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/buildvec-insertvec.ll

574 lines
26 KiB
LLVM
Raw Normal View History

Make utils/update_llc_test_checks.py note that the assertions are autogenerated. Also update existing test cases which appear to be generated by it and weren't modified (other than addition of the header) by rerunning it. llvm-svn: 253917
2015-11-24 05:33:58 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=CHECK --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=CHECK --check-prefix=SSE41
Lower BUILD_VECTOR to SHUFFLE + INSERT_VECTOR_ELT for X86 - If INSERT_VECTOR_ELT is supported (above SSE2, either by custom sequence of legal insn), transform BUILD_VECTOR into SHUFFLE + INSERT_VECTOR_ELT if most of elements could be built from SHUFFLE with few (so far 1) elements being inserted. llvm-svn: 166288
2012-10-20 01:15:18 +08:00
define void @foo(<3 x float> %in, <4 x i8>* nocapture %out) nounwind {
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-LABEL: foo:
[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
; SSE2: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: cvttps2dq %xmm0, %xmm0
; SSE2-NEXT: movl $255, %eax
; SSE2-NEXT: movd %eax, %xmm1
; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[2,0]
; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,0]
; SSE2-NEXT: andps {{.*}}(%rip), %xmm0
; SSE2-NEXT: packuswb %xmm0, %xmm0
; SSE2-NEXT: packuswb %xmm0, %xmm0
; SSE2-NEXT: movd %xmm0, (%rdi)
; SSE2-NEXT: retq
;
; SSE41-LABEL: foo:
[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
; SSE41: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE41-NEXT: cvttps2dq %xmm0, %xmm0
; SSE41-NEXT: movl $255, %eax
; SSE41-NEXT: pinsrd $3, %eax, %xmm0
; SSE41-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u]
; SSE41-NEXT: movd %xmm0, (%rdi)
; SSE41-NEXT: retq
Lower BUILD_VECTOR to SHUFFLE + INSERT_VECTOR_ELT for X86 - If INSERT_VECTOR_ELT is supported (above SSE2, either by custom sequence of legal insn), transform BUILD_VECTOR into SHUFFLE + INSERT_VECTOR_ELT if most of elements could be built from SHUFFLE with few (so far 1) elements being inserted. llvm-svn: 166288
2012-10-20 01:15:18 +08:00
%t0 = fptoui <3 x float> %in to <3 x i8>
%t1 = shufflevector <3 x i8> %t0, <3 x i8> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 undef>
%t2 = insertelement <4 x i8> %t1, i8 -1, i32 3
store <4 x i8> %t2, <4 x i8>* %out, align 4
ret void
Simplify code; NFC. Also, moved test cases from CodeGen/X86/fold-buildvector-bug.ll into CodeGen/X86/buildvec-insertvec.ll and regenerated CHECK lines using update_llc_test_checks.py. llvm-svn: 239142
2015-06-05 18:29:55 +08:00
}
; Verify that the DAGCombiner doesn't wrongly fold a build_vector into a
; blend with a zero vector if the build_vector contains negative zero.
