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

We can not swap multiplicand and multiplier because the sve intrinsics
are predicated. Imagine lanes in vectors having the following values:
         pg = 0
         multiplicand = 1 (from dup)
         multiplier = 2
The resulting value should be 1, but if we swap multiplicand and multiplier it will become 2,
which is incorrect.

Differential Revision: https://reviews.llvm.org/D114577

diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index ea21ad1..34015d2 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -833,17 +833,12 @@ static Optional<Instruction *> instCombineSVEVectorMul(InstCombiner &IC,
     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

diff --git a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-fmul-idempotency.ll b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-fmul-idempotency.ll
index 9bc48d8..77c76ea 100644 (file)
--- a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-fmul-idempotency.ll
+++ b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-fmul-idempotency.ll
@@ -32,7 +32,8 @@ define <vscale x 2 x double> @idempotent_fmul_f64(<vscale x 2 x i1> %pg, <vscale
 
 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.

diff --git a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-mul-idempotency.ll b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-mul-idempotency.ll
index e07fa92..e6acd36 100644 (file)
--- a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-mul-idempotency.ll
+++ b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-mul-idempotency.ll
@@ -32,7 +32,8 @@ define <vscale x 2 x i64> @idempotent_mul_i64(<vscale x 2 x i1> %pg, <vscale x 2
 
 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.