Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Omnibus PR - Oct 2023 #678

Merged
merged 15 commits into from
Oct 27, 2022
Merged

Omnibus PR - Oct 2023 #678

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
2bff4d9
Move pba, sba pool, and mem_t to the thrinfo_t object.
fgvanzee Oct 18, 2022
1508e1c
De-template GEMMT, TRMM, and TRSM macro-kernels.
devinamatthews Oct 5, 2022
6789db1
Remove duplicate declaration.
devinamatthews Oct 14, 2022
1592640
Modify bli_l3_determine_kc.
devinamatthews Oct 14, 2022
0f753b8
Fix incorrect macro for BLAS int size.
devinamatthews Oct 14, 2022
ec54df5
Remote cntl_t parameter from bli_*_front.
devinamatthews Oct 14, 2022
19f80ed
Remove extraneous barrier from gemm/trsm variant 3.
devinamatthews Oct 19, 2022
80b8d8c
Separate the l3 thread decorator into two parts.
devinamatthews Oct 19, 2022
4b2affd
Modify the "level" of the thread control tree passed in at each opera…
devinamatthews Oct 19, 2022
cb16bd9
Rename mis-named bli_thread_* functions.
devinamatthews Oct 19, 2022
028b6db
Fix unused variable errors stemming from neglecting imaginary part.
devinamatthews Oct 23, 2022
44bd6af
Fix bug in bli_gemm_front.
devinamatthews Oct 23, 2022
e85b2d1
Fix gemmsup.
devinamatthews Oct 23, 2022
3f41f20
Minor cleanups, variable renames, etc.
fgvanzee Oct 26, 2022
b8d6d24
More whitespace changes.
fgvanzee Oct 27, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions addon/gemmd/attic/bao_gemmd_bp_var2.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -386,8 +386,8 @@ void PASTECH2(bao_,ch,varname) \
/* Query the number of threads and thread ids for the JR loop.
NOTE: These values are only needed when computing the next
micropanel of B. */ \
const dim_t jr_nt = bli_thread_n_way( thread_jr ); \
const dim_t jr_tid = bli_thread_work_id( thread_jr ); \
const dim_t jr_nt = bli_thrinfo_n_way( thread_jr ); \
const dim_t jr_tid = bli_thrinfo_work_id( thread_jr ); \
\
/* Compute number of primary and leftover components of the JR loop. */ \
dim_t jr_iter = ( nc_cur + NR - 1 ) / NR; \
Expand Down Expand Up @@ -416,8 +416,8 @@ void PASTECH2(bao_,ch,varname) \
/* Query the number of threads and thread ids for the IR loop.
NOTE: These values are only needed when computing the next
micropanel of A. */ \
const dim_t ir_nt = bli_thread_n_way( thread_ir ); \
const dim_t ir_tid = bli_thread_work_id( thread_ir ); \
const dim_t ir_nt = bli_thrinfo_n_way( thread_ir ); \
const dim_t ir_tid = bli_thrinfo_work_id( thread_ir ); \
\
/* Compute number of primary and leftover components of the IR loop. */ \
dim_t ir_iter = ( mc_cur + MR - 1 ) / MR; \
Expand Down Expand Up @@ -476,7 +476,7 @@ void PASTECH2(bao_,ch,varname) \
/* This barrier is needed to prevent threads from starting to pack
the next row panel of B before the current row panel is fully
computed upon. */ \
bli_thread_barrier( thread_pb ); \
bli_thrinfo_barrier( thread_pb ); \
} \
} \
\
Expand Down
10 changes: 5 additions & 5 deletions addon/gemmd/bao_gemmd_bp_var1.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -370,8 +370,8 @@ void PASTECH2(bao_,ch,varname) \
/* Query the number of threads and thread ids for the JR loop.
NOTE: These values are only needed when computing the next
micropanel of B. */ \
const dim_t jr_nt = bli_thread_n_way( thread_jr ); \
const dim_t jr_tid = bli_thread_work_id( thread_jr ); \
const dim_t jr_nt = bli_thrinfo_n_way( thread_jr ); \
const dim_t jr_tid = bli_thrinfo_work_id( thread_jr ); \
\
/* Compute number of primary and leftover components of the JR loop. */ \
dim_t jr_iter = ( nc_cur + NR - 1 ) / NR; \
Expand Down Expand Up @@ -400,8 +400,8 @@ void PASTECH2(bao_,ch,varname) \
/* Query the number of threads and thread ids for the IR loop.
NOTE: These values are only needed when computing the next
micropanel of A. */ \
const dim_t ir_nt = bli_thread_n_way( thread_ir ); \
const dim_t ir_tid = bli_thread_work_id( thread_ir ); \
const dim_t ir_nt = bli_thrinfo_n_way( thread_ir ); \
const dim_t ir_tid = bli_thrinfo_work_id( thread_ir ); \
\
/* Compute number of primary and leftover components of the IR loop. */ \
dim_t ir_iter = ( mc_cur + MR - 1 ) / MR; \
Expand Down Expand Up @@ -458,7 +458,7 @@ void PASTECH2(bao_,ch,varname) \
/* This barrier is needed to prevent threads from starting to pack
the next row panel of B before the current row panel is fully
computed upon. */ \
bli_thread_barrier( rntm, thread_pb ); \
bli_thrinfo_barrier( thread_pb ); \
} \
} \
\
Expand Down
10 changes: 5 additions & 5 deletions addon/gemmd/bao_l3_packm_a.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,7 +61,7 @@ void PASTECH2(bao_,ch,opname) \
\
/* Barrier to make sure all threads are caught up and ready to begin the
packm stage. */ \
bli_thread_barrier( rntm, thread ); \
bli_thrinfo_barrier( thread ); \
\
/* Compute the size of the memory block eneded. */ \
siz_t size_needed = sizeof( ctype ) * m_pack * k_pack; \
Expand Down Expand Up @@ -90,7 +90,7 @@ void PASTECH2(bao_,ch,opname) \
\
/* Broadcast the address of the chief thread's passed-in mem_t to all
threads. */ \
mem_t* mem_p = bli_thread_broadcast( rntm, thread, mem ); \
mem_t* mem_p = bli_thrinfo_broadcast( thread, mem ); \
\
/* Non-chief threads: Copy the contents of the chief thread's
passed-in mem_t to the passed-in mem_t for this thread. (The
Expand Down Expand Up @@ -139,7 +139,7 @@ void PASTECH2(bao_,ch,opname) \
\
/* Broadcast the address of the chief thread's passed-in mem_t
to all threads. */ \
mem_t* mem_p = bli_thread_broadcast( rntm, thread, mem ); \
mem_t* mem_p = bli_thrinfo_broadcast( thread, mem ); \
\
/* Non-chief threads: Copy the contents of the chief thread's
passed-in mem_t to the passed-in mem_t for this thread. (The
Expand Down Expand Up @@ -313,13 +313,13 @@ void PASTECH2(bao_,ch,opname) \
d, incd, \
a, rs_a, cs_a, \
*p, *rs_p, *cs_p, \
pd_p, *ps_p, \
pd_p, *ps_p, \
cntx, \
thread \
); \
\
/* Barrier so that packing is done before computation. */ \
bli_thread_barrier( rntm, thread ); \
bli_thrinfo_barrier( thread ); \
}