define <4 x float> @test_negative_zero_1(<4 x float> %A) {
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-LABEL: test_negative_zero_1:
[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
; SSE2: # %bb.0: # %entry
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movaps %xmm0, %xmm1
[X86] Prefer unpckhpd over movhlps in isel for fake unary cases In r337348, I changed lowering to prefer X86ISD::UNPCKL/UNPCKH opcodes over MOVLHPS/MOVHLPS for v2f64 {0,0} and {1,1} shuffles when we have SSE2. This enabled the removal of a bunch of weirdly bitcasted isel patterns in r337349. To avoid changing the tests I placed a gross hack in isel to still emit movhlps instructions for fake unary unpckh nodes. A similar hack was not needed for unpckl and movlhps because we do execution domain switching for those. But unpckh and movhlps have swapped operand order. This patch removes the hack. This is a code size increase since unpckhpd requires a 0x66 prefix and movhlps does not. But if that's a big concern we should be using movhlps for all unpckhpd opcodes and let commuteInstruction turnit into unpckhpd when its an advantage. Differential Revision: https://reviews.llvm.org/D49499 llvm-svn: 341973
2018-09-12 01:57:27 +08:00
; SSE2-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: xorps %xmm2, %xmm2
; SSE2-NEXT: movss {{.*#+}} xmm2 = xmm1[0],xmm2[1,2,3]
[X86] Redefine MOVSS/MOVSD instructions to take VR128 regclass as input instead of FR32/FR64 This patch redefines the MOVSS/MOVSD instructions to take VR128 as its second input. This allows the MOVSS/SD->BLEND commute to work without requiring a COPY to be inserted. This should fix PR33079 Overall this looks to be an improvement in the generated code. I haven't checked the EXPENSIVE_CHECKS build but I'll do that and update with results. Differential Revision: https://reviews.llvm.org/D38449 llvm-svn: 314914
2017-10-05 01:20:12 +08:00
; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
[X86] Teach the execution domain fixing tables to use movlhps inplace of unpcklpd for the packed single domain. MOVLHPS has a smaller encoding than UNPCKLPD in the legacy encodings. With VEX and EVEX encodings it doesn't matter. llvm-svn: 313509
2017-09-18 12:40:58 +08:00
; SSE2-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: retq
;
; SSE41-LABEL: test_negative_zero_1:
[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
; SSE41: # %bb.0: # %entry
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2],zero
; SSE41-NEXT: retq
Simplify code; NFC. Also, moved test cases from CodeGen/X86/fold-buildvector-bug.ll into CodeGen/X86/buildvec-insertvec.ll and regenerated CHECK lines using update_llc_test_checks.py. llvm-svn: 239142
2015-06-05 18:29:55 +08:00
entry:
%0 = extractelement <4 x float> %A, i32 0
%1 = insertelement <4 x float> undef, float %0, i32 0
%2 = insertelement <4 x float> %1, float -0.0, i32 1
%3 = extractelement <4 x float> %A, i32 2
%4 = insertelement <4 x float> %2, float %3, i32 2
%5 = insertelement <4 x float> %4, float 0.0, i32 3
ret <4 x float> %5
}
[x86] use an insert op to put one variable element into a constant of vectors Instead of loading (a potential ton of) scalar constants, load those as a vector and then insert into it. Differential Revision: https://reviews.llvm.org/D38756 llvm-svn: 316685
2017-10-27 02:27:55 +08:00
; FIXME: This could be 'movhpd {{.*#+}} xmm0 = xmm0[0],mem[0]'.
Simplify code; NFC. Also, moved test cases from CodeGen/X86/fold-buildvector-bug.ll into CodeGen/X86/buildvec-insertvec.ll and regenerated CHECK lines using update_llc_test_checks.py. llvm-svn: 239142
2015-06-05 18:29:55 +08:00
define <2 x double> @test_negative_zero_2(<2 x double> %A) {
[x86] use an insert op to put one variable element into a constant of vectors Instead of loading (a potential ton of) scalar constants, load those as a vector and then insert into it. Differential Revision: https://reviews.llvm.org/D38756 llvm-svn: 316685
