[AARCH64][CostModel] Modified the cost of mask vector load/store

Reviewed By: david-arm

Differential Revision: https://reviews.llvm.org/D134413

diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 355c661..eaa3031 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -2367,7 +2367,7 @@ AArch64TTIImpl::getMaskedMemoryOpCost(unsigned Opcode, Type *Src,
   if (cast<VectorType>(Src)->getElementCount() == ElementCount::getScalable(1))
     return InstructionCost::getInvalid();
 
-  return LT.first * 2;
+  return LT.first;
 }
 
 static unsigned getSVEGatherScatterOverhead(unsigned Opcode) {

diff --git a/llvm/test/Analysis/CostModel/AArch64/masked_ldst.ll b/llvm/test/Analysis/CostModel/AArch64/masked_ldst.ll
index cc62f84..71102b5 100644 (file)
--- a/llvm/test/Analysis/CostModel/AArch64/masked_ldst.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/masked_ldst.ll
@@ -56,25 +56,25 @@ entry:
 
 define void @scalable() {
 ; CHECK-LABEL: 'scalable'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv2i8 = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8.p0nxv2i8(<vscale x 2 x i8>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv4i8 = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0nxv4i8(<vscale x 4 x i8>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv8i8 = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8.p0nxv8i8(<vscale x 8 x i8>* undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv16i8 = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0nxv16i8(<vscale x 16 x i8>* undef, i32 8, <vscale x 16 x i1> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv2i16 = call <vscale x 2 x i16> @llvm.masked.load.nxv2i16.p0nxv2i16(<vscale x 2 x i16>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv4i16 = call <vscale x 4 x i16> @llvm.masked.load.nxv4i16.p0nxv4i16(<vscale x 4 x i16>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv8i16 = call <vscale x 8 x i16> @llvm.masked.load.nxv8i16.p0nxv8i16(<vscale x 8 x i16>* undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv2i32 = call <vscale x 2 x i32> @llvm.masked.load.nxv2i32.p0nxv2i32(<vscale x 2 x i32>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv4i32 = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv2i64 = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0nxv2i64(<vscale x 2 x i64>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv2f16 = call <vscale x 2 x half> @llvm.masked.load.nxv2f16.p0nxv2f16(<vscale x 2 x half>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv4f16 = call <vscale x 4 x half> @llvm.masked.load.nxv4f16.p0nxv4f16(<vscale x 4 x half>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv8f16 = call <vscale x 8 x half> @llvm.masked.load.nxv8f16.p0nxv8f16(<vscale x 8 x half>* undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv2f32 = call <vscale x 2 x float> @llvm.masked.load.nxv2f32.p0nxv2f32(<vscale x 2 x float>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv4f32 = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv2f64 = call <vscale x 2 x double> @llvm.masked.load.nxv2f64.p0nxv2f64(<vscale x 2 x double>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv2i8 = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8.p0nxv2i8(<vscale x 2 x i8>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv4i8 = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0nxv4i8(<vscale x 4 x i8>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv8i8 = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8.p0nxv8i8(<vscale x 8 x i8>* undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv16i8 = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0nxv16i8(<vscale x 16 x i8>* undef, i32 8, <vscale x 16 x i1> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv2i16 = call <vscale x 2 x i16> @llvm.masked.load.nxv2i16.p0nxv2i16(<vscale x 2 x i16>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv4i16 = call <vscale x 4 x i16> @llvm.masked.load.nxv4i16.p0nxv4i16(<vscale x 4 x i16>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv8i16 = call <vscale x 8 x i16> @llvm.masked.load.nxv8i16.p0nxv8i16(<vscale x 8 x i16>* undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv2i32 = call <vscale x 2 x i32> @llvm.masked.load.nxv2i32.p0nxv2i32(<vscale x 2 x i32>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv4i32 = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv2i64 = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0nxv2i64(<vscale x 2 x i64>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv2f16 = call <vscale x 2 x half> @llvm.masked.load.nxv2f16.p0nxv2f16(<vscale x 2 x half>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv4f16 = call <vscale x 4 x half> @llvm.masked.load.nxv4f16.p0nxv4f16(<vscale x 4 x half>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv8f16 = call <vscale x 8 x half> @llvm.masked.load.nxv8f16.p0nxv8f16(<vscale x 8 x half>* undef, i32 8, <vscale x 8 x i1> undef, <vscale x 8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv2f32 = call <vscale x 2 x float> @llvm.masked.load.nxv2f32.p0nxv2f32(<vscale x 2 x float>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv4f32 = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %nxv2f64 = call <vscale x 2 x double> @llvm.masked.load.nxv2f64.p0nxv2f64(<vscale x 2 x double>* undef, i32 8, <vscale x 2 x i1> undef, <vscale x 2 x double> undef)
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %nxv1i64 = call <vscale x 1 x i64> @llvm.masked.load.nxv1i64.p0nxv1i64(<vscale x 1 x i64>* undef, i32 8, <vscale x 1 x i1> undef, <vscale x 1 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %nxv4i64 = call <vscale x 4 x i64> @llvm.masked.load.nxv4i64.p0nxv4i64(<vscale x 4 x i64>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %nxv32f16 = call <vscale x 32 x half> @llvm.masked.load.nxv32f16.p0nxv32f16(<vscale x 32 x half>* undef, i32 8, <vscale x 32 x i1> undef, <vscale x 32 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv4i64 = call <vscale x 4 x i64> @llvm.masked.load.nxv4i64.p0nxv4i64(<vscale x 4 x i64>* undef, i32 8, <vscale x 4 x i1> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %nxv32f16 = call <vscale x 32 x half> @llvm.masked.load.nxv32f16.p0nxv32f16(<vscale x 32 x half>* undef, i32 8, <vscale x 32 x i1> undef, <vscale x 32 x half> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 entry:

