns	222708 ns	1.14
batchnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	231666.5 ns	219917 ns	1.05
batchnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	205458 ns	206209 ns	1.00
batchnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	240672 ns	243430 ns	0.99
batchnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	26115627.5 ns	27468024.5 ns	0.95
batchnorm(4, act=identity, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	512115 ns	513269 ns	1.00
dense(32, bias=true, act=identity)(32 x 128)/forward/CPU/2 thread(s)	3750 ns	3750 ns	1
dense(32, bias=true, act=identity)(32 x 128)/forward/CPU/4 thread(s)	3750 ns	3750 ns	1
dense(32, bias=true, act=identity)(32 x 128)/forward/CPU/8 thread(s)	3750 ns	3750 ns	1
dense(32, bias=true, act=identity)(32 x 128)/forward/CPU/1 thread(s)	3750 ns	3791 ns	0.99
dense(32, bias=true, act=identity)(32 x 128)/forward/GPU/CUDA	21665 ns	21959 ns	0.99
dense(32, bias=true, act=identity)(32 x 128)/forward/GPU/oneAPI	2106682 ns	2194149 ns	0.96
dense(32, bias=true, act=identity)(32 x 128)/forward/GPU/AMDGPU	43630 ns	35557 ns	1.23
dense(32, bias=true, act=identity)(32 x 128)/zygote/CPU/2 thread(s)	14500 ns	14500 ns	1
dense(32, bias=true, act=identity)(32 x 128)/zygote/CPU/4 thread(s)	14542 ns	14500 ns	1.00
dense(32, bias=true, act=identity)(32 x 128)/zygote/CPU/8 thread(s)	14584 ns	14500 ns	1.01
dense(32, bias=true, act=identity)(32 x 128)/zygote/CPU/1 thread(s)	14458 ns	14459 ns	1.00
dense(32, bias=true, act=identity)(32 x 128)/zygote/GPU/CUDA	301039 ns	302419 ns	1.00
dense(32, bias=true, act=identity)(32 x 128)/zygote/GPU/oneAPI	11172042.5 ns	11036089 ns	1.01
dense(32, bias=true, act=identity)(32 x 128)/zygote/GPU/AMDGPU	195452 ns	179841 ns	1.09
groupnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	117271 ns	128041 ns	0.92
groupnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	105312.5 ns	144417 ns	0.73
groupnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	105666 ns	106917 ns	0.99
groupnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	99375 ns	151959 ns	0.65
groupnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/GPU/CUDA	150300.5 ns	140874 ns	1.07
groupnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	6047278 ns	5963081 ns	1.01
groupnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	171362 ns	236762 ns	0.72
groupnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	1912167 ns	1924583 ns	0.99
groupnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	1918167 ns	1920500 ns	1.00
groupnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	1920208.5 ns	1914229.5 ns	1.00
groupnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	1931333 ns	1928875 ns	1.00
groupnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	660598 ns	673452 ns	0.98
groupnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	29570117 ns	29935915 ns	0.99
groupnorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1219983 ns	899671 ns	1.36
groupnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	17875 ns	17333 ns	1.03
groupnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	17645.5 ns	17354.5 ns	1.02
groupnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	21583.5 ns	21208 ns	1.02
groupnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	18500 ns	17375 ns	1.06
groupnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/CUDA	104806 ns	108833.5 ns	0.96
groupnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	3524106 ns	3415955 ns	1.03
groupnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	76655.5 ns	91100 ns	0.84
groupnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	229084 ns	216917 ns	1.06
groupnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	249729.5 ns	252646 ns	0.99
groupnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	225104.5 ns	222166 ns	1.01
groupnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	216374.5 ns	229125 ns	0.94
groupnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	497993 ns	508535.5 ns	0.98
groupnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	19805584 ns	19323488.5 ns	1.02
groupnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	477940 ns	419764 ns	1.14
batchedmm(16, Bsize=4)/forward/CPU/2 thread(s)	23708.5 ns	24271 ns	0.98
batchedmm(16, Bsize=4)/forward/CPU/4 thread(s)	30208 ns	30791.5 ns	0.98
batchedmm(16, Bsize=4)/forward/CPU/8 thread(s)	28625 ns	29437.5 ns	0.97
batchedmm(16, Bsize=4)/forward/CPU/1 thread(s)	1250 ns	1584 ns	0.79
batchedmm(16, Bsize=4)/forward/GPU/CUDA	15640 ns	16398 ns	0.95
batchedmm(16, Bsize=4)/forward/GPU/oneAPI	71882264.5 ns	72518390 ns	0.99
batchedmm(16, Bsize=4)/forward/GPU/AMDGPU	87081 ns	76093 ns	1.14
batchedmm(16, Bsize=4)/zygote/CPU/2 thread(s)	4771 ns	4500 ns	1.06
batchedmm(16, Bsize=4)/zygote/CPU/4 thread(s)	5042 ns	4916 ns	1.03
batchedmm(16, Bsize=4)/zygote/CPU/8 thread(s)	5375 ns	5125 ns	1.05
batchedmm(16, Bsize=4)/zygote/CPU/1 thread(s)	4791 ns	4625 ns	1.04
batchedmm(16, Bsize=4)/zygote/GPU/CUDA	201063.5 ns	204364 ns	0.98
batchedmm(16, Bsize=4)/zygote/GPU/oneAPI	93151103.5 ns	94073985 ns	0.99
batchedmm(16, Bsize=4)/zygote/GPU/AMDGPU	390274 ns	331675 ns	1.18
layernorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	220875 ns	222666 ns	0.99
layernorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	223291 ns	220666.5 ns	1.01
layernorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	224542 ns	225667 ns	1.00
layernorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	221042 ns	220583 ns	1.00
layernorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/CUDA	218652.5 ns	222506.5 ns	0.98
layernorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	7853304 ns	7881934.5 ns	1.00
layernorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	274613 ns	267871 ns	1.03
layernorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	507333.5 ns	495084 ns	1.02
layernorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	513291.5 ns	511812.5 ns	1.00
layernorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	517583.5 ns	500854 ns	1.03
layernorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	495500 ns	675750 ns	0.73
layernorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	1033086 ns	1053634 ns	0.98
layernorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	43068906 ns	42862742 ns	1.00
layernorm(4, act=gelu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	851254 ns	780999 ns	1.09
groupnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	20125 ns	20375 ns	0.99
groupnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	22271 ns	20000 ns	1.11
groupnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	23084 ns	23875 ns	0.97
groupnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	19500 ns	18792 ns	1.04
groupnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/GPU/CUDA	112207.5 ns	114286 ns	0.98
groupnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	3446725.5 ns	3510843 ns	0.98
groupnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	75731 ns	89858 ns	0.84
groupnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	221542 ns	212375 ns	1.04
groupnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	218750 ns	213041 ns	1.03
groupnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	223104 ns	214458 ns	1.04
groupnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	213312 ns	212541 ns	1.00
groupnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	713841 ns	727333.5 ns	0.98
groupnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	25836932 ns	24570511 ns	1.05
groupnorm(4, act=identity, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	533536 ns	469036 ns	1.14
