diff options
Diffstat (limited to 'llvm/test/Analysis/CostModel/X86/reduction.ll')
| -rw-r--r-- | llvm/test/Analysis/CostModel/X86/reduction.ll | 219 |
1 files changed, 219 insertions, 0 deletions
diff --git a/llvm/test/Analysis/CostModel/X86/reduction.ll b/llvm/test/Analysis/CostModel/X86/reduction.ll index eafe580b3cc..fe48435d086 100644 --- a/llvm/test/Analysis/CostModel/X86/reduction.ll +++ b/llvm/test/Analysis/CostModel/X86/reduction.ll @@ -5,6 +5,8 @@ ; RUN: opt < %s -cost-model -costmodel-reduxcost=true -mtriple=x86_64-apple-darwin -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1 ; RUN: opt < %s -cost-model -costmodel-reduxcost=true -mtriple=x86_64-apple-darwin -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2 +; RUN: opt < %s -cost-model -costmodel-reduxcost=true -mtriple=x86_64-apple-darwin -analyze -mcpu=slm | FileCheck %s --check-prefixes=SLM + ; Check that we recognize the tree starting at the extractelement as a ; reduction. ; NOTE: We're only really interested in the extractelement cost, which represents the entire reduction. @@ -42,6 +44,14 @@ define fastcc float @reduction_cost_float(<4 x float> %rdx) { ; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0 ; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; +; SLM-LABEL: 'reduction_cost_float' +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = fadd <4 x float> %rdx, %rdx.shuf +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = fadd <4 x float> %bin.rdx, %rdx.shuf7 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r +; %rdx.shuf = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef> %bin.rdx = fadd <4 x float> %rdx, %rdx.shuf %rdx.shuf7 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> @@ -82,6 +92,16 @@ define fastcc i32 @reduction_cost_int(<8 x i32> %rdx) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0 ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r ; +; SLM-LABEL: 'reduction_cost_int' +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx, %rdx.shuf +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.2 = add <8 x i32> %bin.rdx, %rdx.shuf.2 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.3 = add <8 x i32> %bin.rdx.2, %rdx.shuf.3 +; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r +; %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4 , i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef> @@ -144,6 +164,17 @@ define fastcc float @pairwise_hadd(<4 x float> %rdx, float %f1) { ; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1 ; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2 ; +; SLM-LABEL: 'pairwise_hadd' +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2 +; %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2 , i32 undef, i32 undef> %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, @@ -205,6 +236,17 @@ define fastcc float @pairwise_hadd_assoc(<4 x float> %rdx, float %f1) { ; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1 ; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2 ; +; SLM-LABEL: 'pairwise_hadd_assoc' +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.1, %rdx.shuf.0.0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2 +; %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2 , i32 undef, i32 undef> %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, @@ -262,6 +304,16 @@ define fastcc float @pairwise_hadd_skip_first(<4 x float> %rdx, float %f1) { ; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1 ; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2 ; +; SLM-LABEL: 'pairwise_hadd_skip_first' +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx.1 = fadd <4 x float> %bin.rdx.0, %rdx.shuf.1.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx.1, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r2 = fadd float %r, %f1 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r2 +; %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2 , i32 undef, i32 undef> %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, @@ -301,6 +353,12 @@ define fastcc double @no_pairwise_reduction2double(<2 x double> %rdx, double %f1 ; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x double> %bin.rdx, i32 0 ; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r ; +; SLM-LABEL: 'no_pairwise_reduction2double' +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 1, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <2 x double> %rdx, %rdx.shuf +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x double> %bin.rdx, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r +; %rdx.shuf = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 1, i32 undef> %bin.rdx = fadd <2 x double> %rdx, %rdx.shuf @@ -341,6 +399,14 @@ define fastcc float @no_pairwise_reduction4float(<4 x float> %rdx, float %f1) { ; AVX-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0 ; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; +; SLM-LABEL: 'no_pairwise_reduction4float' +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = fadd <4 x float> %rdx, %rdx.shuf +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = fadd <4 x float> %bin.rdx, %rdx.shuf7 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r +; %rdx.shuf = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef> %bin.rdx = fadd <4 x float> %rdx, %rdx.shuf %rdx.shuf7 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> @@ -391,6 +457,14 @@ define fastcc double @no_pairwise_reduction4double(<4 x double> %rdx, double %f1 ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r ; +; SLM-LABEL: 'no_pairwise_reduction4double' +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r +; %rdx.shuf = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef> %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> @@ -451,6 +525,16 @@ define fastcc float @no_pairwise_reduction8float(<8 x float> %rdx, float %f1) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0 ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; +; SLM-LABEL: 'no_pairwise_reduction8float' +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = fadd <8 x float> %rdx, %rdx.shuf3 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x float> %bin.rdx4, <8 x float> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <8 x float> %bin.rdx, %rdx.shuf7 +; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r +; %rdx.shuf3 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7,i32 undef, i32 undef, i32 undef, i32 undef> %bin.rdx4 = fadd <8 x float> %rdx, %rdx.shuf3 %rdx.shuf = shufflevector <8 x float> %bin.rdx4, <8 x float> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> @@ -475,6 +559,12 @@ define fastcc i64 @no_pairwise_reduction2i64(<2 x i64> %rdx, i64 %f1) { ; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <2 x i64> %bin.rdx, i32 0 ; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r ; +; SLM-LABEL: 'no_pairwise_reduction2i64' +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = add <2 x i64> %rdx, %rdx.shuf +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x i64> %bin.rdx, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r +; %rdx.shuf = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef> %bin.rdx = add <2 x i64> %rdx, %rdx.shuf @@ -491,6 +581,14 @@ define fastcc i32 @no_pairwise_reduction4i32(<4 x i32> %rdx, i32 %f1) { ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0 ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r ; +; SLM-LABEL: 'no_pairwise_reduction4i32' +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx, %rdx.shuf +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %bin.rdx, %rdx.shuf7 +; SLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r +; %rdx.shuf = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef> %bin.rdx = add <4 x i32> %rdx, %rdx.shuf %rdx.shuf7 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> @@ -525,6 +623,14 @@ define fastcc i64 @no_pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r ; +; SLM-LABEL: 'no_pairwise_reduction4i64' +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %bin.rdx = add <4 x i64> %rdx, %rdx.shuf +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %bin.rdx8 = add <4 x i64> %bin.rdx, %rdx.shuf7 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r +; %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef> %bin.rdx = add <4 x i64> %rdx, %rdx.shuf %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> @@ -575,6 +681,16 @@ define fastcc i16 @no_pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) { ; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <8 x i16> %bin.rdx8, i32 0 ; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %r ; +; SLM-LABEL: 'no_pairwise_reduction8i16' +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf3 = shufflevector <8 x i16> %rdx, <8 x i16> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx4 = add <8 x i16> %rdx, %rdx.shuf3 +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <8 x i16> %bin.rdx4, <8 x i16> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <8 x i16> %bin.rdx4, %rdx.shuf +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <8 x i16> %bin.rdx, <8 x i16> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <8 x i16> %bin.rdx, %rdx.shuf7 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <8 x i16> %bin.rdx8, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %r +; %rdx.shuf3 = shufflevector <8 x i16> %rdx, <8 x i16> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7,i32 undef, i32 undef, i32 undef, i32 undef> %bin.rdx4 = add <8 x i16> %rdx, %rdx.shuf3 %rdx.shuf = shufflevector <8 x i16> %bin.rdx4, <8 x i16> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> @@ -617,6 +733,16 @@ define fastcc i32 @no_pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0 ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r ; +; SLM-LABEL: 'no_pairwise_reduction8i32' +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = add <8 x i32> %rdx, %rdx.shuf3 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %bin.rdx4, %rdx.shuf +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7 +; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r +; %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7,i32 undef, i32 undef, i32 undef, i32 undef> %bin.rdx4 = add <8 x i32> %rdx, %rdx.shuf3 %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> @@ -657,6 +783,13 @@ define fastcc double @pairwise_reduction2double(<2 x double> %rdx, double %f1) { ; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x double> %bin.rdx8, i32 0 ; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r ; +; SLM-LABEL: 'pairwise_reduction2double' +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 0, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 1, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <2 x double> %rdx.shuf.1.0, %rdx.shuf.1.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x double> %bin.rdx8, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r +; %rdx.shuf.1.0 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 0, i32 undef> %rdx.shuf.1.1 = shufflevector <2 x double> %rdx, <2 x double> undef, <2 x i32> <i32 1, i32 undef> %bin.rdx8 = fadd <2 x double> %rdx.shuf.1.0, %rdx.shuf.1.1 @@ -706,6 +839,16 @@ define fastcc float @pairwise_reduction4float(<4 x float> %rdx, float %f1) { ; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0 ; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; +; SLM-LABEL: 'pairwise_reduction4float' +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x float> %bin.rdx8, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r +; %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef> %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef> %bin.rdx = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1 @@ -768,6 +911,16 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r ; +; SLM-LABEL: 'pairwise_reduction4double' +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx.shuf.0.0, %rdx.shuf.0.