[PowerPC] Update chain uses when emitting lxsizx

[ecnelises]

Fixes #83362

[llvmbot]

@llvm/pr-subscribers-backend-powerpc

Author: Qiu Chaofan (ecnelises)

Changes

Fixes #83362

---

Full diff: https://github.com/llvm/llvm-project/pull/84892.diff

3 Files Affected:

• (modified) llvm/lib/Target/PowerPC/PPCISelLowering.cpp (+1)
• (modified) llvm/test/CodeGen/PowerPC/scalar-double-ldst.ll (+58)
• (modified) llvm/test/CodeGen/PowerPC/scalar-float-ldst.ll (+58)

diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index 68c80dd9aa5c76..f4c4f1e8342dac 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -15024,6 +15024,7 @@ SDValue PPCTargetLowering::combineFPToIntToFP(SDNode *N,
     SDValue Ld = DAG.getMemIntrinsicNode(PPCISD::LXSIZX, dl,
                                          DAG.getVTList(MVT::f64, MVT::Other),
                                          Ops, MVT::i8, LDN->getMemOperand());
+    DAG.ReplaceAllUsesOfValueWith(FirstOperand.getValue(1), Ld.getValue(1));
 
     // For signed conversion, we need to sign-extend the value in the VSR
     if (Signed) {
diff --git a/llvm/test/CodeGen/PowerPC/scalar-double-ldst.ll b/llvm/test/CodeGen/PowerPC/scalar-double-ldst.ll
index 6f68679325c579..798637b6840f1e 100644
--- a/llvm/test/CodeGen/PowerPC/scalar-double-ldst.ll
+++ b/llvm/test/CodeGen/PowerPC/scalar-double-ldst.ll
@@ -7281,3 +7281,61 @@ entry:
   store double %str, ptr inttoptr (i64 1000000000000 to ptr), align 4096
   ret void
 }
+
+define dso_local void @st_reversed_double_from_i8(ptr %ptr) {
+; CHECK-P10-LABEL: st_reversed_double_from_i8:
+; CHECK-P10:       # %bb.0: # %entry
+; CHECK-P10-NEXT:    li r4, 8
+; CHECK-P10-NEXT:    lxsibzx f0, 0, r3
+; CHECK-P10-NEXT:    xxspltidp vs2, -1023410176
+; CHECK-P10-NEXT:    lxsibzx f1, r3, r4
+; CHECK-P10-NEXT:    xscvuxddp f0, f0
+; CHECK-P10-NEXT:    xscvuxddp f1, f1
+; CHECK-P10-NEXT:    xsadddp f0, f0, f2
+; CHECK-P10-NEXT:    xsadddp f1, f1, f2
+; CHECK-P10-NEXT:    stfd f1, 0(r3)
+; CHECK-P10-NEXT:    stfd f0, 8(r3)
+; CHECK-P10-NEXT:    blr
+;
+; CHECK-P9-LABEL: st_reversed_double_from_i8:
+; CHECK-P9:       # %bb.0: # %entry
+; CHECK-P9-NEXT:    li r4, 8
+; CHECK-P9-NEXT:    lxsibzx f0, 0, r3
+; CHECK-P9-NEXT:    lxsibzx f1, r3, r4
+; CHECK-P9-NEXT:    addis r4, r2, .LCPI300_0@toc@ha
+; CHECK-P9-NEXT:    lfs f2, .LCPI300_0@toc@l(r4)
+; CHECK-P9-NEXT:    xscvuxddp f0, f0
+; CHECK-P9-NEXT:    xscvuxddp f1, f1
+; CHECK-P9-NEXT:    xsadddp f0, f0, f2
+; CHECK-P9-NEXT:    xsadddp f1, f1, f2
+; CHECK-P9-NEXT:    stfd f0, 8(r3)
+; CHECK-P9-NEXT:    stfd f1, 0(r3)
+; CHECK-P9-NEXT:    blr
+;
+; CHECK-P8-LABEL: st_reversed_double_from_i8:
+; CHECK-P8:       # %bb.0: # %entry
+; CHECK-P8-NEXT:    lbz r4, 0(r3)
+; CHECK-P8-NEXT:    lbz r5, 8(r3)
+; CHECK-P8-NEXT:    mtfprwz f0, r4
+; CHECK-P8-NEXT:    mtfprwz f1, r5
+; CHECK-P8-NEXT:    addis r4, r2, .LCPI300_0@toc@ha
+; CHECK-P8-NEXT:    lfs f2, .LCPI300_0@toc@l(r4)
+; CHECK-P8-NEXT:    xscvuxddp f0, f0
+; CHECK-P8-NEXT:    xscvuxddp f1, f1
+; CHECK-P8-NEXT:    xsadddp f0, f0, f2
+; CHECK-P8-NEXT:    xsadddp f1, f1, f2