layernorm(2, act=identity, affine=false)(32 x 32)/forward/CPU/2 thread(s)	6875 ns	6666 ns	1.03
layernorm(2, act=identity, affine=false)(32 x 32)/forward/CPU/4 thread(s)	6625 ns	6604.5 ns	1.00
layernorm(2, act=identity, affine=false)(32 x 32)/forward/CPU/8 thread(s)	7458 ns	8750.5 ns	0.85
layernorm(2, act=identity, affine=false)(32 x 32)/forward/CPU/1 thread(s)	6084 ns	6208 ns	0.98
layernorm(2, act=identity, affine=false)(32 x 32)/forward/GPU/CUDA	133356 ns	137142 ns	0.97
layernorm(2, act=identity, affine=false)(32 x 32)/forward/GPU/oneAPI	5813011 ns	5605207 ns	1.04
layernorm(2, act=identity, affine=false)(32 x 32)/forward/GPU/AMDGPU	67851 ns	60974 ns	1.11
layernorm(2, act=identity, affine=false)(32 x 32)/zygote/CPU/2 thread(s)	10583 ns	9791 ns	1.08
layernorm(2, act=identity, affine=false)(32 x 32)/zygote/CPU/4 thread(s)	11166.5 ns	10084 ns	1.11
layernorm(2, act=identity, affine=false)(32 x 32)/zygote/CPU/8 thread(s)	10625 ns	10750 ns	0.99
layernorm(2, act=identity, affine=false)(32 x 32)/zygote/CPU/1 thread(s)	10500 ns	10750 ns	0.98
layernorm(2, act=identity, affine=false)(32 x 32)/zygote/GPU/CUDA	791888 ns	794651.5 ns	1.00
layernorm(2, act=identity, affine=false)(32 x 32)/zygote/GPU/oneAPI	38204864 ns	37034174 ns	1.03
layernorm(2, act=identity, affine=false)(32 x 32)/zygote/GPU/AMDGPU	384539 ns	370101.5 ns	1.04
layernorm(2, act=relu, affine=false)(4 x 32)/forward/CPU/2 thread(s)	5000 ns	4666 ns	1.07
layernorm(2, act=relu, affine=false)(4 x 32)/forward/CPU/4 thread(s)	5000 ns	4708 ns	1.06
layernorm(2, act=relu, affine=false)(4 x 32)/forward/CPU/8 thread(s)	6167 ns	7437.5 ns	0.83
layernorm(2, act=relu, affine=false)(4 x 32)/forward/CPU/1 thread(s)	4500 ns	4917 ns	0.92
layernorm(2, act=relu, affine=false)(4 x 32)/forward/GPU/CUDA	135679.5 ns	138544.5 ns	0.98
layernorm(2, act=relu, affine=false)(4 x 32)/forward/GPU/oneAPI	5370478.5 ns	5520602 ns	0.97
layernorm(2, act=relu, affine=false)(4 x 32)/forward/GPU/AMDGPU	59130 ns	59692 ns	0.99
layernorm(2, act=relu, affine=false)(4 x 32)/zygote/CPU/2 thread(s)	7792 ns	7458 ns	1.04
layernorm(2, act=relu, affine=false)(4 x 32)/zygote/CPU/4 thread(s)	7542 ns	7166 ns	1.05
layernorm(2, act=relu, affine=false)(4 x 32)/zygote/CPU/8 thread(s)	7833 ns	7791 ns	1.01
layernorm(2, act=relu, affine=false)(4 x 32)/zygote/CPU/1 thread(s)	7250 ns	7708 ns	0.94
layernorm(2, act=relu, affine=false)(4 x 32)/zygote/GPU/CUDA	755166.5 ns	755761 ns	1.00
layernorm(2, act=relu, affine=false)(4 x 32)/zygote/GPU/oneAPI	39315379 ns	37179182 ns	1.06
layernorm(2, act=relu, affine=false)(4 x 32)/zygote/GPU/AMDGPU	397459.5 ns	376523 ns	1.06
batchedmm(128, Bsize=512)/forward/CPU/2 thread(s)	14342083 ns	14498417 ns	0.99
batchedmm(128, Bsize=512)/forward/CPU/4 thread(s)	10137958 ns	10124125 ns	1.00
batchedmm(128, Bsize=512)/forward/CPU/8 thread(s)	10102833 ns	10094833 ns	1.00
batchedmm(128, Bsize=512)/forward/CPU/1 thread(s)	27729333 ns	27748583.5 ns	1.00
batchedmm(128, Bsize=512)/forward/GPU/CUDA	547150.5 ns	532665 ns	1.03
batchedmm(128, Bsize=512)/forward/GPU/oneAPI	94505718 ns	94795139 ns	1.00
batchedmm(128, Bsize=512)/forward/GPU/AMDGPU	394839 ns	866850 ns	0.46
batchedmm(128, Bsize=512)/zygote/CPU/2 thread(s)	46201374.5 ns	46333437 ns	1.00
batchedmm(128, Bsize=512)/zygote/CPU/4 thread(s)	33505729.5 ns	33447541.5 ns	1.00
batchedmm(128, Bsize=512)/zygote/CPU/8 thread(s)	33506833 ns	33510458 ns	1.00
batchedmm(128, Bsize=512)/zygote/CPU/1 thread(s)	85350458 ns	85445667 ns	1.00
batchedmm(128, Bsize=512)/zygote/GPU/CUDA	2644948 ns	2636151 ns	1.00
batchedmm(128, Bsize=512)/zygote/GPU/oneAPI	192552360 ns	192783631 ns	1.00
batchedmm(128, Bsize=512)/zygote/GPU/AMDGPU	3310165 ns	5189385.5 ns	0.64
groupnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	66875 ns	66458 ns	1.01
groupnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	67062.5 ns	65687.5 ns	1.02
groupnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	70562.5 ns	70500 ns	1.00
groupnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	66292 ns	66500 ns	1.00
groupnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/CUDA	117903.5 ns	118172.5 ns	1.00
groupnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	3543442.5 ns	3662360 ns	0.97
groupnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	234013 ns	237313 ns	0.99
groupnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	480625 ns	467958 ns	1.03
groupnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	471875 ns	480333.5 ns	0.98
groupnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	479792 ns	474916.5 ns	1.01
groupnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	467417 ns	686583.5 ns	0.68
groupnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	702486.5 ns	715446 ns	0.98
groupnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	26280981 ns	26609747 ns	0.99
groupnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	792918 ns	655875 ns	1.21
batchnorm(2, act=relu, affine=false)(32 x 32)/forward/CPU/2 thread(s)	500 ns	542 ns	0.92
batchnorm(2, act=relu, affine=false)(32 x 32)/forward/CPU/4 thread(s)	584 ns	625 ns	0.93
batchnorm(2, act=relu, affine=false)(32 x 32)/forward/CPU/8 thread(s)	625 ns	583 ns	1.07
batchnorm(2, act=relu, affine=false)(32 x 32)/forward/CPU/1 thread(s)	500 ns	500 ns	1
batchnorm(2, act=relu, affine=false)(32 x 32)/forward/GPU/CUDA	33017 ns	32877 ns	1.00
batchnorm(2, act=relu, affine=false)(32 x 32)/forward/GPU/oneAPI	1183373 ns	1227269 ns	0.96
batchnorm(2, act=relu, affine=false)(32 x 32)/forward/GPU/AMDGPU	47820 ns	47579 ns	1.01
batchnorm(2, act=relu, affine=false)(32 x 32)/zygote/CPU/2 thread(s)	8708 ns	8750 ns	1.00
batchnorm(2, act=relu, affine=false)(32 x 32)/zygote/CPU/4 thread(s)	9771 ns	9208 ns	1.06
batchnorm(2, act=relu, affine=false)(32 x 32)/zygote/CPU/8 thread(s)	9208 ns	9104.5 ns	1.01
batchnorm(2, act=relu, affine=false)(32 x 32)/zygote/CPU/1 thread(s)	8167 ns	9750 ns	0.84
batchnorm(2, act=relu, affine=false)(32 x 32)/zygote/GPU/CUDA	282049 ns	280778.5 ns	1.00
batchnorm(2, act=relu, affine=false)(32 x 32)/zygote/GPU/oneAPI	20818689 ns	21881943 ns	0.95
batchnorm(2, act=relu, affine=false)(32 x 32)/zygote/GPU/AMDGPU	378759 ns	355484 ns	1.07
dense(32, bias=false, act=gelu)(32 x 128)/forward/CPU/2 thread(s)	9458 ns	9500 ns	1.00
dense(32, bias=false, act=gelu)(32 x 128)/forward/CPU/4 thread(s)	9500 ns	9500 ns	1
dense(32, bias=false, act=gelu)(32 x 128)/forward/CPU/8 thread(s)	9459 ns	9500 ns	1.00
dense(32, bias=false, act=gelu)(32 x 128)/forward/CPU/1 thread(s)	9459 ns	9500 ns	1.00
dense(32, bias=false, act=gelu)(32 x 128)/forward/GPU/CUDA	23093.5 ns	23273 ns	0.99
dense(32, bias=false, act=gelu)(32 x 128)/forward/GPU/oneAPI	1930074 ns	1862112.5 ns	1.04
dense(32, bias=false, act=gelu)(32 x 128)/forward/GPU/AMDGPU	210972 ns	200655 ns	1.05
dense(32, bias=false, act=gelu)(32 x 128)/zygote/CPU/2 thread(s)	50417 ns	50209 ns	1.00
dense(32, bias=false, act=gelu)(32 x 128)/zygote/CPU/4 thread(s)	50209 ns	50250 ns	1.00
dense(32, bias=false, act=gelu)(32 x 128)/zygote/CPU/8 thread(s)	51166 ns	50500 ns	1.01
dense(32, bias=false, act=gelu)(32 x 128)/zygote/CPU/1 thread(s)	50292 ns	72375 ns	0.69
dense(32, bias=false, act=gelu)(32 x 128)/zygote/GPU/CUDA	276253 ns	278469.5 ns	0.99
dense(32, bias=false, act=gelu)(32 x 128)/zygote/GPU/oneAPI	13609571 ns	13204061 ns	1.03
dense(32, bias=false, act=gelu)(32 x 128)/zygote/GPU/AMDGPU	610356 ns	491037 ns	1.24
batchnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	55167 ns	54917 ns	1.00
batchnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	55875 ns	55667 ns	1.00
batchnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	55459 ns	55584 ns	1.00
batchnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	55500 ns	56000 ns	0.99
batchnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/CUDA	27847 ns	28169 ns	0.99
batchnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	1197101 ns	1174691 ns	1.02
batchnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	206462 ns	203240 ns	1.02
batchnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	479083 ns	518854 ns	0.92
batchnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	504375 ns	500625 ns	1.01
batchnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	537333 ns	497750 ns	1.08
batchnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	461667 ns	643417 ns	0.72
batchnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	236634 ns	238777 ns	0.99
batchnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	33673119 ns	31628121.5 ns	1.06
batchnorm(4, act=gelu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	841708 ns	758938 ns	1.11
layernorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	643604.5 ns	655042 ns	0.98
layernorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	591417 ns	613083 ns	0.96
layernorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	647458 ns	652541 ns	0.99
layernorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	653625 ns	678416.5 ns	0.96
layernorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/GPU/CUDA	206246.5 ns	192069 ns	1.07
layernorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	8254396 ns	8140636 ns	1.01
layernorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	266572 ns	269704 ns	0.99
layernorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	2241792 ns	2167104.5 ns	1.03
layernorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	2237167 ns	2233125 ns	1.00
layernorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	2233375 ns	2241292 ns	1.00
layernorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	2235000 ns	2230208.5 ns	1.00
layernorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	932062 ns	929752.5 ns	1.00
layernorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	48393957 ns	55073105 ns	0.88
layernorm(4, act=identity, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1360079 ns	1217770.5 ns	1.12
groupnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	19125 ns	19500 ns	0.98
groupnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	24979 ns	19208.5 ns	1.30
groupnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	23437.5 ns	23542 ns	1.00
groupnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	18583 ns	20000 ns	0.93
groupnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/CUDA	111398.5 ns	111306 ns	1.00
groupnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	3483614 ns	3589059.5 ns	0.97
groupnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	79426 ns	91551 ns	0.87
groupnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	225521 ns	220459 ns	1.02
groupnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	233166.5 ns	226458 ns	1.03
groupnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	229166 ns	223104.5 ns	1.03
groupnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	219708 ns	219708 ns	1
groupnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	719263 ns	714110 ns	1.01
groupnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	25222149 ns	26626181 ns	0.95
groupnorm(4, act=relu, affine=true)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	554326 ns	487481 ns	1.14
batchnorm(2, act=relu, affine=true)(32 x 32)/forward/CPU/2 thread(s)	500 ns	625 ns	0.80
batchnorm(2, act=relu, affine=true)(32 x 32)/forward/CPU/4 thread(s)	625 ns	583 ns	1.07
batchnorm(2, act=relu, affine=true)(32 x 32)/forward/CPU/8 thread(s)	625 ns	584 ns	1.07
batchnorm(2, act=relu, affine=true)(32 x 32)/forward/CPU/1 thread(s)	459 ns	500 ns	0.92
batchnorm(2, act=relu, affine=true)(32 x 32)/forward/GPU/CUDA	24044 ns	23491 ns	1.02
batchnorm(2, act=relu, affine=true)(32 x 32)/forward/GPU/oneAPI	1223409 ns	1232519 ns	0.99
batchnorm(2, act=relu, affine=true)(32 x 32)/forward/GPU/AMDGPU	47911 ns	43771 ns	1.09
batchnorm(2, act=relu, affine=true)(32 x 32)/zygote/CPU/2 thread(s)	9750 ns	9417 ns	1.04
batchnorm(2, act=relu, affine=true)(32 x 32)/zygote/CPU/4 thread(s)	9667 ns	9291.5 ns	1.04
batchnorm(2, act=relu, affine=true)(32 x 32)/zygote/CPU/8 thread(s)	10417 ns	9708 ns	1.07
batchnorm(2, act=relu, affine=true)(32 x 32)/zygote/CPU/1 thread(s)	10042 ns	9646 ns	1.04
batchnorm(2, act=relu, affine=true)(32 x 32)/zygote/GPU/CUDA	267747 ns	261581 ns	1.02
batchnorm(2, act=relu, affine=true)(32 x 32)/zygote/GPU/oneAPI	25715090 ns	23734390 ns	1.08
batchnorm(2, act=relu, affine=true)(32 x 32)/zygote/GPU/AMDGPU	404304.5 ns	381618 ns	1.06
groupnorm(2, act=identity, affine=false)(4 x 32)/forward/CPU/2 thread(s)	7417 ns	8917 ns	0.83
groupnorm(2, act=identity, affine=false)(4 x 32)/forward/CPU/4 thread(s)	9000.5 ns	7583 ns	1.19
groupnorm(2, act=identity, affine=false)(4 x 32)/forward/CPU/8 thread(s)	10458 ns	11854.5 ns	0.88
groupnorm(2, act=identity, affine=false)(4 x 32)/forward/CPU/1 thread(s)	7959 ns	9042 ns	0.88
groupnorm(2, act=identity, affine=false)(4 x 32)/forward/GPU/CUDA	116633.5 ns	115935.5 ns	1.01
groupnorm(2, act=identity, affine=false)(4 x 32)/forward/GPU/oneAPI	3300094 ns	3441325 ns	0.96
groupnorm(2, act=identity, affine=false)(4 x 32)/forward/GPU/AMDGPU	69880 ns	70456.5 ns	0.99
groupnorm(2, act=identity, affine=false)(4 x 32)/zygote/CPU/2 thread(s)	7666 ns	8125 ns	0.94
groupnorm(2, act=identity, affine=false)(4 x 32)/zygote/CPU/4 thread(s)	7500 ns	7542 ns	0.99
groupnorm(2, act=identity, affine=false)(4 x 32)/zygote/CPU/8 thread(s)	8375 ns	8000 ns	1.05
groupnorm(2, act=identity, affine=false)(4 x 32)/zygote/CPU/1 thread(s)	7750 ns	7292 ns	1.06
groupnorm(2, act=identity, affine=false)(4 x 32)/zygote/GPU/CUDA	492259.5 ns	484010 ns	1.02
groupnorm(2, act=identity, affine=false)(4 x 32)/zygote/GPU/oneAPI	17197317 ns	17813154.5 ns	0.97
groupnorm(2, act=identity, affine=false)(4 x 32)/zygote/GPU/AMDGPU	321574 ns	302215 ns	1.06
bias_activation(2, act=gelu)(2 x 128)/forward/CPU/2 thread(s)	1416 ns	1417 ns	1.00
bias_activation(2, act=gelu)(2 x 128)/forward/CPU/4 thread(s)	1583 ns	1667 ns	0.95
bias_activation(2, act=gelu)(2 x 128)/forward/CPU/8 thread(s)	2083 ns	1959 ns	1.06
bias_activation(2, act=gelu)(2 x 128)/forward/CPU/1 thread(s)	1542 ns	1500 ns	1.03
bias_activation(2, act=gelu)(2 x 128)/forward/GPU/CUDA	20671 ns	20030 ns	1.03
bias_activation(2, act=gelu)(2 x 128)/forward/GPU/oneAPI	1166362.5 ns	1146657 ns	1.02
bias_activation(2, act=gelu)(2 x 128)/forward/GPU/AMDGPU	191412 ns	184144 ns	1.04
bias_activation(2, act=gelu)(2 x 128)/zygote/CPU/2 thread(s)	3459 ns	3708 ns	0.93
bias_activation(2, act=gelu)(2 x 128)/zygote/CPU/4 thread(s)	3667 ns	3625 ns	1.01
bias_activation(2, act=gelu)(2 x 128)/zygote/CPU/8 thread(s)	3750 ns	3833 ns	0.98
bias_activation(2, act=gelu)(2 x 128)/zygote/CPU/1 thread(s)	3542 ns	4917 ns	0.72
bias_activation(2, act=gelu)(2 x 128)/zygote/GPU/CUDA	216790 ns	213101.5 ns	1.02
bias_activation(2, act=gelu)(2 x 128)/zygote/GPU/oneAPI	10825139.5 ns	10511562.5 ns	1.03
bias_activation(2, act=gelu)(2 x 128)/zygote/GPU/AMDGPU	581136 ns	524324.5 ns	1.11
bias_activation(512, act=tanh)(512 x 128)/forward/CPU/2 thread(s)	147979 ns	148729 ns	0.99
bias_activation(512, act=tanh)(512 x 128)/forward/CPU/4 thread(s)	128271 ns	128917 ns	0.99
bias_activation(512, act=tanh)(512 x 128)/forward/CPU/8 thread(s)	130625 ns	129917 ns	1.01