2017-10-27 02:27:55 +08:00
; SSE2-LABEL: test_negative_zero_2:
[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
; SSE2: # %bb.0: # %entry
[x86] use an insert op to put one variable element into a constant of vectors Instead of loading (a potential ton of) scalar constants, load those as a vector and then insert into it. Differential Revision: https://reviews.llvm.org/D38756 llvm-svn: 316685
2017-10-27 02:27:55 +08:00
; SSE2-NEXT: movapd {{.*#+}} xmm1 = <u,-0>
; SSE2-NEXT: movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
; SSE2-NEXT: movapd %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: test_negative_zero_2:
[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
; SSE41: # %bb.0: # %entry
[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
; SSE41-NEXT: blendps {{.*#+}} xmm0 = xmm0[0,1],mem[2,3]
[x86] use an insert op to put one variable element into a constant of vectors Instead of loading (a potential ton of) scalar constants, load those as a vector and then insert into it. Differential Revision: https://reviews.llvm.org/D38756 llvm-svn: 316685
2017-10-27 02:27:55 +08:00
; SSE41-NEXT: retq
Simplify code; NFC. Also, moved test cases from CodeGen/X86/fold-buildvector-bug.ll into CodeGen/X86/buildvec-insertvec.ll and regenerated CHECK lines using update_llc_test_checks.py. llvm-svn: 239142
2015-06-05 18:29:55 +08:00
entry:
%0 = extractelement <2 x double> %A, i32 0
%1 = insertelement <2 x double> undef, double %0, i32 0
%2 = insertelement <2 x double> %1, double -0.0, i32 1
ret <2 x double> %2
Lower BUILD_VECTOR to SHUFFLE + INSERT_VECTOR_ELT for X86 - If INSERT_VECTOR_ELT is supported (above SSE2, either by custom sequence of legal insn), transform BUILD_VECTOR into SHUFFLE + INSERT_VECTOR_ELT if most of elements could be built from SHUFFLE with few (so far 1) elements being inserted. llvm-svn: 166288
2012-10-20 01:15:18 +08:00
}
[X86][SSE] Added PR27854 tests llvm-svn: 276571
2016-07-25 00:39:50 +08:00
define <4 x float> @test_buildvector_v4f32_register(float %f0, float %f1, float %f2, float %f3) {
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-LABEL: test_buildvector_v4f32_register:
[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
; SSE2: # %bb.0:
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
[X86] Teach the execution domain fixing tables to use movlhps inplace of unpcklpd for the packed single domain. MOVLHPS has a smaller encoding than UNPCKLPD in the legacy encodings. With VEX and EVEX encodings it doesn't matter. llvm-svn: 313509
2017-09-18 12:40:58 +08:00
; SSE2-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: retq
;
; SSE41-LABEL: test_buildvector_v4f32_register:
[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
; SSE41: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[2,3]
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1],xmm2[0],xmm0[3]
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm3[0]
; SSE41-NEXT: retq
[X86][SSE] Added PR27854 tests llvm-svn: 276571
2016-07-25 00:39:50 +08:00
%ins0 = insertelement <4 x float> undef, float %f0, i32 0
%ins1 = insertelement <4 x float> %ins0, float %f1, i32 1
%ins2 = insertelement <4 x float> %ins1, float %f2, i32 2
%ins3 = insertelement <4 x float> %ins2, float %f3, i32 3
ret <4 x float> %ins3
}
define <4 x float> @test_buildvector_v4f32_load(float* %p0, float* %p1, float* %p2, float* %p3) {
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-LABEL: test_buildvector_v4f32_load:
[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
; SSE2: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
