maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/combine-sra.ll

317 lines
12 KiB
LLVM
Raw Normal View History

[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[X86] Add common CHECK prefix to shift combine tests llvm-svn: 324638
2018-02-09 03:23:47 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=CHECK,SSE
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-shuffle | FileCheck %s --check-prefixes=CHECK,AVX,AVX2-FAST
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; fold (sra 0, x) -> 0
define <4 x i32> @combine_vec_ashr_zero(<4 x i32> %x) {
; SSE-LABEL: combine_vec_ashr_zero:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: xorps %xmm0, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_ashr_zero:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
%1 = ashr <4 x i32> zeroinitializer, %x
ret <4 x i32> %1
}
; fold (sra -1, x) -> -1
define <4 x i32> @combine_vec_ashr_allones(<4 x i32> %x) {
; SSE-LABEL: combine_vec_ashr_allones:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: pcmpeqd %xmm0, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_ashr_allones:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; AVX-NEXT: vpcmpeqd %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
%1 = ashr <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, %x
ret <4 x i32> %1
}
; fold (sra x, c >= size(x)) -> undef
define <4 x i32> @combine_vec_ashr_outofrange0(<4 x i32> %x) {
[X86] Add common CHECK prefix to shift combine tests llvm-svn: 324638
2018-02-09 03:23:47 +08:00
; CHECK-LABEL: combine_vec_ashr_outofrange0:
; CHECK: # %bb.0:
; CHECK-NEXT: retq
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
%1 = ashr <4 x i32> %x, <i32 33, i32 33, i32 33, i32 33>
ret <4 x i32> %1
}
define <4 x i32> @combine_vec_ashr_outofrange1(<4 x i32> %x) {
[X86] Add common CHECK prefix to shift combine tests llvm-svn: 324638
2018-02-09 03:23:47 +08:00
; CHECK-LABEL: combine_vec_ashr_outofrange1:
; CHECK: # %bb.0:
; CHECK-NEXT: retq
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
%1 = ashr <4 x i32> %x, <i32 33, i32 34, i32 35, i32 36>
ret <4 x i32> %1
}
; fold (sra x, 0) -> x
define <4 x i32> @combine_vec_ashr_by_zero(<4 x i32> %x) {
[X86] Add common CHECK prefix to shift combine tests llvm-svn: 324638
2018-02-09 03:23:47 +08:00
; CHECK-LABEL: combine_vec_ashr_by_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: retq
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
%1 = ashr <4 x i32> %x, zeroinitializer
ret <4 x i32> %1
}
; fold (sra (sra x, c1), c2) -> (sra x, (add c1, c2))
define <4 x i32> @combine_vec_ashr_ashr0(<4 x i32> %x) {
; SSE-LABEL: combine_vec_ashr_ashr0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: psrad $6, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_ashr_ashr0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; AVX-NEXT: vpsrad $6, %xmm0, %xmm0
; AVX-NEXT: retq
%1 = ashr <4 x i32> %x, <i32 2, i32 2, i32 2, i32 2>
%2 = ashr <4 x i32> %1, <i32 4, i32 4, i32 4, i32 4>
ret <4 x i32> %2
}
define <4 x i32> @combine_vec_ashr_ashr1(<4 x i32> %x) {
; SSE-LABEL: combine_vec_ashr_ashr1:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[DAGCombiner] Match ISD::SRA non-uniform constant vectors patterns using predicates. Use predicate matchers introduced in D35492 to match more ISD::SRA constant folds llvm-svn: 308600
2017-07-20 18:43:05 +08:00
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: psrad $10, %xmm1
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: movdqa %xmm0, %xmm2
[DAGCombiner] Match ISD::SRA non-uniform constant vectors patterns using predicates. Use predicate matchers introduced in D35492 to match more ISD::SRA constant folds llvm-svn: 308600
2017-07-20 18:43:05 +08:00
; SSE-NEXT: psrad $6, %xmm2
; SSE-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0,1,2,3],xmm1[4,5,6,7]
