maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Analysis/CostModel/X86/reduce-and.ll

371 lines
37 KiB
LLVM
Raw Normal View History

[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt < %s -cost-model -costmodel-reduxcost=true -mtriple=x86_64-apple-darwin -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
; RUN: opt < %s -cost-model -costmodel-reduxcost=true -mtriple=x86_64-apple-darwin -analyze -mattr=+ssse3 | FileCheck %s --check-prefixes=CHECK,SSE,SSSE3
; RUN: opt < %s -cost-model -costmodel-reduxcost=true -mtriple=x86_64-apple-darwin -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
; 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 -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
; RUN: opt < %s -cost-model -costmodel-reduxcost=true -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
; RUN: opt < %s -cost-model -costmodel-reduxcost=true -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512DQ
define i32 @reduce_i64(i32 %arg) {
; SSE-LABEL: 'reduce_i64'
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; AVX1-LABEL: 'reduce_i64'
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX2-LABEL: 'reduce_i64'
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
;
; AVX512-LABEL: 'reduce_i64'
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX512-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V1 = call i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64> undef)
%V2 = call i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64> undef)
%V4 = call i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64> undef)
%V8 = call i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64> undef)
%V16 = call i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64> undef)
ret i32 undef
}
define i32 @reduce_i32(i32 %arg) {
; SSE-LABEL: 'reduce_i32'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; AVX1-LABEL: 'reduce_i32'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX2-LABEL: 'reduce_i32'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
;
; AVX512-LABEL: 'reduce_i32'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX512-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V2 = call i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32> undef)
%V4 = call i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32> undef)
%V8 = call i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32> undef)
%V16 = call i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32> undef)
%V32 = call i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32> undef)
ret i32 undef
}
define i32 @reduce_i16(i32 %arg) {
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; SSE2-LABEL: 'reduce_i16'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SSSE3-LABEL: 'reduce_i16'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
;
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; SSE42-LABEL: 'reduce_i16'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX1-LABEL: 'reduce_i16'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX2-LABEL: 'reduce_i16'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
;
; AVX512F-LABEL: 'reduce_i16'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512BW-LABEL: 'reduce_i16'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512DQ-LABEL: 'reduce_i16'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V4 = call i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16> undef)
%V8 = call i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16> undef)
%V16 = call i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16> undef)
%V32 = call i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16> undef)
%V64 = call i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16> undef)
ret i32 undef
}
define i32 @reduce_i8(i32 %arg) {
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; SSE2-LABEL: 'reduce_i8'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
;
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; SSSE3-LABEL: 'reduce_i8'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SSE42-LABEL: 'reduce_i8'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX1-LABEL: 'reduce_i8'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX1-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 83 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX2-LABEL: 'reduce_i8'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
;
; AVX512F-LABEL: 'reduce_i8'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX512F-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512BW-LABEL: 'reduce_i8'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 118 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 120 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512DQ-LABEL: 'reduce_i8'
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V8 = call i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8> undef)
%V16 = call i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8> undef)
%V32 = call i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8> undef)
%V64 = call i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8> undef)
%V128 = call i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8> undef)
ret i32 undef
}
define i32 @reduce_i1(i32 %arg) {
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; SSE2-LABEL: 'reduce_i1'
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 66 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
; SSE2-NEXT: Cost Model: Found an estimated cost of 74 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SSSE3-LABEL: 'reduce_i1'
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
; SSSE3-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SSE42-LABEL: 'reduce_i1'
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
; SSE42-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX1-LABEL: 'reduce_i1'