[X86] Remove some composite MOVSS/MOVSD isel patterns. These patterns looked for a MOVSS/SD followed by a scalar_to_vector. Or a scalar_to_vector followed by a load. In both cases we emitted a MOVSS/SD for the MOVSS/SD part, a REG_CLASS for the scalar_to_vector, and a MOVSS/SD for the load. But we have patterns that do each of those 3 things individually so there's no reason to build large patterns. Most of the test changes are just reorderings. The one test that had a meaningful change is pr30430.ll and it appears to be a regression. But its doing -O0 so I think it missed a lot of opportunities and was just getting lucky before. llvm-svn: 336762
2018-07-11 12:51:40 +08:00
; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE2-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSE2-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: retq
;
; SSE41-LABEL: test_buildvector_v4f32_load:
[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
; SSE41: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE41-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; SSE41-NEXT: retq
[X86][SSE] Added PR27854 tests llvm-svn: 276571
2016-07-25 00:39:50 +08:00
%f0 = load float, float* %p0, align 4
%f1 = load float, float* %p1, align 4
%f2 = load float, float* %p2, align 4
%f3 = load float, float* %p3, align 4
%ins0 = insertelement <4 x float> undef, float %f0, i32 0
%ins1 = insertelement <4 x float> %ins0, float %f1, i32 1
%ins2 = insertelement <4 x float> %ins1, float %f2, i32 2
%ins3 = insertelement <4 x float> %ins2, float %f3, i32 3
ret <4 x float> %ins3
}
define <4 x float> @test_buildvector_v4f32_partial_load(float %f0, float %f1, float %f2, float* %p3) {
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-LABEL: test_buildvector_v4f32_partial_load:
[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
; SSE2: # %bb.0:
[X86] Remove some composite MOVSS/MOVSD isel patterns. These patterns looked for a MOVSS/SD followed by a scalar_to_vector. Or a scalar_to_vector followed by a load. In both cases we emitted a MOVSS/SD for the MOVSS/SD part, a REG_CLASS for the scalar_to_vector, and a MOVSS/SD for the load. But we have patterns that do each of those 3 things individually so there's no reason to build large patterns. Most of the test changes are just reorderings. The one test that had a meaningful change is pr30430.ll and it appears to be a regression. But its doing -O0 so I think it missed a lot of opportunities and was just getting lucky before. llvm-svn: 336762
2018-07-11 12:51:40 +08:00
; SSE2-NEXT: movss {{.*#+}} xmm3 = mem[0],zero,zero,zero
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
[X86] Remove some composite MOVSS/MOVSD isel patterns. These patterns looked for a MOVSS/SD followed by a scalar_to_vector. Or a scalar_to_vector followed by a load. In both cases we emitted a MOVSS/SD for the MOVSS/SD part, a REG_CLASS for the scalar_to_vector, and a MOVSS/SD for the load. But we have patterns that do each of those 3 things individually so there's no reason to build large patterns. Most of the test changes are just reorderings. The one test that had a meaningful change is pr30430.ll and it appears to be a regression. But its doing -O0 so I think it missed a lot of opportunities and was just getting lucky before. llvm-svn: 336762
2018-07-11 12:51:40 +08:00
; SSE2-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
[X86] Teach the execution domain fixing tables to use movlhps inplace of unpcklpd for the packed single domain. MOVLHPS has a smaller encoding than UNPCKLPD in the legacy encodings. With VEX and EVEX encodings it doesn't matter. llvm-svn: 313509
2017-09-18 12:40:58 +08:00
; SSE2-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: retq
;
; SSE41-LABEL: test_buildvector_v4f32_partial_load:
[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
; SSE41: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[2,3]
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1],xmm2[0],xmm0[3]