bias_activation(512, act=tanh)(512 x 128)/forward/CPU/1 thread(s)	225209 ns	235541 ns	0.96
bias_activation(512, act=tanh)(512 x 128)/forward/GPU/CUDA	23166.5 ns	22778 ns	1.02
bias_activation(512, act=tanh)(512 x 128)/forward/GPU/oneAPI	1193615 ns	1179919.5 ns	1.01
bias_activation(512, act=tanh)(512 x 128)/forward/GPU/AMDGPU	36441 ns	46868 ns	0.78
bias_activation(512, act=tanh)(512 x 128)/zygote/CPU/2 thread(s)	143209 ns	143645.5 ns	1.00
bias_activation(512, act=tanh)(512 x 128)/zygote/CPU/4 thread(s)	125792 ns	130875 ns	0.96
bias_activation(512, act=tanh)(512 x 128)/zygote/CPU/8 thread(s)	130479.5 ns	138417 ns	0.94
bias_activation(512, act=tanh)(512 x 128)/zygote/CPU/1 thread(s)	251104.5 ns	290021 ns	0.87
bias_activation(512, act=tanh)(512 x 128)/zygote/GPU/CUDA	214906.5 ns	211960 ns	1.01
bias_activation(512, act=tanh)(512 x 128)/zygote/GPU/oneAPI	10713541 ns	10741797 ns	1.00
bias_activation(512, act=tanh)(512 x 128)/zygote/GPU/AMDGPU	231632 ns	223578 ns	1.04
batchnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	7500 ns	7167 ns	1.05
batchnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	5959 ns	5958 ns	1.00
batchnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	5875 ns	5958.5 ns	0.99
batchnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	10083 ns	10000 ns	1.01
batchnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/CUDA	34265 ns	33236 ns	1.03
batchnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	1203594 ns	1203805 ns	1.00
batchnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	49981 ns	57207 ns	0.87
batchnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	225604 ns	221249.5 ns	1.02
batchnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	267167 ns	238542 ns	1.12
batchnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	236917 ns	264500 ns	0.90
batchnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	212812.5 ns	213250 ns	1.00
batchnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	263010 ns	259447 ns	1.01
batchnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	28448372 ns	27707385 ns	1.03
batchnorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	521925 ns	530542 ns	0.98
layernorm(2, act=gelu, affine=false)(32 x 32)/forward/CPU/2 thread(s)	12416 ns	13209 ns	0.94
layernorm(2, act=gelu, affine=false)(32 x 32)/forward/CPU/4 thread(s)	11958 ns	12166 ns	0.98
layernorm(2, act=gelu, affine=false)(32 x 32)/forward/CPU/8 thread(s)	13291.5 ns	13584 ns	0.98
layernorm(2, act=gelu, affine=false)(32 x 32)/forward/CPU/1 thread(s)	12416 ns	12667 ns	0.98
layernorm(2, act=gelu, affine=false)(32 x 32)/forward/GPU/CUDA	135191 ns	135078 ns	1.00
layernorm(2, act=gelu, affine=false)(32 x 32)/forward/GPU/oneAPI	5177938 ns	5685986 ns	0.91
layernorm(2, act=gelu, affine=false)(32 x 32)/forward/GPU/AMDGPU	235942 ns	227730.5 ns	1.04
layernorm(2, act=gelu, affine=false)(32 x 32)/zygote/CPU/2 thread(s)	24458.5 ns	23917 ns	1.02
layernorm(2, act=gelu, affine=false)(32 x 32)/zygote/CPU/4 thread(s)	24750 ns	24083.5 ns	1.03
layernorm(2, act=gelu, affine=false)(32 x 32)/zygote/CPU/8 thread(s)	25020.5 ns	24750 ns	1.01
layernorm(2, act=gelu, affine=false)(32 x 32)/zygote/CPU/1 thread(s)	23792 ns	30146 ns	0.79
layernorm(2, act=gelu, affine=false)(32 x 32)/zygote/GPU/CUDA	844672 ns	833527 ns	1.01
layernorm(2, act=gelu, affine=false)(32 x 32)/zygote/GPU/oneAPI	39036318 ns	39963084.5 ns	0.98
layernorm(2, act=gelu, affine=false)(32 x 32)/zygote/GPU/AMDGPU	684117 ns	615374.5 ns	1.11
groupnorm(2, act=identity, affine=true)(32 x 32)/forward/CPU/2 thread(s)	8708 ns	9271 ns	0.94
groupnorm(2, act=identity, affine=true)(32 x 32)/forward/CPU/4 thread(s)	9687.5 ns	9541 ns	1.02
groupnorm(2, act=identity, affine=true)(32 x 32)/forward/CPU/8 thread(s)	10438 ns	10375 ns	1.01
groupnorm(2, act=identity, affine=true)(32 x 32)/forward/CPU/1 thread(s)	8541 ns	9250 ns	0.92
groupnorm(2, act=identity, affine=true)(32 x 32)/forward/GPU/CUDA	119636.5 ns	119628 ns	1.00
groupnorm(2, act=identity, affine=true)(32 x 32)/forward/GPU/oneAPI	3564984 ns	3356719.5 ns	1.06
groupnorm(2, act=identity, affine=true)(32 x 32)/forward/GPU/AMDGPU	70291 ns	74940 ns	0.94
groupnorm(2, act=identity, affine=true)(32 x 32)/zygote/CPU/2 thread(s)	13833 ns	14041 ns	0.99
groupnorm(2, act=identity, affine=true)(32 x 32)/zygote/CPU/4 thread(s)	14083 ns	13958 ns	1.01
groupnorm(2, act=identity, affine=true)(32 x 32)/zygote/CPU/8 thread(s)	14375 ns	14750 ns	0.97
groupnorm(2, act=identity, affine=true)(32 x 32)/zygote/CPU/1 thread(s)	14250 ns	13459 ns	1.06
groupnorm(2, act=identity, affine=true)(32 x 32)/zygote/GPU/CUDA	646842.5 ns	638262 ns	1.01
groupnorm(2, act=identity, affine=true)(32 x 32)/zygote/GPU/oneAPI	22010471 ns	22466836 ns	0.98
groupnorm(2, act=identity, affine=true)(32 x 32)/zygote/GPU/AMDGPU	363989 ns	344824 ns	1.06
groupnorm(2, act=identity, affine=false)(32 x 32)/forward/CPU/2 thread(s)	8875 ns	9666.5 ns	0.92
groupnorm(2, act=identity, affine=false)(32 x 32)/forward/CPU/4 thread(s)	9042 ns	9208 ns	0.98
groupnorm(2, act=identity, affine=false)(32 x 32)/forward/CPU/8 thread(s)	10792 ns	10959 ns	0.98
groupnorm(2, act=identity, affine=false)(32 x 32)/forward/CPU/1 thread(s)	9000 ns	9083.5 ns	0.99
groupnorm(2, act=identity, affine=false)(32 x 32)/forward/GPU/CUDA	119111 ns	118521 ns	1.00
groupnorm(2, act=identity, affine=false)(32 x 32)/forward/GPU/oneAPI	3329855.5 ns	3571671.5 ns	0.93
groupnorm(2, act=identity, affine=false)(32 x 32)/forward/GPU/AMDGPU	72351 ns	79399 ns	0.91
groupnorm(2, act=identity, affine=false)(32 x 32)/zygote/CPU/2 thread(s)	12541.5 ns	13416 ns	0.93
groupnorm(2, act=identity, affine=false)(32 x 32)/zygote/CPU/4 thread(s)	12958 ns	12416 ns	1.04
groupnorm(2, act=identity, affine=false)(32 x 32)/zygote/CPU/8 thread(s)	13625 ns	13479.5 ns	1.01
groupnorm(2, act=identity, affine=false)(32 x 32)/zygote/CPU/1 thread(s)	13270.5 ns	12708 ns	1.04
groupnorm(2, act=identity, affine=false)(32 x 32)/zygote/GPU/CUDA	534452 ns	530027 ns	1.01
groupnorm(2, act=identity, affine=false)(32 x 32)/zygote/GPU/oneAPI	19320932 ns	19360325 ns	1.00
groupnorm(2, act=identity, affine=false)(32 x 32)/zygote/GPU/AMDGPU	339643 ns	317163 ns	1.07
batchedmm(2, Bsize=128)/forward/CPU/2 thread(s)	29104 ns	30896 ns	0.94
batchedmm(2, Bsize=128)/forward/CPU/4 thread(s)	34250 ns	33813 ns	1.01
batchedmm(2, Bsize=128)/forward/CPU/8 thread(s)	31333 ns	32249.5 ns	0.97
batchedmm(2, Bsize=128)/forward/CPU/1 thread(s)	1667 ns	1875 ns	0.89
batchedmm(2, Bsize=128)/forward/GPU/CUDA	16403 ns	16425 ns	1.00
batchedmm(2, Bsize=128)/forward/GPU/oneAPI	77474262 ns	76985679 ns	1.01
batchedmm(2, Bsize=128)/forward/GPU/AMDGPU	78711 ns	76663 ns	1.03
batchedmm(2, Bsize=128)/zygote/CPU/2 thread(s)	5313 ns	5417 ns	0.98
batchedmm(2, Bsize=128)/zygote/CPU/4 thread(s)	5187.5 ns	5000 ns	1.04
batchedmm(2, Bsize=128)/zygote/CPU/8 thread(s)	5542 ns	5479.5 ns	1.01
batchedmm(2, Bsize=128)/zygote/CPU/1 thread(s)	6334 ns	6270.5 ns	1.01
batchedmm(2, Bsize=128)/zygote/GPU/CUDA	139944.5 ns	138278 ns	1.01
batchedmm(2, Bsize=128)/zygote/GPU/oneAPI	109880855.5 ns	109824422.5 ns	1.00
batchedmm(2, Bsize=128)/zygote/GPU/AMDGPU	385874 ns	340566 ns	1.13
batchnorm(2, act=identity, affine=true)(4 x 32)/forward/CPU/2 thread(s)	291 ns	333 ns	0.87
batchnorm(2, act=identity, affine=true)(4 x 32)/forward/CPU/4 thread(s)	375 ns	375 ns	1
batchnorm(2, act=identity, affine=true)(4 x 32)/forward/CPU/8 thread(s)	375 ns	375 ns	1
batchnorm(2, act=identity, affine=true)(4 x 32)/forward/CPU/1 thread(s)	291 ns	291 ns	1
batchnorm(2, act=identity, affine=true)(4 x 32)/forward/GPU/CUDA	26331 ns	25574 ns	1.03