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: movdqa %xmm0, %xmm1
[DAGCombiner] Match ISD::SRA non-uniform constant vectors patterns using predicates. Use predicate matchers introduced in D35492 to match more ISD::SRA constant folds llvm-svn: 308600
2017-07-20 18:43:05 +08:00
; SSE-NEXT: psrad $8, %xmm1
; SSE-NEXT: psrad $4, %xmm0
; SSE-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
; SSE-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm2[2,3],xmm0[4,5],xmm2[6,7]
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_ashr_ashr1:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; AVX-NEXT: vpsravd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%1 = ashr <4 x i32> %x, <i32 0, i32 1, i32 2, i32 3>
%2 = ashr <4 x i32> %1, <i32 4, i32 5, i32 6, i32 7>
ret <4 x i32> %2
}
define <4 x i32> @combine_vec_ashr_ashr2(<4 x i32> %x) {
; SSE-LABEL: combine_vec_ashr_ashr2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[DAGCombiner] Match ISD::SRA non-uniform constant vectors patterns using predicates. Use predicate matchers introduced in D35492 to match more ISD::SRA constant folds llvm-svn: 308600
2017-07-20 18:43:05 +08:00
; SSE-NEXT: psrad $31, %xmm0
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_ashr_ashr2:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[DAGCombiner] Match ISD::SRA non-uniform constant vectors patterns using predicates. Use predicate matchers introduced in D35492 to match more ISD::SRA constant folds llvm-svn: 308600
2017-07-20 18:43:05 +08:00
; AVX-NEXT: vpsrad $31, %xmm0, %xmm0
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; AVX-NEXT: retq
%1 = ashr <4 x i32> %x, <i32 17, i32 18, i32 19, i32 20>
%2 = ashr <4 x i32> %1, <i32 25, i32 26, i32 27, i32 28>
ret <4 x i32> %2
[X86][SSE] Add extra (sra (sra x, c1), c2) -> (sra x, (add c1, c2)) test case We should be able to handle the case where some c1+c2 elements exceed max shift and some don't by performing a clamp after the sum llvm-svn: 308724
2017-07-21 18:22:49 +08:00
}
define <4 x i32> @combine_vec_ashr_ashr3(<4 x i32> %x) {
; SSE-LABEL: combine_vec_ashr_ashr3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[X86][SSE] Add extra (sra (sra x, c1), c2) -> (sra x, (add c1, c2)) test case We should be able to handle the case where some c1+c2 elements exceed max shift and some don't by performing a clamp after the sum llvm-svn: 308724
2017-07-21 18:22:49 +08:00
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: psrad $27, %xmm1
; SSE-NEXT: movdqa %xmm0, %xmm2
; SSE-NEXT: psrad $5, %xmm2
; SSE-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0,1,2,3],xmm1[4,5,6,7]
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: psrad $31, %xmm1
; SSE-NEXT: psrad $1, %xmm0
; SSE-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
; SSE-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm2[2,3],xmm0[4,5],xmm2[6,7]
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: psrad $10, %xmm1
; SSE-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1,2,3],xmm0[4,5,6,7]
; SSE-NEXT: psrad $31, %xmm0
; SSE-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_ashr_ashr3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[X86][SSE] Add extra (sra (sra x, c1), c2) -> (sra x, (add c1, c2)) test case We should be able to handle the case where some c1+c2 elements exceed max shift and some don't by performing a clamp after the sum llvm-svn: 308724
2017-07-21 18:22:49 +08:00
; AVX-NEXT: vpsravd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: vpsravd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%1 = ashr <4 x i32> %x, <i32 1, i32 5, i32 50, i32 27>
%2 = ashr <4 x i32> %1, <i32 33, i32 10, i32 33, i32 0>
ret <4 x i32> %2
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
}
; fold (sra x, (trunc (and y, c))) -> (sra x, (and (trunc y), (trunc c))).
