[CostModel][X86] Update SSE41/AVX1 vXi32 SHL costs

SSE41 provides pmulld which allows the simpler pslld/paddd/cvttps2dq/pmulld pattern than SSE2's use of pmuludq.

llvm-svn: 291372

2 files changed, 14 insertions, 12 deletions

diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 30b20555257..489aab349d4 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -489,6 +489,8 @@ int X86TTIImpl::getArithmeticInstrCost(
     { ISD::SHL,  MVT::v32i8,  2*11 }, // pblendvb sequence.
     { ISD::SHL,  MVT::v8i16,    14 }, // pblendvb sequence.
     { ISD::SHL,  MVT::v16i16, 2*14 }, // pblendvb sequence.
+    { ISD::SHL,  MVT::v4i32,     4 }, // pslld/paddd/cvttps2dq/pmulld
+    { ISD::SHL,  MVT::v8i32,   2*4 }, // pslld/paddd/cvttps2dq/pmulld
 
     { ISD::SRL,  MVT::v16i8,    12 }, // pblendvb sequence.
     { ISD::SRL,  MVT::v32i8,  2*12 }, // pblendvb sequence.
diff --git a/llvm/test/Analysis/CostModel/X86/vshift-shl-cost.ll b/llvm/test/Analysis/CostModel/X86/vshift-shl-cost.ll
index 7090ae4a35e..98982225be8 100644
--- a/llvm/test/Analysis/CostModel/X86/vshift-shl-cost.ll
+++ b/llvm/test/Analysis/CostModel/X86/vshift-shl-cost.ll
@@ -57,8 +57,8 @@ define <8 x i64> @var_shift_v8i64(<8 x i64> %a, <8 x i64> %b) {
 define <4 x i32> @var_shift_v4i32(<4 x i32> %a, <4 x i32> %b) {
 ; CHECK: 'Cost Model Analysis' for function 'var_shift_v4i32':
 ; SSE2: Found an estimated cost of 10 for instruction:   %shift
-; SSE41: Found an estimated cost of 10 for instruction:   %shift
-; AVX: Found an estimated cost of 10 for instruction:   %shift
+; SSE41: Found an estimated cost of 4 for instruction:   %shift
+; AVX: Found an estimated cost of 4 for instruction:   %shift
 ; AVX2: Found an estimated cost of 1 for instruction:   %shift
 ; AVX512: Found an estimated cost of 1 for instruction:   %shift
 ; XOPAVX: Found an estimated cost of 1 for instruction:   %shift
@@ -70,8 +70,8 @@ define <4 x i32> @var_shift_v4i32(<4 x i32> %a, <4 x i32> %b) {
 define <8 x i32> @var_shift_v8i32(<8 x i32> %a, <8 x i32> %b) {
 ; CHECK: 'Cost Model Analysis' for function 'var_shift_v8i32':
 ; SSE2: Found an estimated cost of 20 for instruction:   %shift
-; SSE41: Found an estimated cost of 20 for instruction:   %shift
-; AVX: Found an estimated cost of 20 for instruction:   %shift
+; SSE41: Found an estimated cost of 8 for instruction:   %shift
+; AVX: Found an estimated cost of 8 for instruction:   %shift
 ; AVX2: Found an estimated cost of 1 for instruction:   %shift
 ; AVX512: Found an estimated cost of 1 for instruction:   %shift
 ; XOPAVX: Found an estimated cost of 2 for instruction:   %shift
@@ -83,8 +83,8 @@ define <8 x i32> @var_shift_v8i32(<8 x i32> %a, <8 x i32> %b) {
 define <16 x i32> @var_shift_v16i32(<16 x i32> %a, <16 x i32> %b) {
 ; CHECK: 'Cost Model Analysis' for function 'var_shift_v16i32':
 ; SSE2: Found an estimated cost of 40 for instruction:   %shift
-; SSE41: Found an estimated cost of 40 for instruction:   %shift
-; AVX: Found an estimated cost of 40 for instruction:   %shift
+; SSE41: Found an estimated cost of 16 for instruction:   %shift
+; AVX: Found an estimated cost of 16 for instruction:   %shift
 ; AVX2: Found an estimated cost of 2 for instruction:   %shift
 ; AVX512: Found an estimated cost of 1 for instruction:   %shift
 ; XOPAVX: Found an estimated cost of 4 for instruction:   %shift
@@ -216,8 +216,8 @@ define <8 x i64> @splatvar_shift_v8i64(<8 x i64> %a, <8 x i64> %b) {
 define <4 x i32> @splatvar_shift_v4i32(<4 x i32> %a, <4 x i32> %b) {
 ; CHECK: 'Cost Model Analysis' for function 'splatvar_shift_v4i32':
 ; SSE2: Found an estimated cost of 10 for instruction:   %shift
-; SSE41: Found an estimated cost of 10 for instruction:   %shift
-; AVX: Found an estimated cost of 10 for instruction:   %shift
+; SSE41: Found an estimated cost of 4 for instruction:   %shift
+; AVX: Found an estimated cost of 4 for instruction:   %shift
 ; AVX2: Found an estimated cost of 1 for instruction:   %shift
 ; AVX512: Found an estimated cost of 1 for instruction:   %shift
 ; XOPAVX: Found an estimated cost of 1 for instruction:   %shift
@@ -230,8 +230,8 @@ define <4 x i32> @splatvar_shift_v4i32(<4 x i32> %a, <4 x i32> %b) {
 define <8 x i32> @splatvar_shift_v8i32(<8 x i32> %a, <8 x i32> %b) {
 ; CHECK: 'Cost Model Analysis' for function 'splatvar_shift_v8i32':
 ; SSE2: Found an estimated cost of 20 for instruction:   %shift
-; SSE41: Found an estimated cost of 20 for instruction:   %shift
-; AVX: Found an estimated cost of 20 for instruction:   %shift
+; SSE41: Found an estimated cost of 8 for instruction:   %shift
+; AVX: Found an estimated cost of 8 for instruction:   %shift
 ; AVX2: Found an estimated cost of 1 for instruction:   %shift
 ; AVX512: Found an estimated cost of 1 for instruction:   %shift
 ; XOPAVX: Found an estimated cost of 2 for instruction:   %shift
@@ -244,8 +244,8 @@ define <8 x i32> @splatvar_shift_v8i32(<8 x i32> %a, <8 x i32> %b) {
 define <16 x i32> @splatvar_shift_v16i32(<16 x i32> %a, <16 x i32> %b) {
 ; CHECK: 'Cost Model Analysis' for function 'splatvar_shift_v16i32':
 ; SSE2: Found an estimated cost of 40 for instruction:   %shift
-; SSE41: Found an estimated cost of 40 for instruction:   %shift
-; AVX: Found an estimated cost of 40 for instruction:   %shift
+; SSE41: Found an estimated cost of 16 for instruction:   %shift
+; AVX: Found an estimated cost of 16 for instruction:   %shift
 ; AVX2: Found an estimated cost of 2 for instruction:   %shift
 ; AVX512: Found an estimated cost of 1 for instruction:   %shift
 ; XOPAVX: Found an estimated cost of 4 for instruction:   %shift