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 77 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 79 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
; AVX1-NEXT: Cost Model: Found an estimated cost of 83 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
;
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; AVX2-LABEL: 'reduce_i1'
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 57 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
; AVX2-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
[TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368) Correct costings of SK_ExtractSubvector requires the SubTy argument to indicate the type/size of the extracted subvector. Unlike the rest of the shuffle kinds this means that the main Ty argument represents the source vector type not the destination! I've done my best to fix a number of vectorizer uses: SLP - the reduction epilogue costs should be using a SK_PermuteSingleSrc shuffle as these all occur at the hardware vector width - we're not extracting (illegal) subvector types. This is causing the cost model diffs as SK_ExtractSubvector costs are poorly handled and tend to just return 1 at the moment. LV - I'm not clear on what the SK_ExtractSubvector should represents for recurrences - I've used a <1 x ?> subvector extraction as that seems to match the VF delta. Differential Revision: https://reviews.llvm.org/D53573 llvm-svn: 345617
2018-10-31 02:10:02 +08:00
; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
;
; AVX512F-LABEL: 'reduce_i1'
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX512F-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 148 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 150 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 154 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
; AVX512F-NEXT: Cost Model: Found an estimated cost of 162 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512BW-LABEL: 'reduce_i1'
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 148 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 357 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 838 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 840 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
; AVX512BW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512DQ-LABEL: 'reduce_i1'
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
Revert "[TTI] Reduction costs only need to include a single extract element cost" This reverts commit r346970. It was causing PR39774, a crash in slp-vectorizer on a rather simple loop with just a bunch of 'and's in the body. llvm-svn: 347541
2018-11-26 18:17:27 +08:00
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 59 for instruction: %V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 148 for instruction: %V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 150 for instruction: %V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 154 for instruction: %V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 162 for instruction: %V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
[CostModel][X86] Add integer vector reduction cost tests llvm-svn: 344846
2018-10-20 22:29:59 +08:00
; AVX512DQ-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V1 = call i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1> undef)
%V2 = call i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1> undef)
%V4 = call i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1> undef)
%V8 = call i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1> undef)
%V16 = call i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1> undef)
%V32 = call i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1> undef)
%V64 = call i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1> undef)
%V128 = call i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1> undef)
ret i32 undef
}
declare i64 @llvm.experimental.vector.reduce.and.i64.v1i64(<1 x i64>)
declare i64 @llvm.experimental.vector.reduce.and.i64.v2i64(<2 x i64>)
declare i64 @llvm.experimental.vector.reduce.and.i64.v4i64(<4 x i64>)
declare i64 @llvm.experimental.vector.reduce.and.i64.v8i64(<8 x i64>)
declare i64 @llvm.experimental.vector.reduce.and.i64.v16i64(<16 x i64>)
declare i32 @llvm.experimental.vector.reduce.and.i32.v2i32(<2 x i32>)
declare i32 @llvm.experimental.vector.reduce.and.i32.v4i32(<4 x i32>)
declare i32 @llvm.experimental.vector.reduce.and.i32.v8i32(<8 x i32>)
declare i32 @llvm.experimental.vector.reduce.and.i32.v16i32(<16 x i32>)
declare i32 @llvm.experimental.vector.reduce.and.i32.v32i32(<32 x i32>)
declare i16 @llvm.experimental.vector.reduce.and.i16.v4i16(<4 x i16>)
declare i16 @llvm.experimental.vector.reduce.and.i16.v8i16(<8 x i16>)
declare i16 @llvm.experimental.vector.reduce.and.i16.v16i16(<16 x i16>)
declare i16 @llvm.experimental.vector.reduce.and.i16.v32i16(<32 x i16>)
declare i16 @llvm.experimental.vector.reduce.and.i16.v64i16(<64 x i16>)
declare i8 @llvm.experimental.vector.reduce.and.i8.v8i8(<8 x i8>)
declare i8 @llvm.experimental.vector.reduce.and.i8.v16i8(<16 x i8>)
declare i8 @llvm.experimental.vector.reduce.and.i8.v32i8(<32 x i8>)
declare i8 @llvm.experimental.vector.reduce.and.i8.v64i8(<64 x i8>)
declare i8 @llvm.experimental.vector.reduce.and.i8.v128i8(<128 x i8>)
declare i1 @llvm.experimental.vector.reduce.and.i1.v1i1(<1 x i1>)
declare i1 @llvm.experimental.vector.reduce.and.i1.v2i1(<2 x i1>)
declare i1 @llvm.experimental.vector.reduce.and.i1.v4i1(<4 x i1>)
declare i1 @llvm.experimental.vector.reduce.and.i1.v8i1(<8 x i1>)
declare i1 @llvm.experimental.vector.reduce.and.i1.v16i1(<16 x i1>)
declare i1 @llvm.experimental.vector.reduce.and.i1.v32i1(<32 x i1>)
declare i1 @llvm.experimental.vector.reduce.and.i1.v64i1(<64 x i1>)
declare i1 @llvm.experimental.vector.reduce.and.i1.v128i1(<128 x i1>)