define <4 x i32> @combine_vec_ashr_trunc_and(<4 x i32> %x, <4 x i64> %y) {
; SSE-LABEL: combine_vec_ashr_trunc_and:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
; SSE-NEXT: andps {{.*}}(%rip), %xmm1
[X86][SSE] Reduce instruction/register usages for v4i32 vector shifts (PR37441) As suggested by Fabian on PR37441, use PSHUFLW to extend shift amount types for use with PSRAD/PSRLD to reduce register pressure. Some of this ideally would be done by combineTargetShuffle but its tricky to do as most of the shuffles are sharing inputs. Differential Revision: https://reviews.llvm.org/D46959 llvm-svn: 332524
2018-05-17 04:52:52 +08:00
; SSE-NEXT: pshuflw {{.*#+}} xmm2 = xmm1[2,3,3,3,4,5,6,7]
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: movdqa %xmm0, %xmm3
; SSE-NEXT: psrad %xmm2, %xmm3
[X86][SSE] Reduce instruction/register usages for v4i32 vector shifts (PR37441) As suggested by Fabian on PR37441, use PSHUFLW to extend shift amount types for use with PSRAD/PSRLD to reduce register pressure. Some of this ideally would be done by combineTargetShuffle but its tricky to do as most of the shuffles are sharing inputs. Differential Revision: https://reviews.llvm.org/D46959 llvm-svn: 332524
2018-05-17 04:52:52 +08:00
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm1[2,3,0,1]
; SSE-NEXT: pshuflw {{.*#+}} xmm4 = xmm2[2,3,3,3,4,5,6,7]
; SSE-NEXT: movdqa %xmm0, %xmm5
; SSE-NEXT: psrad %xmm4, %xmm5
; SSE-NEXT: pblendw {{.*#+}} xmm5 = xmm3[0,1,2,3],xmm5[4,5,6,7]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,1,1,1,4,5,6,7]
; SSE-NEXT: movdqa %xmm0, %xmm3
; SSE-NEXT: psrad %xmm1, %xmm3
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm2[0,1,1,1,4,5,6,7]
; SSE-NEXT: psrad %xmm1, %xmm0
; SSE-NEXT: pblendw {{.*#+}} xmm0 = xmm3[0,1,2,3],xmm0[4,5,6,7]
; SSE-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm5[2,3],xmm0[4,5],xmm5[6,7]
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: retq
;
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-SLOW-LABEL: combine_vec_ashr_trunc_and:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX2-SLOW-NEXT: vpsravd %xmm1, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: combine_vec_ashr_trunc_and:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX2-FAST-NEXT: vpsravd %xmm1, %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
%1 = and <4 x i64> %y, <i64 15, i64 255, i64 4095, i64 65535>
%2 = trunc <4 x i64> %1 to <4 x i32>
%3 = ashr <4 x i32> %x, %2
ret <4 x i32> %3
}
; fold (sra (trunc (srl x, c1)), c2) -> (trunc (sra x, c1 + c2))
; if c1 is equal to the number of bits the trunc removes
define <4 x i32> @combine_vec_ashr_trunc_lshr(<4 x i64> %x) {
; SSE-LABEL: combine_vec_ashr_trunc_lshr:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[X86][SSE] Allow float domain crossing if we are merging 2 or more shuffles and the root started as a float domain shuffle llvm-svn: 325349
2018-02-16 22:57:25 +08:00
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; SSE-NEXT: movaps %xmm0, %xmm2
; SSE-NEXT: movaps %xmm0, %xmm1
; SSE-NEXT: psrad $2, %xmm1
[X86][SSE] Add custom execution domain fixing for BLENDPD/BLENDPS/PBLENDD/PBLENDW (PR34873) Add support for custom execution domain fixing and implement support for BLENDPD/BLENDPS/PBLENDD/PBLENDW. Differential Revision: https://reviews.llvm.org/D42042 llvm-svn: 322524
2018-01-16 06:18:45 +08:00
; SSE-NEXT: pblendw {{.*#+}} xmm1 = xmm0[0,1,2,3],xmm1[4,5,6,7]
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; SSE-NEXT: psrad $3, %xmm0
; SSE-NEXT: psrad $1, %xmm2
; SSE-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0,1,2,3],xmm0[4,5,6,7]
; SSE-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1],xmm2[2,3],xmm1[4,5],xmm2[6,7]
; SSE-NEXT: movdqa %xmm1, %xmm0
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: retq
;
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-SLOW-LABEL: combine_vec_ashr_trunc_lshr:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpsrlq $32, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpsravd {{.*}}(%rip), %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: combine_vec_ashr_trunc_lshr:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vpsrlq $32, %ymm0, %ymm0
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm1, %ymm0