//INSERT_GENTFUNC_BASIC0( packm_a )
Expand Down
10 changes: 5 additions & 5 deletions addon/gemmd/bao_l3_packm_b.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,7 +61,7 @@ void PASTECH2(bao_,ch,opname) \
\
/* Barrier to make sure all threads are caught up and ready to begin the
packm stage. */ \
bli_thread_barrier( rntm, thread ); \
bli_thrinfo_barrier( thread ); \
\
/* Compute the size of the memory block eneded. */ \
siz_t size_needed = sizeof( ctype ) * k_pack * n_pack; \
Expand Down Expand Up @@ -90,7 +90,7 @@ void PASTECH2(bao_,ch,opname) \
\
/* Broadcast the address of the chief thread's passed-in mem_t to all
threads. */ \
mem_t* mem_p = bli_thread_broadcast( rntm, thread, mem ); \
mem_t* mem_p = bli_thrinfo_broadcast( thread, mem ); \
\
/* Non-chief threads: Copy the contents of the chief thread's
passed-in mem_t to the passed-in mem_t for this thread. (The
Expand Down Expand Up @@ -139,7 +139,7 @@ void PASTECH2(bao_,ch,opname) \
\
/* Broadcast the address of the chief thread's passed-in mem_t
to all threads. */ \
mem_t* mem_p = bli_thread_broadcast( rntm, thread, mem ); \
mem_t* mem_p = bli_thrinfo_broadcast( thread, mem ); \
\
/* Non-chief threads: Copy the contents of the chief thread's
passed-in mem_t to the passed-in mem_t for this thread. (The
Expand Down Expand Up @@ -313,13 +313,13 @@ void PASTECH2(bao_,ch,opname) \
d, incd, \
b, rs_b, cs_b, \
*p, *rs_p, *cs_p, \
pd_p, *ps_p, \
pd_p, *ps_p, \
cntx, \
thread \
); \
\
/* Barrier so that packing is done before computation. */ \
bli_thread_barrier( rntm, thread ); \
bli_thrinfo_barrier( thread ); \
}

//INSERT_GENTFUNC_BASIC0( packm_b )
Expand Down
4 changes: 2 additions & 2 deletions addon/gemmd/bao_l3_packm_var1.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,8 +127,8 @@ void PASTECH2(bao_,ch,varname) \
\
/* Query the number of threads and thread ids from the current thread's
packm thrinfo_t node. */ \
const dim_t nt = bli_thread_n_way( thread ); \
const dim_t tid = bli_thread_work_id( thread ); \
const dim_t nt = bli_thrinfo_n_way( thread ); \
const dim_t tid = bli_thrinfo_work_id( thread ); \
\
/* Suppress warnings in case tid isn't used (ie: as in slab partitioning). */ \
( void )nt; \
Expand Down
4 changes: 2 additions & 2 deletions addon/gemmd/bao_l3_packm_var2.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,8 +127,8 @@ void PASTECH2(bao_,ch,varname) \
\
/* Query the number of threads and thread ids from the current thread's
packm thrinfo_t node. */ \
const dim_t nt = bli_thread_n_way( thread ); \
const dim_t tid = bli_thread_work_id( thread ); \
const dim_t nt = bli_thrinfo_n_way( thread ); \
const dim_t tid = bli_thrinfo_work_id( thread ); \
\
/* Suppress warnings in case tid isn't used (ie: as in slab partitioning). */ \
( void )nt; \
Expand Down
Loading