batchnorm(2, act=identity, affine=true)(4 x 32)/forward/GPU/oneAPI	1212809 ns	1142450 ns	1.06
batchnorm(2, act=identity, affine=true)(4 x 32)/forward/GPU/AMDGPU	50001 ns	45666 ns	1.09
batchnorm(2, act=identity, affine=true)(4 x 32)/zygote/CPU/2 thread(s)	6375 ns	6458 ns	0.99
batchnorm(2, act=identity, affine=true)(4 x 32)/zygote/CPU/4 thread(s)	6520.5 ns	6375 ns	1.02
batchnorm(2, act=identity, affine=true)(4 x 32)/zygote/CPU/8 thread(s)	6833.5 ns	6791.5 ns	1.01
batchnorm(2, act=identity, affine=true)(4 x 32)/zygote/CPU/1 thread(s)	6250 ns	6458.5 ns	0.97
batchnorm(2, act=identity, affine=true)(4 x 32)/zygote/GPU/CUDA	189017.5 ns	185923.5 ns	1.02
batchnorm(2, act=identity, affine=true)(4 x 32)/zygote/GPU/oneAPI	24086071.5 ns	22900684.5 ns	1.05
batchnorm(2, act=identity, affine=true)(4 x 32)/zygote/GPU/AMDGPU	393884 ns	365402.5 ns	1.08
batchnorm(2, act=gelu, affine=true)(32 x 32)/forward/CPU/2 thread(s)	2000 ns	2084 ns	0.96
batchnorm(2, act=gelu, affine=true)(32 x 32)/forward/CPU/4 thread(s)	2084 ns	2084 ns	1
batchnorm(2, act=gelu, affine=true)(32 x 32)/forward/CPU/8 thread(s)	2166 ns	2083 ns	1.04
batchnorm(2, act=gelu, affine=true)(32 x 32)/forward/CPU/1 thread(s)	2000 ns	2000 ns	1
batchnorm(2, act=gelu, affine=true)(32 x 32)/forward/GPU/CUDA	26947 ns	26453 ns	1.02
batchnorm(2, act=gelu, affine=true)(32 x 32)/forward/GPU/oneAPI	1232598.5 ns	1207656 ns	1.02
batchnorm(2, act=gelu, affine=true)(32 x 32)/forward/GPU/AMDGPU	209912 ns	203645.5 ns	1.03
batchnorm(2, act=gelu, affine=true)(32 x 32)/zygote/CPU/2 thread(s)	17271 ns	18041 ns	0.96
batchnorm(2, act=gelu, affine=true)(32 x 32)/zygote/CPU/4 thread(s)	17958 ns	17166.5 ns	1.05
batchnorm(2, act=gelu, affine=true)(32 x 32)/zygote/CPU/8 thread(s)	18437.5 ns	17750 ns	1.04
batchnorm(2, act=gelu, affine=true)(32 x 32)/zygote/CPU/1 thread(s)	17416.5 ns	23458.5 ns	0.74
batchnorm(2, act=gelu, affine=true)(32 x 32)/zygote/GPU/CUDA	273533.5 ns	268326 ns	1.02
batchnorm(2, act=gelu, affine=true)(32 x 32)/zygote/GPU/oneAPI	25687047 ns	24994377.5 ns	1.03
batchnorm(2, act=gelu, affine=true)(32 x 32)/zygote/GPU/AMDGPU	706927 ns	600702.5 ns	1.18
layernorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	174834 ns	147875 ns	1.18
layernorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	177583 ns	155437.5 ns	1.14
layernorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	154000 ns	155125 ns	0.99
layernorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	147938 ns	151708 ns	0.98
layernorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/CUDA	193431 ns	190890.5 ns	1.01
layernorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	7836168 ns	7974634 ns	0.98
layernorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	191502 ns	271146.5 ns	0.71
layernorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	1322708.5 ns	1321937.5 ns	1.00
layernorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	1324354.5 ns	1330625 ns	1.00
layernorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	1323396 ns	1308375 ns	1.01
layernorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	1323166 ns	1285166 ns	1.03
layernorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	871146 ns	867140 ns	1.00
layernorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	46559834.5 ns	45331705.5 ns	1.03
layernorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	992400 ns	1006962 ns	0.99
layernorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/2 thread(s)	24521 ns	25500 ns	0.96
layernorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/4 thread(s)	25208 ns	23542 ns	1.07
layernorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/8 thread(s)	27666 ns	28708.5 ns	0.96
layernorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/CPU/1 thread(s)	24333 ns	24416.5 ns	1.00
layernorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/CUDA	230336.5 ns	226899 ns	1.02
layernorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/oneAPI	7412823 ns	7680667 ns	0.97
layernorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/forward/GPU/AMDGPU	115211 ns	128029 ns	0.90
layernorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/2 thread(s)	119395.5 ns	125062.5 ns	0.95
layernorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/4 thread(s)	178146.5 ns	165729.5 ns	1.07
layernorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/8 thread(s)	128749.5 ns	125854.5 ns	1.02
layernorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/CPU/1 thread(s)	117812.5 ns	180062 ns	0.65
layernorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/CUDA	999409 ns	998018.5 ns	1.00
layernorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/oneAPI	45419603 ns	44411227 ns	1.02
layernorm(4, act=relu, affine=false)(16 x 16 x 4 x 32)/zygote/GPU/AMDGPU	590316 ns	568743 ns	1.04
batchnorm(2, act=relu, affine=true)(4 x 32)/forward/CPU/2 thread(s)	292 ns	375 ns	0.78
batchnorm(2, act=relu, affine=true)(4 x 32)/forward/CPU/4 thread(s)	334 ns	375 ns	0.89
batchnorm(2, act=relu, affine=true)(4 x 32)/forward/CPU/8 thread(s)	375 ns	375 ns	1
batchnorm(2, act=relu, affine=true)(4 x 32)/forward/CPU/1 thread(s)	250 ns	250 ns	1
batchnorm(2, act=relu, affine=true)(4 x 32)/forward/GPU/CUDA	23826 ns	23453 ns	1.02
batchnorm(2, act=relu, affine=true)(4 x 32)/forward/GPU/oneAPI	1180276 ns	1190116 ns	0.99
batchnorm(2, act=relu, affine=true)(4 x 32)/forward/GPU/AMDGPU	49221 ns	44533 ns	1.11
batchnorm(2, act=relu, affine=true)(4 x 32)/zygote/CPU/2 thread(s)	6458 ns	6895.5 ns	0.94
batchnorm(2, act=relu, affine=true)(4 x 32)/zygote/CPU/4 thread(s)	6667 ns	6458 ns	1.03
batchnorm(2, act=relu, affine=true)(4 x 32)/zygote/CPU/8 thread(s)	7000 ns	6958 ns	1.01
batchnorm(2, act=relu, affine=true)(4 x 32)/zygote/CPU/1 thread(s)	6625 ns	6520.5 ns	1.02
batchnorm(2, act=relu, affine=true)(4 x 32)/zygote/GPU/CUDA	205667.5 ns	201834 ns	1.02
batchnorm(2, act=relu, affine=true)(4 x 32)/zygote/GPU/oneAPI	24604250 ns	23542895 ns	1.05
batchnorm(2, act=relu, affine=true)(4 x 32)/zygote/GPU/AMDGPU	395509.5 ns	372536 ns	1.06
layernorm(2, act=gelu, affine=true)(4 x 32)/forward/CPU/2 thread(s)	6292 ns	5645.5 ns	1.11
layernorm(2, act=gelu, affine=true)(4 x 32)/forward/CPU/4 thread(s)	6083 ns	5375 ns	1.13
layernorm(2, act=gelu, affine=true)(4 x 32)/forward/CPU/8 thread(s)	6875 ns	7979 ns	0.86
layernorm(2, act=gelu, affine=true)(4 x 32)/forward/CPU/1 thread(s)	5834 ns	5166 ns	1.13
layernorm(2, act=gelu, affine=true)(4 x 32)/forward/GPU/CUDA	139751.5 ns	139838.5 ns	1.00
layernorm(2, act=gelu, affine=true)(4 x 32)/forward/GPU/oneAPI	5712361.5 ns	5619575.5 ns	1.02
layernorm(2, act=gelu, affine=true)(4 x 32)/forward/GPU/AMDGPU	236162 ns	229750 ns	1.03
layernorm(2, act=gelu, affine=true)(4 x 32)/zygote/CPU/2 thread(s)	10354.5 ns	9958 ns	1.04
layernorm(2, act=gelu, affine=true)(4 x 32)/zygote/CPU/4 thread(s)	10167 ns	10042 ns	1.01
layernorm(2, act=gelu, affine=true)(4 x 32)/zygote/CPU/8 thread(s)	10209 ns	10417 ns	0.98
layernorm(2, act=gelu, affine=true)(4 x 32)/zygote/CPU/1 thread(s)	10125 ns	10854.5 ns	0.93
layernorm(2, act=gelu, affine=true)(4 x 32)/zygote/GPU/CUDA	879601 ns	866511 ns	1.02
layernorm(2, act=gelu, affine=true)(4 x 32)/zygote/GPU/oneAPI	40717350 ns	43130156 ns	0.94
layernorm(2, act=gelu, affine=true)(4 x 32)/zygote/GPU/AMDGPU	675267 ns	603858 ns	1.12
dense(2, bias=false, act=gelu)(2 x 128)/forward/CPU/2 thread(s)	709 ns	708 ns	1.00
dense(2, bias=false, act=gelu)(2 x 128)/forward/CPU/4 thread(s)	709 ns	708 ns	1.00
dense(2, bias=false, act=gelu)(2 x 128)/forward/CPU/8 thread(s)	708 ns	750 ns	0.94
dense(2, bias=false, act=gelu)(2 x 128)/forward/CPU/1 thread(s)	708 ns	667 ns	1.06