; AVX2-FAST-NEXT: vpsravd {{.*}}(%rip), %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
%1 = lshr <4 x i64> %x, <i64 32, i64 32, i64 32, i64 32>
%2 = trunc <4 x i64> %1 to <4 x i32>
%3 = ashr <4 x i32> %2, <i32 0, i32 1, i32 2, i32 3>
ret <4 x i32> %3
}
; fold (sra (trunc (sra x, c1)), c2) -> (trunc (sra x, c1 + c2))
; if c1 is equal to the number of bits the trunc removes
define <4 x i32> @combine_vec_ashr_trunc_ashr(<4 x i64> %x) {
; SSE-LABEL: combine_vec_ashr_trunc_ashr:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[SelectionDAG] Add initial implementation of TargetLowering::SimplifyDemandedVectorElts This is mainly a move of simplifyShuffleOperands from DAGCombiner::visitVECTOR_SHUFFLE to create a more general purpose TargetLowering::SimplifyDemandedVectorElts implementation. Further features can be moved/added in future patches. Differential Revision: https://reviews.llvm.org/D42896 llvm-svn: 325232
2018-02-15 20:14:15 +08:00
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; SSE-NEXT: movaps %xmm0, %xmm2
; SSE-NEXT: movaps %xmm0, %xmm1
; SSE-NEXT: psrad $2, %xmm1
[X86][SSE] Add custom execution domain fixing for BLENDPD/BLENDPS/PBLENDD/PBLENDW (PR34873) Add support for custom execution domain fixing and implement support for BLENDPD/BLENDPS/PBLENDD/PBLENDW. Differential Revision: https://reviews.llvm.org/D42042 llvm-svn: 322524
2018-01-16 06:18:45 +08:00
; SSE-NEXT: pblendw {{.*#+}} xmm1 = xmm0[0,1,2,3],xmm1[4,5,6,7]
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; SSE-NEXT: psrad $3, %xmm0
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: psrad $1, %xmm2
[x86] use a single shufps when it can save instructions This is a tiny patch with a big pile of test changes. This partially fixes PR27885: https://llvm.org/bugs/show_bug.cgi?id=27885 My motivating case looks like this: - vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2] - vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] - vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7] + vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2] And this happens several times in the diffs. For chips with domain-crossing penalties, the instruction count and size reduction should usually overcome any potential domain-crossing penalty due to using an FP op in a sequence of int ops. For chips such as recent Intel big cores and Atom, there is no domain-crossing penalty for shufps, so using shufps is a pure win. So the test case diffs all appear to be improvements except one test in vector-shuffle-combining.ll where we miss an opportunity to use a shift to generate zero elements and one test in combine-sra.ll where multiple uses prevent the expected shuffle combining. Differential Revision: https://reviews.llvm.org/D27692 llvm-svn: 289837
2016-12-16 02:03:38 +08:00
; SSE-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0,1,2,3],xmm0[4,5,6,7]
; SSE-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1],xmm2[2,3],xmm1[4,5],xmm2[6,7]
; SSE-NEXT: movdqa %xmm1, %xmm0
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: retq
;
X86 Tests: Update more isel tests with FastVariableShuffle feature Summary: Added the FastVariableShuffle feature to cases that resembled processors for which this fearure is on. For AVX2 there are processors with and w/o this fearue enable. For AVX512 only KNL does enable this feature so cases which only have +avx512f were left without the FastVariableShuffle enabled. Reviewers: RKSimon, craig.topper Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D41851 llvm-svn: 322090
2018-01-10 00:26:06 +08:00
; AVX2-SLOW-LABEL: combine_vec_ashr_trunc_ashr:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[1,3,2,3,5,7,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpsravd {{.*}}(%rip), %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: combine_vec_ashr_trunc_ashr:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm1 = [1,3,5,7,5,7,6,7]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm1, %ymm0
; AVX2-FAST-NEXT: vpsravd {{.*}}(%rip), %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
%1 = ashr <4 x i64> %x, <i64 32, i64 32, i64 32, i64 32>
%2 = trunc <4 x i64> %1 to <4 x i32>
%3 = ashr <4 x i32> %2, <i32 0, i32 1, i32 2, i32 3>
ret <4 x i32> %3
}
; If the sign bit is known to be zero, switch this to a SRL.