+; CHECK-P8-NEXT:    stfd f1, 0(r3)
+; CHECK-P8-NEXT:    stfd f0, 8(r3)
+; CHECK-P8-NEXT:    blr
+entry:
+  %idx = getelementptr inbounds i8, ptr %ptr, i64 8
+  %i0 = load i8, ptr %ptr, align 1
+  %i1 = load i8, ptr %idx, align 1
+  %f0 = uitofp i8 %i0 to double
+  %f1 = uitofp i8 %i1 to double
+  %a0 = fadd double %f0, -1.280000e+02
+  %a1 = fadd double %f1, -1.280000e+02
+  store double %a1, ptr %ptr, align 8
+  store double %a0, ptr %idx, align 8
+  ret void
+}
diff --git a/llvm/test/CodeGen/PowerPC/scalar-float-ldst.ll b/llvm/test/CodeGen/PowerPC/scalar-float-ldst.ll
index 824dd4c4db6cb7..f3960573421298 100644
--- a/llvm/test/CodeGen/PowerPC/scalar-float-ldst.ll
+++ b/llvm/test/CodeGen/PowerPC/scalar-float-ldst.ll
@@ -7271,3 +7271,61 @@ entry:
   store double %conv, ptr inttoptr (i64 1000000000000 to ptr), align 4096
   ret void
 }
+
+define dso_local void @st_reversed_float_from_i8(ptr %ptr) {
+; CHECK-P10-LABEL: st_reversed_float_from_i8:
+; CHECK-P10:       # %bb.0: # %entry
+; CHECK-P10-NEXT:    li r4, 8
+; CHECK-P10-NEXT:    lxsibzx f0, 0, r3
+; CHECK-P10-NEXT:    xxspltidp vs2, -1023410176
+; CHECK-P10-NEXT:    lxsibzx f1, r3, r4
+; CHECK-P10-NEXT:    xscvuxdsp f0, f0
+; CHECK-P10-NEXT:    xscvuxdsp f1, f1
+; CHECK-P10-NEXT:    xsaddsp f0, f0, f2
+; CHECK-P10-NEXT:    xsaddsp f1, f1, f2
+; CHECK-P10-NEXT:    stfs f0, 8(r3)
+; CHECK-P10-NEXT:    stfs f1, 0(r3)
+; CHECK-P10-NEXT:    blr
+;
+; CHECK-P9-LABEL: st_reversed_float_from_i8:
+; CHECK-P9:       # %bb.0: # %entry
+; CHECK-P9-NEXT:    li r4, 8
+; CHECK-P9-NEXT:    lxsibzx f0, 0, r3
+; CHECK-P9-NEXT:    lxsibzx f1, r3, r4
+; CHECK-P9-NEXT:    addis r4, r2, .LCPI300_0@toc@ha
+; CHECK-P9-NEXT:    lfs f2, .LCPI300_0@toc@l(r4)
+; CHECK-P9-NEXT:    xscvuxdsp f0, f0
+; CHECK-P9-NEXT:    xscvuxdsp f1, f1
+; CHECK-P9-NEXT:    xsaddsp f0, f0, f2
+; CHECK-P9-NEXT:    xsaddsp f1, f1, f2
+; CHECK-P9-NEXT:    stfs f0, 8(r3)
+; CHECK-P9-NEXT:    stfs f1, 0(r3)
+; CHECK-P9-NEXT:    blr
+;
+; CHECK-P8-LABEL: st_reversed_float_from_i8:
+; CHECK-P8:       # %bb.0: # %entry
+; CHECK-P8-NEXT:    lbz r4, 0(r3)
+; CHECK-P8-NEXT:    lbz r5, 8(r3)
+; CHECK-P8-NEXT:    mtfprwz f0, r4
+; CHECK-P8-NEXT:    mtfprwz f1, r5
+; CHECK-P8-NEXT:    addis r4, r2, .LCPI300_0@toc@ha
+; CHECK-P8-NEXT:    lfs f2, .LCPI300_0@toc@l(r4)
+; CHECK-P8-NEXT:    xscvuxdsp f0, f0
+; CHECK-P8-NEXT:    xscvuxdsp f1, f1
+; CHECK-P8-NEXT:    xsaddsp f0, f0, f2
+; CHECK-P8-NEXT:    xsaddsp f1, f1, f2
+; CHECK-P8-NEXT:    stfs f1, 0(r3)
+; CHECK-P8-NEXT:    stfs f0, 8(r3)
+; CHECK-P8-NEXT:    blr
+entry:
+  %idx = getelementptr inbounds i8, ptr %ptr, i64 8
+  %i0 = load i8, ptr %ptr, align 1
+  %i1 = load i8, ptr %idx, align 1
+  %f0 = uitofp i8 %i0 to float
+  %f1 = uitofp i8 %i1 to float
+  %a0 = fadd float %f0, -1.280000e+02
+  %a1 = fadd float %f1, -1.280000e+02
+  store float %a1, ptr %ptr, align 8
+  store float %a0, ptr %idx, align 8
+  ret void
+}

[chenzheng1030]

Looks reasonable to me. Thanks for the fix.

[cuviper]

I confirmed that this fixes my original Rust workload, thanks!