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; SSE41-NEXT: retq
[X86][SSE] Added PR27854 tests llvm-svn: 276571
2016-07-25 00:39:50 +08:00
%f3 = load float, float* %p3, align 4
%ins0 = insertelement <4 x float> undef, float %f0, i32 0
%ins1 = insertelement <4 x float> %ins0, float %f1, i32 1
%ins2 = insertelement <4 x float> %ins1, float %f2, i32 2
%ins3 = insertelement <4 x float> %ins2, float %f3, i32 3
ret <4 x float> %ins3
}
[X86][SSE] Add additional v4i32/v8i16/v16i8 build vector insertion tests With particular interest in cases where we don't make use of implicit zeroing or fail to break register dependencies llvm-svn: 294363
2017-02-08 06:03:37 +08:00
define <4 x i32> @test_buildvector_v4i32_register(i32 %a0, i32 %a1, i32 %a2, i32 %a3) {
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-LABEL: test_buildvector_v4i32_register:
[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
; SSE2: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movd %ecx, %xmm0
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: movd %edx, %xmm1
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: movd %esi, %xmm2
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movd %edi, %xmm0
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: retq
;
; SSE41-LABEL: test_buildvector_v4i32_register:
[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
; SSE41: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE41-NEXT: movd %edi, %xmm0
; SSE41-NEXT: pinsrd $1, %esi, %xmm0
; SSE41-NEXT: pinsrd $2, %edx, %xmm0
; SSE41-NEXT: pinsrd $3, %ecx, %xmm0
; SSE41-NEXT: retq
[X86][SSE] Add additional v4i32/v8i16/v16i8 build vector insertion tests With particular interest in cases where we don't make use of implicit zeroing or fail to break register dependencies llvm-svn: 294363
2017-02-08 06:03:37 +08:00
%ins0 = insertelement <4 x i32> undef, i32 %a0, i32 0
%ins1 = insertelement <4 x i32> %ins0, i32 %a1, i32 1
%ins2 = insertelement <4 x i32> %ins1, i32 %a2, i32 2
%ins3 = insertelement <4 x i32> %ins2, i32 %a3, i32 3
ret <4 x i32> %ins3
}
define <4 x i32> @test_buildvector_v4i32_partial(i32 %a0, i32 %a3) {
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-LABEL: test_buildvector_v4i32_partial:
[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
; SSE2: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movd %edi, %xmm0
; SSE2-NEXT: movd %esi, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,0,1,1]
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: retq
;
; SSE41-LABEL: test_buildvector_v4i32_partial:
[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
; SSE41: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE41-NEXT: movd %edi, %xmm0
; SSE41-NEXT: pinsrd $3, %esi, %xmm0
; SSE41-NEXT: retq
[X86][SSE] Add additional v4i32/v8i16/v16i8 build vector insertion tests With particular interest in cases where we don't make use of implicit zeroing or fail to break register dependencies llvm-svn: 294363
2017-02-08 06:03:37 +08:00
%ins0 = insertelement <4 x i32> undef, i32 %a0, i32 0
%ins1 = insertelement <4 x i32> %ins0, i32 undef, i32 1
%ins2 = insertelement <4 x i32> %ins1, i32 undef, i32 2
%ins3 = insertelement <4 x i32> %ins2, i32 %a3, i32 3
ret <4 x i32> %ins3
}
define <4 x i32> @test_buildvector_v4i32_register_zero(i32 %a0, i32 %a2, i32 %a3) {
; CHECK-LABEL: test_buildvector_v4i32_register_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
; CHECK: # %bb.0:
[X86][SSE] Add additional v4i32/v8i16/v16i8 build vector insertion tests With particular interest in cases where we don't make use of implicit zeroing or fail to break register dependencies llvm-svn: 294363
2017-02-08 06:03:37 +08:00
; CHECK-NEXT: movd %edx, %xmm0
; CHECK-NEXT: movd %esi, %xmm1
; CHECK-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT: movd %edi, %xmm0
; CHECK-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; CHECK-NEXT: retq