dense(2, bias=false, act=gelu)(2 x 128)/forward/GPU/CUDA	23026.5 ns	22827 ns	1.01
dense(2, bias=false, act=gelu)(2 x 128)/forward/GPU/oneAPI	2088235 ns	2079377 ns	1.00
dense(2, bias=false, act=gelu)(2 x 128)/forward/GPU/AMDGPU	210772 ns	202368 ns	1.04
dense(2, bias=false, act=gelu)(2 x 128)/zygote/CPU/2 thread(s)	4917 ns	4834 ns	1.02
dense(2, bias=false, act=gelu)(2 x 128)/zygote/CPU/4 thread(s)	4875 ns	4833 ns	1.01
dense(2, bias=false, act=gelu)(2 x 128)/zygote/CPU/8 thread(s)	5209 ns	5125 ns	1.02
dense(2, bias=false, act=gelu)(2 x 128)/zygote/CPU/1 thread(s)	4833 ns	6291 ns	0.77
dense(2, bias=false, act=gelu)(2 x 128)/zygote/GPU/CUDA	226029 ns	222098 ns	1.02
dense(2, bias=false, act=gelu)(2 x 128)/zygote/GPU/oneAPI	10810104.5 ns	9952955 ns	1.09
dense(2, bias=false, act=gelu)(2 x 128)/zygote/GPU/AMDGPU	586506 ns	471721 ns	1.24
groupnorm(2, act=identity, affine=true)(4 x 32)/forward/CPU/2 thread(s)	8146 ns	8750 ns	0.93
groupnorm(2, act=identity, affine=true)(4 x 32)/forward/CPU/4 thread(s)	8625 ns	7834 ns	1.10
groupnorm(2, act=identity, affine=true)(4 x 32)/forward/CPU/8 thread(s)	9270.5 ns	9375 ns	0.99
groupnorm(2, act=identity, affine=true)(4 x 32)/forward/CPU/1 thread(s)	7291.5 ns	7646 ns	0.95
groupnorm(2, act=identity, affine=true)(4 x 32)/forward/GPU/CUDA	118631.5 ns	117939.5 ns	1.01
groupnorm(2, act=identity, affine=true)(4 x 32)/forward/GPU/oneAPI	3512039 ns	3568146 ns	0.98
groupnorm(2, act=identity, affine=true)(4 x 32)/forward/GPU/AMDGPU	70461 ns	74409 ns	0.95
groupnorm(2, act=identity, affine=true)(4 x 32)/zygote/CPU/2 thread(s)	8125.5 ns	8792 ns	0.92
groupnorm(2, act=identity, affine=true)(4 x 32)/zygote/CPU/4 thread(s)	8583 ns	8583 ns	1
groupnorm(2, act=identity, affine=true)(4 x 32)/zygote/CPU/8 thread(s)	9250 ns	8875 ns	1.04
groupnorm(2, act=identity, affine=true)(4 x 32)/zygote/CPU/1 thread(s)	8542 ns	8083 ns	1.06
groupnorm(2, act=identity, affine=true)(4 x 32)/zygote/GPU/CUDA	573498 ns	568724.5 ns	1.01
groupnorm(2, act=identity, affine=true)(4 x 32)/zygote/GPU/oneAPI	20841257.5 ns	20842961 ns	1.00
groupnorm(2, act=identity, affine=true)(4 x 32)/zygote/GPU/AMDGPU	343184 ns	335106 ns	1.02
batchedmm(128, Bsize=4)/forward/CPU/2 thread(s)	126249.5 ns	126042 ns	1.00
batchedmm(128, Bsize=4)/forward/CPU/4 thread(s)	128834 ns	129208 ns	1.00
batchedmm(128, Bsize=4)/forward/CPU/8 thread(s)	131000 ns	129542 ns	1.01
batchedmm(128, Bsize=4)/forward/CPU/1 thread(s)	181395.5 ns	180792 ns	1.00
batchedmm(128, Bsize=4)/forward/GPU/CUDA	46573 ns	46423 ns	1.00
batchedmm(128, Bsize=4)/forward/GPU/oneAPI	70147077 ns	72616088 ns	0.97
batchedmm(128, Bsize=4)/forward/GPU/AMDGPU	95481 ns	101850 ns	0.94
batchedmm(128, Bsize=4)/zygote/CPU/2 thread(s)	338333 ns	315875 ns	1.07
batchedmm(128, Bsize=4)/zygote/CPU/4 thread(s)	349000 ns	334166.5 ns	1.04
batchedmm(128, Bsize=4)/zygote/CPU/8 thread(s)	337062.5 ns	323291.5 ns	1.04
batchedmm(128, Bsize=4)/zygote/CPU/1 thread(s)	567833.5 ns	609395.5 ns	0.93
batchedmm(128, Bsize=4)/zygote/GPU/CUDA	189615.5 ns	187684 ns	1.01
batchedmm(128, Bsize=4)/zygote/GPU/oneAPI	92008312 ns	93899553 ns	0.98
batchedmm(128, Bsize=4)/zygote/GPU/AMDGPU	440594.5 ns	405833.5 ns	1.09
dense(512, bias=true, act=identity)(512 x 128)/forward/CPU/2 thread(s)	397084 ns	397500 ns	1.00
dense(512, bias=true, act=identity)(512 x 128)/forward/CPU/4 thread(s)	288708 ns	287979.5 ns	1.00
dense(512, bias=true, act=identity)(512 x 128)/forward/CPU/8 thread(s)	288709 ns	288375 ns	1.00
dense(512, bias=true, act=identity)(512 x 128)/forward/CPU/1 thread(s)	756250 ns	756000 ns	1.00
dense(512, bias=true, act=identity)(512 x 128)/forward/GPU/CUDA	43906 ns	43964 ns	1.00
dense(512, bias=true, act=identity)(512 x 128)/forward/GPU/oneAPI	1378630 ns	1424885 ns	0.97
dense(512, bias=true, act=identity)(512 x 128)/forward/GPU/AMDGPU	81921 ns	79439 ns	1.03
dense(512, bias=true, act=identity)(512 x 128)/zygote/CPU/2 thread(s)	1460000 ns	1461000 ns	1.00
dense(512, bias=true, act=identity)(512 x 128)/zygote/CPU/4 thread(s)	1133854 ns	1133834 ns	1.00
dense(512, bias=true, act=identity)(512 x 128)/zygote/CPU/8 thread(s)	1133374.5 ns	1129645.5 ns	1.00
dense(512, bias=true, act=identity)(512 x 128)/zygote/CPU/1 thread(s)	2441854.5 ns	2449292 ns	1.00
dense(512, bias=true, act=identity)(512 x 128)/zygote/GPU/CUDA	258953 ns	254140 ns	1.02
dense(512, bias=true, act=identity)(512 x 128)/zygote/GPU/oneAPI	11022577.5 ns	11042616 ns	1.00
dense(512, bias=true, act=identity)(512 x 128)/zygote/GPU/AMDGPU	350313 ns	254646 ns	1.38
layernorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	652042 ns	626500 ns	1.04
layernorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	655770.5 ns	657208.5 ns	1.00
layernorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	649874.5 ns	649750.5 ns	1.00
layernorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	689167 ns	642417 ns	1.07
layernorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/CUDA	182902 ns	185720.5 ns	0.98
layernorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	8018912 ns	8332264.5 ns	0.96
layernorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	263233 ns	264649 ns	0.99
layernorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	2443292 ns	2452625 ns	1.00
layernorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	2446500 ns	2465208.5 ns	0.99
layernorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	2444562.5 ns	2459375 ns	0.99
layernorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	2453167 ns	2376375 ns	1.03
layernorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	954882.5 ns	949649 ns	1.01
layernorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	49210806 ns	53455476.5 ns	0.92
layernorm(4, act=relu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1318509 ns	1323598 ns	1.00
batchedmm(2, Bsize=32)/forward/CPU/2 thread(s)	33250.5 ns	32458 ns	1.02
batchedmm(2, Bsize=32)/forward/CPU/4 thread(s)	35646 ns	36521 ns	0.98
batchedmm(2, Bsize=32)/forward/CPU/8 thread(s)	34312 ns	34833 ns	0.99
batchedmm(2, Bsize=32)/forward/CPU/1 thread(s)	792 ns	959 ns	0.83
batchedmm(2, Bsize=32)/forward/GPU/CUDA	15879 ns	15902 ns	1.00
batchedmm(2, Bsize=32)/forward/GPU/oneAPI	67611192 ns	73782106 ns	0.92
batchedmm(2, Bsize=32)/forward/GPU/AMDGPU	85861 ns	74499.5 ns	1.15
batchedmm(2, Bsize=32)/zygote/CPU/2 thread(s)	3000 ns	3125 ns	0.96
batchedmm(2, Bsize=32)/zygote/CPU/4 thread(s)	3125 ns	3250 ns	0.96
batchedmm(2, Bsize=32)/zygote/CPU/8 thread(s)	3542 ns	3375 ns	1.05
batchedmm(2, Bsize=32)/zygote/CPU/1 thread(s)	3084 ns	3062.5 ns	1.01
batchedmm(2, Bsize=32)/zygote/GPU/CUDA	139105.5 ns	137187.5 ns	1.01
batchedmm(2, Bsize=32)/zygote/GPU/oneAPI	91963406 ns	98822060.5 ns	0.93
batchedmm(2, Bsize=32)/zygote/GPU/AMDGPU	349913.5 ns	314258 ns	1.11
batchnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	441375 ns	436500 ns	1.01
batchnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	439792 ns	438625 ns	1.00
batchnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	440208 ns	438791 ns	1.00
batchnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	450041 ns	445917 ns	1.01
batchnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/CUDA	43441 ns	42826 ns	1.01
batchnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	1439826.5 ns	1503651 ns	0.96
batchnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	239472 ns	374379.5 ns	0.64
batchnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	4142666 ns	4140000 ns	1.00
batchnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	4279125 ns	4271375 ns	1.00
batchnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	4266750 ns	4270687.5 ns	1.00
batchnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	4032604 ns	5468750 ns	0.74
batchnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	238139 ns	236201.5 ns	1.01
batchnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	36792447.5 ns	36248116 ns	1.02
batchnorm(4, act=gelu, affine=true)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1233123 ns	1135862 ns	1.09
dense(32, bias=false, act=identity)(32 x 128)/forward/CPU/2 thread(s)	3791 ns	3750 ns	1.01
dense(32, bias=false, act=identity)(32 x 128)/forward/CPU/4 thread(s)	3792 ns	3791 ns	1.00
dense(32, bias=false, act=identity)(32 x 128)/forward/CPU/8 thread(s)	3750 ns	3750 ns	1
dense(32, bias=false, act=identity)(32 x 128)/forward/CPU/1 thread(s)	3709 ns	3709 ns	1
dense(32, bias=false, act=identity)(32 x 128)/forward/GPU/CUDA	34461 ns	34158 ns	1.01
dense(32, bias=false, act=identity)(32 x 128)/forward/GPU/oneAPI	1301757 ns	1274307 ns	1.02
dense(32, bias=false, act=identity)(32 x 128)/forward/GPU/AMDGPU	40721 ns	41117 ns	0.99
dense(32, bias=false, act=identity)(32 x 128)/zygote/CPU/2 thread(s)	15292 ns	15375 ns	0.99
dense(32, bias=false, act=identity)(32 x 128)/zygote/CPU/4 thread(s)	15375 ns	15334 ns	1.00
dense(32, bias=false, act=identity)(32 x 128)/zygote/CPU/8 thread(s)	15625 ns	15500 ns	1.01
dense(32, bias=false, act=identity)(32 x 128)/zygote/CPU/1 thread(s)	15333 ns	15250 ns	1.01
dense(32, bias=false, act=identity)(32 x 128)/zygote/GPU/CUDA	259750 ns	255579 ns	1.02
dense(32, bias=false, act=identity)(32 x 128)/zygote/GPU/oneAPI	9866512.5 ns	8309435 ns	1.19
dense(32, bias=false, act=identity)(32 x 128)/zygote/GPU/AMDGPU	168172 ns	158606 ns	1.06
dense(512, bias=false, act=relu)(512 x 128)/forward/CPU/2 thread(s)	404291 ns	404792 ns	1.00
dense(512, bias=false, act=relu)(512 x 128)/forward/CPU/4 thread(s)	296209 ns	295917 ns	1.00
dense(512, bias=false, act=relu)(512 x 128)/forward/CPU/8 thread(s)	294584 ns	295958 ns	1.00
dense(512, bias=false, act=relu)(512 x 128)/forward/CPU/1 thread(s)	760542 ns	759750 ns	1.00
dense(512, bias=false, act=relu)(512 x 128)/forward/GPU/CUDA	113769 ns	113245 ns	1.00
dense(512, bias=false, act=relu)(512 x 128)/forward/GPU/oneAPI	1008763 ns	1043498 ns	0.97
dense(512, bias=false, act=relu)(512 x 128)/forward/GPU/AMDGPU	89651 ns	91962 ns	0.97
dense(512, bias=false, act=relu)(512 x 128)/zygote/CPU/2 thread(s)	1484624.5 ns	1482854 ns	1.00
dense(512, bias=false, act=relu)(512 x 128)/zygote/CPU/4 thread(s)	1157750 ns	1158625 ns	1.00
dense(512, bias=false, act=relu)(512 x 128)/zygote/CPU/8 thread(s)	1145000 ns	1150334 ns	1.00
dense(512, bias=false, act=relu)(512 x 128)/zygote/CPU/1 thread(s)	2462750 ns	2466708 ns	1.00
dense(512, bias=false, act=relu)(512 x 128)/zygote/GPU/CUDA	238527 ns	236768.5 ns	1.01
dense(512, bias=false, act=relu)(512 x 128)/zygote/GPU/oneAPI	12433376 ns	9725420.5 ns	1.28
dense(512, bias=false, act=relu)(512 x 128)/zygote/GPU/AMDGPU	352393.5 ns	298578 ns	1.18
batchnorm(2, act=gelu, affine=true)(4 x 32)/forward/CPU/2 thread(s)	500 ns	584 ns	0.86
batchnorm(2, act=gelu, affine=true)(4 x 32)/forward/CPU/4 thread(s)	625 ns	625 ns	1
batchnorm(2, act=gelu, affine=true)(4 x 32)/forward/CPU/8 thread(s)	584 ns	584 ns	1
batchnorm(2, act=gelu, affine=true)(4 x 32)/forward/CPU/1 thread(s)	541 ns	542 ns	1.00
batchnorm(2, act=gelu, affine=true)(4 x 32)/forward/GPU/CUDA	26037 ns	25569 ns	1.02
batchnorm(2, act=gelu, affine=true)(4 x 32)/forward/GPU/oneAPI	1255059.5 ns	1198679 ns	1.05
batchnorm(2, act=gelu, affine=true)(4 x 32)/forward/GPU/AMDGPU	210442 ns	202679 ns	1.04
batchnorm(2, act=gelu, affine=true)(4 x 32)/zygote/CPU/2 thread(s)	7541 ns	8083 ns	0.93
batchnorm(2, act=gelu, affine=true)(4 x 32)/zygote/CPU/4 thread(s)	7708 ns	7792 ns	0.99
batchnorm(2, act=gelu, affine=true)(4 x 32)/zygote/CPU/8 thread(s)	8084 ns	8375 ns	0.97
batchnorm(2, act=gelu, affine=true)(4 x 32)/zygote/CPU/1 thread(s)	7583 ns	8437.5 ns	0.90
batchnorm(2, act=gelu, affine=true)(4 x 32)/zygote/GPU/CUDA	211417.5 ns	207068.5 ns	1.02
batchnorm(2, act=gelu, affine=true)(4 x 32)/zygote/GPU/oneAPI	24400994.5 ns	25228707 ns	0.97
batchnorm(2, act=gelu, affine=true)(4 x 32)/zygote/GPU/AMDGPU	693867 ns	593474 ns	1.17
batchedmm(128, Bsize=32)/forward/CPU/2 thread(s)	829271.5 ns	829375 ns	1.00
batchedmm(128, Bsize=32)/forward/CPU/4 thread(s)	616604 ns	617667 ns	1.00
batchedmm(128, Bsize=32)/forward/CPU/8 thread(s)	618458 ns	618667 ns	1.00
batchedmm(128, Bsize=32)/forward/CPU/1 thread(s)	1541041.5 ns	1544417 ns	1.00
batchedmm(128, Bsize=32)/forward/GPU/CUDA	131087.5 ns	130866 ns	1.00
batchedmm(128, Bsize=32)/forward/GPU/oneAPI	67626584 ns	74874331.5 ns	0.90
batchedmm(128, Bsize=32)/forward/GPU/AMDGPU	167721 ns	211214 ns	0.79
batchedmm(128, Bsize=32)/zygote/CPU/2 thread(s)	2681083 ns	2686104.5 ns	1.00
batchedmm(128, Bsize=32)/zygote/CPU/4 thread(s)	1986250 ns	1994542 ns	1.00
batchedmm(128, Bsize=32)/zygote/CPU/8 thread(s)	1998541.5 ns	1998375 ns	1.00
batchedmm(128, Bsize=32)/zygote/CPU/1 thread(s)	4921791 ns	4960479 ns	0.99
batchedmm(128, Bsize=32)/zygote/GPU/CUDA	235041 ns	234509 ns	1.00
batchedmm(128, Bsize=32)/zygote/GPU/oneAPI	96224859 ns	102181218 ns	0.94
batchedmm(128, Bsize=32)/zygote/GPU/AMDGPU	859218 ns	831293.5 ns	1.03
batchnorm(2, act=relu, affine=false)(4 x 32)/forward/CPU/2 thread(s)	333 ns	292 ns	1.14
batchnorm(2, act=relu, affine=false)(4 x 32)/forward/CPU/4 thread(s)	375 ns	375 ns	1
batchnorm(2, act=relu, affine=false)(4 x 32)/forward/CPU/8 thread(s)	375 ns	375 ns	1
batchnorm(2, act=relu, affine=false)(4 x 32)/forward/CPU/1 thread(s)	250 ns	250 ns	1
batchnorm(2, act=relu, affine=false)(4 x 32)/forward/GPU/CUDA	33342 ns	32562 ns	1.02
batchnorm(2, act=relu, affine=false)(4 x 32)/forward/GPU/oneAPI	1243213 ns	1276503 ns	0.97
batchnorm(2, act=relu, affine=false)(4 x 32)/forward/GPU/AMDGPU	49520 ns	48691 ns	1.02
batchnorm(2, act=relu, affine=false)(4 x 32)/zygote/CPU/2 thread(s)	6312.5 ns	6333 ns	1.00
batchnorm(2, act=relu, affine=false)(4 x 32)/zygote/CPU/4 thread(s)	6375 ns	6375 ns	1
batchnorm(2, act=relu, affine=false)(4 x 32)/zygote/CPU/8 thread(s)	6917 ns	6667 ns	1.04
batchnorm(2, act=relu, affine=false)(4 x 32)/zygote/CPU/1 thread(s)	6250 ns	6104.5 ns	1.02
batchnorm(2, act=relu, affine=false)(4 x 32)/zygote/GPU/CUDA	226628 ns	227701 ns	1.00
batchnorm(2, act=relu, affine=false)(4 x 32)/zygote/GPU/oneAPI	20936439.5 ns	21756022 ns	0.96
batchnorm(2, act=relu, affine=false)(4 x 32)/zygote/GPU/AMDGPU	365763 ns	346728 ns	1.05
layernorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	1723875 ns	1760625 ns	0.98
layernorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	1762479 ns	1749875 ns	1.01
layernorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	1732458.5 ns	1744292 ns	0.99
layernorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	1731875 ns	1755166 ns	0.99
layernorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/CUDA	190679 ns	189332 ns	1.01
layernorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	8143920 ns	7765672 ns	1.05
layernorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	366039 ns	413433 ns	0.89
layernorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	4353396 ns	4360416 ns	1.00
layernorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	4360791.5 ns	4366917 ns	1.00
layernorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	4367521 ns	4349104 ns	1.00
layernorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	4360208 ns	5705104 ns	0.76
layernorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	855902 ns	849205 ns	1.01
layernorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	46724354.5 ns	48802559 ns	0.96
layernorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1250493 ns	1205562.5 ns	1.04
bias_activation(512, act=relu)(512 x 128)/forward/CPU/2 thread(s)	13708 ns	9604 ns	1.43
bias_activation(512, act=relu)(512 x 128)/forward/CPU/4 thread(s)	7166 ns	6916 ns	1.04
bias_activation(512, act=relu)(512 x 128)/forward/CPU/8 thread(s)	7834 ns	8208 ns	0.95
bias_activation(512, act=relu)(512 x 128)/forward/CPU/1 thread(s)	7229 ns	6854 ns	1.05
bias_activation(512, act=relu)(512 x 128)/forward/GPU/CUDA	22753 ns	22924.5 ns	0.99
bias_activation(512, act=relu)(512 x 128)/forward/GPU/oneAPI	1051464 ns	1184238.5 ns	0.89
bias_activation(512, act=relu)(512 x 128)/forward/GPU/AMDGPU	37990 ns	46437 ns	0.82
bias_activation(512, act=relu)(512 x 128)/zygote/CPU/2 thread(s)	45958.5 ns	50604.5 ns	0.91
bias_activation(512, act=relu)(512 x 128)/zygote/CPU/4 thread(s)	50187.5 ns	52166 ns	0.96
bias_activation(512, act=relu)(512 x 128)/zygote/CPU/8 thread(s)	65249.5 ns	45458.5 ns	1.44
bias_activation(512, act=relu)(512 x 128)/zygote/CPU/1 thread(s)	68708 ns	33312.5 ns	2.06
bias_activation(512, act=relu)(512 x 128)/zygote/GPU/CUDA	213762.5 ns	211538 ns	1.01
bias_activation(512, act=relu)(512 x 128)/zygote/GPU/oneAPI	10164364 ns	10576796.5 ns	0.96
bias_activation(512, act=relu)(512 x 128)/zygote/GPU/AMDGPU	234103 ns	226508 ns	1.03
batchedmm(2, Bsize=512)/forward/CPU/2 thread(s)	20791.5 ns	21646 ns	0.96
batchedmm(2, Bsize=512)/forward/CPU/4 thread(s)	25208 ns	26083.5 ns	0.97
batchedmm(2, Bsize=512)/forward/CPU/8 thread(s)	24229 ns	24958.5 ns	0.97
batchedmm(2, Bsize=512)/forward/CPU/1 thread(s)	5208 ns	5291.5 ns	0.98
batchedmm(2, Bsize=512)/forward/GPU/CUDA	18045 ns	18121 ns	1.00
batchedmm(2, Bsize=512)/forward/GPU/oneAPI	82328327.5 ns	88732630 ns	0.93
batchedmm(2, Bsize=512)/forward/GPU/AMDGPU	90131 ns	73668 ns	1.22
batchedmm(2, Bsize=512)/zygote/CPU/2 thread(s)	12312.5 ns	12125 ns	1.02
batchedmm(2, Bsize=512)/zygote/CPU/4 thread(s)	10500 ns	10667 ns	0.98
batchedmm(2, Bsize=512)/zygote/CPU/8 thread(s)	10875 ns	10833 ns	1.00
batchedmm(2, Bsize=512)/zygote/CPU/1 thread(s)	18125 ns	18042 ns	1.00
batchedmm(2, Bsize=512)/zygote/GPU/CUDA	222607.5 ns	221707 ns	1.00
batchedmm(2, Bsize=512)/zygote/GPU/oneAPI	143966308.5 ns	148404121 ns	0.97
batchedmm(2, Bsize=512)/zygote/GPU/AMDGPU	383434 ns	322703 ns	1.19
dense(512, bias=true, act=relu)(512 x 128)/forward/CPU/2 thread(s)	405834 ns	405917 ns	1.00
dense(512, bias=true, act=relu)(512 x 128)/forward/CPU/4 thread(s)	297333 ns	296791.5 ns	1.00
dense(512, bias=true, act=relu)(512 x 128)/forward/CPU/8 thread(s)	296750 ns	297167 ns	1.00
dense(512, bias=true, act=relu)(512 x 128)/forward/CPU/1 thread(s)	762541 ns	756709 ns	1.01
dense(512, bias=true, act=relu)(512 x 128)/forward/GPU/CUDA	46967 ns	46696 ns	1.01
dense(512, bias=true, act=relu)(512 x 128)/forward/GPU/oneAPI	1397676 ns	1393570.5 ns	1.00
dense(512, bias=true, act=relu)(512 x 128)/forward/GPU/AMDGPU	90631 ns	90770 ns	1.00
dense(512, bias=true, act=relu)(512 x 128)/zygote/CPU/2 thread(s)	1478916 ns	1487375 ns	0.99
dense(512, bias=true, act=relu)(512 x 128)/zygote/CPU/4 thread(s)	1164458 ns	1163500 ns	1.00
dense(512, bias=true, act=relu)(512 x 128)/zygote/CPU/8 thread(s)	1157937.5 ns	1157209 ns	1.00
dense(512, bias=true, act=relu)(512 x 128)/zygote/CPU/1 thread(s)	2468458 ns	2472417 ns	1.00
dense(512, bias=true, act=relu)(512 x 128)/zygote/GPU/CUDA	284577.5 ns	283340.5 ns	1.00
dense(512, bias=true, act=relu)(512 x 128)/zygote/GPU/oneAPI	14188453 ns	11947586 ns	1.19
dense(512, bias=true, act=relu)(512 x 128)/zygote/GPU/AMDGPU	375254 ns	269032 ns	1.39
batchnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	438667 ns	436458 ns	1.01
batchnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	439125 ns	443270.5 ns	0.99
batchnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	440208 ns	440750 ns	1.00
batchnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	447917 ns	449000 ns	1.00
batchnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/CUDA	54562 ns	53940 ns	1.01
batchnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	999880.5 ns	1027722 ns	0.97
batchnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	236502.5 ns	323133 ns	0.73
batchnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	4148000 ns	4138541 ns	1.00
batchnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	4270667 ns	4268354.5 ns	1.00
batchnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	4263812.5 ns	4258750 ns	1.00
batchnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	4038187.5 ns	5475229.5 ns	0.74
batchnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	258729.5 ns	255597 ns	1.01
batchnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	31613962 ns	31502698.5 ns	1.00
batchnorm(4, act=gelu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1211463 ns	1132896.5 ns	1.07
dense(32, bias=true, act=gelu)(32 x 128)/forward/CPU/2 thread(s)	9292 ns	9333 ns	1.00
dense(32, bias=true, act=gelu)(32 x 128)/forward/CPU/4 thread(s)	8000 ns	8000 ns	1
dense(32, bias=true, act=gelu)(32 x 128)/forward/CPU/8 thread(s)	8000 ns	8000 ns	1
dense(32, bias=true, act=gelu)(32 x 128)/forward/CPU/1 thread(s)	13250 ns	13250 ns	1
dense(32, bias=true, act=gelu)(32 x 128)/forward/GPU/CUDA	24006 ns	23885 ns	1.01
dense(32, bias=true, act=gelu)(32 x 128)/forward/GPU/oneAPI	2083029 ns	1973050 ns	1.06
dense(32, bias=true, act=gelu)(32 x 128)/forward/GPU/AMDGPU	213222 ns	202528 ns	1.05
dense(32, bias=true, act=gelu)(32 x 128)/zygote/CPU/2 thread(s)	49667 ns	49625 ns	1.00
dense(32, bias=true, act=gelu)(32 x 128)/zygote/CPU/4 thread(s)	49583 ns	49667 ns	1.00
dense(32, bias=true, act=gelu)(32 x 128)/zygote/CPU/8 thread(s)	50041 ns	49583 ns	1.01
dense(32, bias=true, act=gelu)(32 x 128)/zygote/CPU/1 thread(s)	49416 ns	71667 ns	0.69
dense(32, bias=true, act=gelu)(32 x 128)/zygote/GPU/CUDA	344384 ns	336641 ns	1.02
dense(32, bias=true, act=gelu)(32 x 128)/zygote/GPU/oneAPI	12740327 ns	13058534 ns	0.98
dense(32, bias=true, act=gelu)(32 x 128)/zygote/GPU/AMDGPU	656211.5 ns	508895.5 ns	1.29
groupnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/2 thread(s)	83063 ns	108270.5 ns	0.77
groupnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/4 thread(s)	82958 ns	86167 ns	0.96
groupnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/8 thread(s)	87395.5 ns	86500 ns	1.01
groupnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/CPU/1 thread(s)	107312.5 ns	146083 ns	0.73
groupnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/CUDA	192844 ns	192063 ns	1.00
groupnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/oneAPI	6092023.5 ns	5750624 ns	1.06
groupnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/forward/GPU/AMDGPU	200502 ns	267851 ns	0.75
groupnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/2 thread(s)	2016750 ns	2018917 ns	1.00
groupnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/4 thread(s)	2018396 ns	2016937.5 ns	1.00
groupnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/8 thread(s)	2015124.5 ns	2011375 ns	1.00
groupnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/CPU/1 thread(s)	2019500 ns	2024000.5 ns	1.00
groupnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/CUDA	519972 ns	511598 ns	1.02
groupnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/oneAPI	27686183 ns	30563079 ns	0.91
groupnorm(4, act=relu, affine=false)(16 x 16 x 32 x 32)/zygote/GPU/AMDGPU	1092442 ns	860237 ns	1.27

This comment was automatically generated by workflow using github-action-benchmark.