define <4 x i32> @combine_vec_ashr_positive(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: combine_vec_ashr_positive:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
[X86][SSE] Reduce instruction/register usages for v4i32 vector shifts (PR37441) As suggested by Fabian on PR37441, use PSHUFLW to extend shift amount types for use with PSRAD/PSRLD to reduce register pressure. Some of this ideally would be done by combineTargetShuffle but its tricky to do as most of the shuffles are sharing inputs. Differential Revision: https://reviews.llvm.org/D46959 llvm-svn: 332524
2018-05-17 04:52:52 +08:00
; SSE-NEXT: pshuflw {{.*#+}} xmm2 = xmm1[2,3,3,3,4,5,6,7]
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: movdqa %xmm0, %xmm3
; SSE-NEXT: psrld %xmm2, %xmm3
[X86][SSE] Reduce instruction/register usages for v4i32 vector shifts (PR37441) As suggested by Fabian on PR37441, use PSHUFLW to extend shift amount types for use with PSRAD/PSRLD to reduce register pressure. Some of this ideally would be done by combineTargetShuffle but its tricky to do as most of the shuffles are sharing inputs. Differential Revision: https://reviews.llvm.org/D46959 llvm-svn: 332524
2018-05-17 04:52:52 +08:00
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm1[2,3,0,1]
; SSE-NEXT: pshuflw {{.*#+}} xmm4 = xmm2[2,3,3,3,4,5,6,7]
; SSE-NEXT: movdqa %xmm0, %xmm5
; SSE-NEXT: psrld %xmm4, %xmm5
; SSE-NEXT: pblendw {{.*#+}} xmm5 = xmm3[0,1,2,3],xmm5[4,5,6,7]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,1,1,1,4,5,6,7]
; SSE-NEXT: movdqa %xmm0, %xmm3
; SSE-NEXT: psrld %xmm1, %xmm3
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm2[0,1,1,1,4,5,6,7]
; SSE-NEXT: psrld %xmm1, %xmm0
; SSE-NEXT: pblendw {{.*#+}} xmm0 = xmm3[0,1,2,3],xmm0[4,5,6,7]
; SSE-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm5[2,3],xmm0[4,5],xmm5[6,7]
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_ashr_positive:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[X86][SSE] Added vector ashr combine tests This doesn't cover all combines in DAGCombiner::visitSRA yet, but identifies several cases where we fail to combine vectors (or non-splatted) vectors llvm-svn: 284498
2016-10-19 01:31:07 +08:00
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: vpsrlvd %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%1 = and <4 x i32> %x, <i32 15, i32 255, i32 4095, i32 65535>
%2 = ashr <4 x i32> %1, %y
ret <4 x i32> %2
}
[x86] add test for missing vector SRA combine via computeKnownBits llvm-svn: 284896
2016-10-22 07:02:31 +08:00
define <4 x i32> @combine_vec_ashr_positive_splat(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: combine_vec_ashr_positive_splat:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE: # %bb.0:
[DAG] enhance computeKnownBits to handle SRL/SRA with vector splat constant llvm-svn: 284953
2016-10-24 07:13:31 +08:00
; SSE-NEXT: xorps %xmm0, %xmm0
[x86] add test for missing vector SRA combine via computeKnownBits llvm-svn: 284896
2016-10-22 07:02:31 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_ashr_positive_splat:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[DAG] enhance computeKnownBits to handle SRL/SRA with vector splat constant llvm-svn: 284953
2016-10-24 07:13:31 +08:00
; AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
[x86] add test for missing vector SRA combine via computeKnownBits llvm-svn: 284896
2016-10-22 07:02:31 +08:00
; AVX-NEXT: retq
%1 = and <4 x i32> %x, <i32 1023, i32 1023, i32 1023, i32 1023>
%2 = ashr <4 x i32> %1, <i32 10, i32 10, i32 10, i32 10>
ret <4 x i32> %2
}