%ins0 = insertelement <4 x i32> undef, i32 %a0, i32 0
%ins1 = insertelement <4 x i32> %ins0, i32 0, i32 1
%ins2 = insertelement <4 x i32> %ins1, i32 %a2, i32 2
%ins3 = insertelement <4 x i32> %ins2, i32 %a3, i32 3
ret <4 x i32> %ins3
}
define <4 x i32> @test_buildvector_v4i32_register_zero_2(i32 %a1, i32 %a2, i32 %a3) {
; CHECK-LABEL: test_buildvector_v4i32_register_zero_2:
[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
; CHECK: # %bb.0:
[X86][SSE] Add additional v4i32/v8i16/v16i8 build vector insertion tests With particular interest in cases where we don't make use of implicit zeroing or fail to break register dependencies llvm-svn: 294363
2017-02-08 06:03:37 +08:00
; CHECK-NEXT: movd %edx, %xmm0
; CHECK-NEXT: movd %esi, %xmm1
; CHECK-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT: movd %edi, %xmm0
; CHECK-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,0],xmm1[0,1]
; CHECK-NEXT: retq
%ins0 = insertelement <4 x i32> undef, i32 0, i32 0
%ins1 = insertelement <4 x i32> %ins0, i32 %a1, i32 1
%ins2 = insertelement <4 x i32> %ins1, i32 %a2, i32 2
%ins3 = insertelement <4 x i32> %ins2, i32 %a3, i32 3
ret <4 x i32> %ins3
}
define <8 x i16> @test_buildvector_v8i16_register(i16 %a0, i16 %a1, i16 %a2, i16 %a3, i16 %a4, i16 %a5, i16 %a6, i16 %a7) {
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-LABEL: test_buildvector_v8i16_register:
[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
; SSE2: # %bb.0:
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSE2-NEXT: movd %r9d, %xmm0
; SSE2-NEXT: movd %r8d, %xmm2
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSE2-NEXT: movd %ecx, %xmm0
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movd %edx, %xmm1
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: movd %esi, %xmm3
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movd %edi, %xmm0
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3]
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: retq
;
; SSE41-LABEL: test_buildvector_v8i16_register:
[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
; SSE41: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE41-NEXT: movd %edi, %xmm0
; SSE41-NEXT: pinsrw $1, %esi, %xmm0
; SSE41-NEXT: pinsrw $2, %edx, %xmm0
; SSE41-NEXT: pinsrw $3, %ecx, %xmm0
; SSE41-NEXT: pinsrw $4, %r8d, %xmm0
; SSE41-NEXT: pinsrw $5, %r9d, %xmm0
; SSE41-NEXT: pinsrw $6, {{[0-9]+}}(%rsp), %xmm0
; SSE41-NEXT: pinsrw $7, {{[0-9]+}}(%rsp), %xmm0
; SSE41-NEXT: retq
[X86][SSE] Add additional v4i32/v8i16/v16i8 build vector insertion tests With particular interest in cases where we don't make use of implicit zeroing or fail to break register dependencies llvm-svn: 294363
2017-02-08 06:03:37 +08:00
%ins0 = insertelement <8 x i16> undef, i16 %a0, i32 0
%ins1 = insertelement <8 x i16> %ins0, i16 %a1, i32 1
%ins2 = insertelement <8 x i16> %ins1, i16 %a2, i32 2
%ins3 = insertelement <8 x i16> %ins2, i16 %a3, i32 3
%ins4 = insertelement <8 x i16> %ins3, i16 %a4, i32 4
%ins5 = insertelement <8 x i16> %ins4, i16 %a5, i32 5
%ins6 = insertelement <8 x i16> %ins5, i16 %a6, i32 6
%ins7 = insertelement <8 x i16> %ins6, i16 %a7, i32 7
ret <8 x i16> %ins7
}
define <8 x i16> @test_buildvector_v8i16_partial(i16 %a1, i16 %a3, i16 %a4, i16 %a5) {
; CHECK-LABEL: test_buildvector_v8i16_partial:
[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
; CHECK: # %bb.0:
