[PATCH] D114577: [AArch64][SVEIntrinsicOpts] Fix: predicated SVE mul/fmul are not commutative

[Igor Kirillov via Phabricator via llvm-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rG08d45e6f4da0: [AArch64][SVEIntrinsicOpts] Fix: predicated SVE mul/fmul are not commutative (authored by igor.kirillov).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D114577/new/

https://reviews.llvm.org/D114577

Files:
  llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
  llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-fmul-idempotency.ll
  llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-mul-idempotency.ll


Index: llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-mul-idempotency.ll
===================================================================
--- llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-mul-idempotency.ll
+++ llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-mul-idempotency.ll
@@ -32,7 +32,8 @@
 
 define <vscale x 2 x i64> @idempotent_mul_different_argument_order(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) #0 {
 ; CHECK-LABEL: @idempotent_mul_different_argument_order(
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[A:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[PG:%.*]], <vscale x 2 x i64> shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i32 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x i64> [[A:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 ;
   %1 = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 1)
   ; Different argument order to the above tests.
Index: llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-fmul-idempotency.ll
===================================================================
--- llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-fmul-idempotency.ll
+++ llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-fmul-idempotency.ll
@@ -32,7 +32,8 @@
 
 define <vscale x 2 x double> @idempotent_fmul_different_argument_order(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a) #0 {
 ; CHECK-LABEL: @idempotent_fmul_different_argument_order(
-; CHECK-NEXT:    ret <vscale x 2 x double> [[A:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> [[PG:%.*]], <vscale x 2 x double> shufflevector (<vscale x 2 x double> insertelement (<vscale x 2 x double> poison, double 1.000000e+00, i32 0), <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x double> [[A:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
 ;
   %1 = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double 1.0)
   ; Different argument order to the above tests.
Index: llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -833,17 +833,12 @@
     return match(SplatValue, m_FPOne()) || match(SplatValue, m_One());
   };
 
-  // The OpMultiplier variable should always point to the dup (if any), so
-  // swap if necessary.
-  if (IsUnitDup(OpMultiplicand) || IsUnitSplat(OpMultiplicand))
-    std::swap(OpMultiplier, OpMultiplicand);
-
   if (IsUnitSplat(OpMultiplier)) {
-    // [f]mul pg (dupx 1) %n => %n
+    // [f]mul pg %n, (dupx 1) => %n
     OpMultiplicand->takeName(&II);
     return IC.replaceInstUsesWith(II, OpMultiplicand);
   } else if (IsUnitDup(OpMultiplier)) {
-    // [f]mul pg (dup pg 1) %n => %n
+    // [f]mul pg %n, (dup pg 1) => %n
     auto *DupInst = cast<IntrinsicInst>(OpMultiplier);
     auto *DupPg = DupInst->getOperand(1);
     // TODO: this is naive. The optimization is still valid if DupPg


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D114577.390014.patch
Type: text/x-patch
Size: 3206 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20211126/06494782/attachment.bin>