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r +; %rdx.shuf.0.0 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef> %rdx.shuf.0.1 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef> %bin.rdx = fadd <4 x double> %rdx.shuf.0.0, %rdx.shuf.0.1 @@ -845,6 +998,19 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0 ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; +; SLM-LABEL: 'pairwise_reduction8float' +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <8 x float> %rdx.shuf.0.0, %rdx.shuf.0.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <8 x float> %rdx.shuf.1.0, %rdx.shuf.1.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r +; %rdx.shuf.0.0 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6,i32 undef, i32 undef, i32 undef, i32 undef> %rdx.shuf.0.1 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7,i32 undef, i32 undef, i32 undef, i32 undef> %bin.rdx = fadd <8 x float> %rdx.shuf.0.0, %rdx.shuf.0.1 @@ -874,6 +1040,13 @@ define fastcc i64 @pairwise_reduction2i64(<2 x i64> %rdx, i64 %f1) { ; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <2 x i64> %bin.rdx8, i32 0 ; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r ; +; SLM-LABEL: 'pairwise_reduction2i64' +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = add <2 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %r = extractelement <2 x i64> %bin.rdx8, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r +; %rdx.shuf.1.0 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 0, i32 undef> %rdx.shuf.1.1 = shufflevector <2 x i64> %rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef> %bin.rdx8 = add <2 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1 @@ -893,6 +1066,16 @@ define fastcc i32 @pairwise_reduction4i32(<4 x i32> %rdx, i32 %f1) { ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0 ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r ; +; SLM-LABEL: 'pairwise_reduction4i32' +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <4 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <4 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %r = extractelement <4 x i32> %bin.rdx8, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r +; %rdx.shuf.0.0 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef> %rdx.shuf.0.1 = shufflevector <4 x i32> %rdx, <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef> %bin.rdx = add <4 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1 @@ -935,6 +1118,16 @@ define fastcc i64 @pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r ; +; SLM-LABEL: 'pairwise_reduction4i64' +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %bin.rdx = add <4 x i64> %rdx.shuf.0.0, %rdx.shuf.0.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %bin.rdx8 = add <4 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r +; %rdx.shuf.0.0 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef> %rdx.shuf.0.1 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef> %bin.rdx = add <4 x i64> %rdx.shuf.0.0, %rdx.shuf.0.1 @@ -999,6 +1192,19 @@ define fastcc i16 @pairwise_reduction8i16(<8 x i16> %rdx, i16 %f1) { ; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0 ; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %r ; +; SLM-LABEL: 'pairwise_reduction8i16' +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <8 x i16> %rdx, <8 x i16> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <8 x i16> %rdx, <8 x i16> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx = add <8 x i16> %rdx.shuf.0.0, %rdx.shuf.0.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i16> %bin.rdx, <8 x i16> undef, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i16> %bin.rdx, <8 x i16> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx8 = add <8 x i16> %rdx.shuf.1.0, %rdx.shuf.1.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i16> %bin.rdx8, <8 x i16> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %bin.rdx9 = add <8 x i16> %rdx.shuf.2.0, %rdx.shuf.2.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i16> %bin.rdx9, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i16 %r +; %rdx.shuf.0.0 = shufflevector <8 x i16> %rdx, <8 x i16> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6,i32 undef, i32 undef, i32 undef, i32 undef> %rdx.shuf.0.1 = shufflevector <8 x i16> %rdx, <8 x i16> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7,i32 undef, i32 undef, i32 undef, i32 undef> %bin.rdx = add <8 x i16> %rdx.shuf.0.0, %rdx.shuf.0.1 @@ -1053,6 +1259,19 @@ define fastcc i32 @pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) { ; AVX2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0 ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r ; +; SLM-LABEL: 'pairwise_reduction8i32' +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1 +; SLM-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0 +; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r +; %rdx.shuf.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6,i32 undef, i32 undef, i32 undef, i32 undef> %rdx.shuf.0.1 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7,i32 undef, i32 undef, i32 undef, i32 undef> %bin.rdx = add <8 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1 |