diff --git a/llvm/test/Analysis/CostModel/AArch64/masked_ldst_vls.ll b/llvm/test/Analysis/CostModel/AArch64/masked_ldst_vls.ll
index d604fcc..eeb5417 100644 (file)
--- a/llvm/test/Analysis/CostModel/AArch64/masked_ldst_vls.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/masked_ldst_vls.ll
@@ -19,13 +19,13 @@ target triple = "aarch64-unknown-linux-gnu"
 
 define void @fixed_sve_vls() #0 {
 ; CHECK-LABEL: 'fixed_sve_vls'
-; CHECK:  Cost Model: Found an estimated cost of [[#mul(div(2047,VBITS)+1,2)]] for instruction: %v256i8 = call <256 x i8> @llvm.masked.load.v256i8.p0v256i8(<256 x i8>* undef, i32 8, <256 x i1> undef, <256 x i8> undef)
-; CHECK:  Cost Model: Found an estimated cost of [[#mul(div(4091,VBITS)+1,2)]] for instruction: %v256i16 = call <256 x i16> @llvm.masked.load.v256i16.p0v256i16(<256 x i16>* undef, i32 8, <256 x i1> undef, <256 x i16> undef)
-; CHECK:  Cost Model: Found an estimated cost of [[#mul(div(511,VBITS)+1,2)]] for instruction: %v16i32 = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* undef, i32 8, <16 x i1> undef, <16 x i32> undef)
-; CHECK:  Cost Model: Found an estimated cost of [[#mul(div(1023,VBITS)+1,2)]] for instruction: %v16i64 = call <16 x i64> @llvm.masked.load.v16i64.p0v16i64(<16 x i64>* undef, i32 8, <16 x i1> undef, <16 x i64> undef)
-; CHECK:  Cost Model: Found an estimated cost of [[#mul(div(8191,VBITS)+1,2)]] for instruction: %v512f16 = call <512 x half> @llvm.masked.load.v512f16.p0v512f16(<512 x half>* undef, i32 8, <512 x i1> undef, <512 x half> undef)
-; CHECK:  Cost Model: Found an estimated cost of [[#mul(div(8191,VBITS)+1,2)]] for instruction: %v256f32 = call <256 x float> @llvm.masked.load.v256f32.p0v256f32(<256 x float>* undef, i32 8, <256 x i1> undef, <256 x float> undef)
-; CHECK:  Cost Model: Found an estimated cost of [[#mul(div(8191,VBITS)+1,2)]] for instruction: %v128f64 = call <128 x double> @llvm.masked.load.v128f64.p0v128f64(<128 x double>* undef, i32 8, <128 x i1> undef, <128 x double> undef)
+; CHECK:  Cost Model: Found an estimated cost of [[#div(2047,VBITS)+1]] for instruction: %v256i8 = call <256 x i8> @llvm.masked.load.v256i8.p0v256i8(<256 x i8>* undef, i32 8, <256 x i1> undef, <256 x i8> undef)
+; CHECK:  Cost Model: Found an estimated cost of [[#div(4091,VBITS)+1]] for instruction: %v256i16 = call <256 x i16> @llvm.masked.load.v256i16.p0v256i16(<256 x i16>* undef, i32 8, <256 x i1> undef, <256 x i16> undef)
+; CHECK:  Cost Model: Found an estimated cost of [[#div(511,VBITS)+1]] for instruction: %v16i32 = call <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>* undef, i32 8, <16 x i1> undef, <16 x i32> undef)
+; CHECK:  Cost Model: Found an estimated cost of [[#div(1023,VBITS)+1]] for instruction: %v16i64 = call <16 x i64> @llvm.masked.load.v16i64.p0v16i64(<16 x i64>* undef, i32 8, <16 x i1> undef, <16 x i64> undef)
+; CHECK:  Cost Model: Found an estimated cost of [[#div(8191,VBITS)+1]] for instruction: %v512f16 = call <512 x half> @llvm.masked.load.v512f16.p0v512f16(<512 x half>* undef, i32 8, <512 x i1> undef, <512 x half> undef)
+; CHECK:  Cost Model: Found an estimated cost of [[#div(8191,VBITS)+1]] for instruction: %v256f32 = call <256 x float> @llvm.masked.load.v256f32.p0v256f32(<256 x float>* undef, i32 8, <256 x i1> undef, <256 x float> undef)
+; CHECK:  Cost Model: Found an estimated cost of [[#div(8191,VBITS)+1]] for instruction: %v128f64 = call <128 x double> @llvm.masked.load.v128f64.p0v128f64(<128 x double>* undef, i32 8, <128 x i1> undef, <128 x double> undef)
 ; CHECK:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 entry:
   %v256i8 = call <256 x i8> @llvm.masked.load.v256i8.p0v256i8(<256 x i8> *undef, i32 8, <256 x i1> undef, <256 x i8> undef)

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/masked-op-cost.ll b/llvm/test/Transforms/LoopVectorize/AArch64/masked-op-cost.ll
index c790aa5..04c0f2d 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/AArch64/masked-op-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/masked-op-cost.ll
@@ -46,7 +46,7 @@ for.inc:                                          ; preds = %for.body, %if.then
 
 
 ; CHECK-COST: Checking a loop in 'scalable'
-; CHECK-COST: Found an estimated cost of 2 for VF vscale x 4 For instruction:   store i32 2, i32* %arrayidx1, align 4
+; CHECK-COST: Found an estimated cost of 1 for VF vscale x 4 For instruction:   store i32 2, i32* %arrayidx1, align 4
 
 define void @scalable(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i64 %n) #0 {
 ; CHECK-LABEL: @scalable(