[X86][SSE] Attempt to break register dependencies during lowerBuildVector LowerBuildVectorv16i8/LowerBuildVectorv8i16 insert values into a UNDEF vector if the build vector doesn't contain any zero elements, resulting in register dependencies with a previous use of the register. This patch attempts to break the register dependency by either always zeroing the vector before hand or (if we're inserting to the 0'th element) by using VZEXT_MOVL(SCALAR_TO_VECTOR(i32 AEXT(Elt))) which lowers to (V)MOVD and performs a similar function. Additionally (V)MOVD is a shorter instruction than PINSRB/PINSRW. We already do something similar for SSE41 PINSRD. On pre-SSE41 LowerBuildVectorv16i8 we go a little further and use VZEXT_MOVL(SCALAR_TO_VECTOR(i32 ZEXT(Elt))) if the build vector contains zeros to avoid the vector zeroing at the cost of a scalar zero extension, which can probably be brought over to the other cases in a future patch in some cases (load folding etc.) Differential Revision: https://reviews.llvm.org/D29720 llvm-svn: 294581
2017-02-09 19:50:19 +08:00
; CHECK-NEXT: pxor %xmm0, %xmm0
[X86][SSE] Add additional v4i32/v8i16/v16i8 build vector insertion tests With particular interest in cases where we don't make use of implicit zeroing or fail to break register dependencies llvm-svn: 294363
2017-02-08 06:03:37 +08:00
; CHECK-NEXT: pinsrw $1, %edi, %xmm0
; CHECK-NEXT: pinsrw $3, %esi, %xmm0
; CHECK-NEXT: pinsrw $4, %edx, %xmm0
; CHECK-NEXT: pinsrw $5, %ecx, %xmm0
; CHECK-NEXT: retq
%ins0 = insertelement <8 x i16> undef, i16 undef, i32 0
%ins1 = insertelement <8 x i16> %ins0, i16 %a1, i32 1
%ins2 = insertelement <8 x i16> %ins1, i16 undef, i32 2
%ins3 = insertelement <8 x i16> %ins2, i16 %a3, i32 3
%ins4 = insertelement <8 x i16> %ins3, i16 %a4, i32 4
%ins5 = insertelement <8 x i16> %ins4, i16 %a5, i32 5
%ins6 = insertelement <8 x i16> %ins5, i16 undef, i32 6
%ins7 = insertelement <8 x i16> %ins6, i16 undef, i32 7
ret <8 x i16> %ins7
}
define <8 x i16> @test_buildvector_v8i16_register_zero(i16 %a0, i16 %a3, i16 %a4, i16 %a5) {
; CHECK-LABEL: test_buildvector_v8i16_register_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
; CHECK: # %bb.0:
[X86][SSE] Add additional v4i32/v8i16/v16i8 build vector insertion tests With particular interest in cases where we don't make use of implicit zeroing or fail to break register dependencies llvm-svn: 294363
2017-02-08 06:03:37 +08:00
; CHECK-NEXT: pxor %xmm0, %xmm0
; CHECK-NEXT: pinsrw $0, %edi, %xmm0
; CHECK-NEXT: pinsrw $3, %esi, %xmm0
; CHECK-NEXT: pinsrw $4, %edx, %xmm0
; CHECK-NEXT: pinsrw $5, %ecx, %xmm0
; CHECK-NEXT: retq
%ins0 = insertelement <8 x i16> undef, i16 %a0, i32 0
%ins1 = insertelement <8 x i16> %ins0, i16 0, i32 1
%ins2 = insertelement <8 x i16> %ins1, i16 0, i32 2
%ins3 = insertelement <8 x i16> %ins2, i16 %a3, i32 3
%ins4 = insertelement <8 x i16> %ins3, i16 %a4, i32 4
%ins5 = insertelement <8 x i16> %ins4, i16 %a5, i32 5
%ins6 = insertelement <8 x i16> %ins5, i16 0, i32 6
%ins7 = insertelement <8 x i16> %ins6, i16 0, i32 7
ret <8 x i16> %ins7
}
define <8 x i16> @test_buildvector_v8i16_register_zero_2(i16 %a1, i16 %a3, i16 %a4, i16 %a5) {
; CHECK-LABEL: test_buildvector_v8i16_register_zero_2:
[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
; CHECK: # %bb.0:
[X86][SSE] Add additional v4i32/v8i16/v16i8 build vector insertion tests With particular interest in cases where we don't make use of implicit zeroing or fail to break register dependencies llvm-svn: 294363
2017-02-08 06:03:37 +08:00
; CHECK-NEXT: pxor %xmm0, %xmm0
; CHECK-NEXT: pinsrw $1, %edi, %xmm0
; CHECK-NEXT: pinsrw $3, %esi, %xmm0
; CHECK-NEXT: pinsrw $4, %edx, %xmm0
; CHECK-NEXT: pinsrw $5, %ecx, %xmm0
; CHECK-NEXT: retq
%ins0 = insertelement <8 x i16> undef, i16 0, i32 0
%ins1 = insertelement <8 x i16> %ins0, i16 %a1, i32 1
%ins2 = insertelement <8 x i16> %ins1, i16 0, i32 2
%ins3 = insertelement <8 x i16> %ins2, i16 %a3, i32 3
%ins4 = insertelement <8 x i16> %ins3, i16 %a4, i32 4
%ins5 = insertelement <8 x i16> %ins4, i16 %a5, i32 5
%ins6 = insertelement <8 x i16> %ins5, i16 0, i32 6
%ins7 = insertelement <8 x i16> %ins6, i16 0, i32 7
ret <8 x i16> %ins7
}
define <16 x i8> @test_buildvector_v16i8_register(i8 %a0, i8 %a1, i8 %a2, i8 %a3, i8 %a4, i8 %a5, i8 %a6, i8 %a7, i8 %a8, i8 %a9, i8 %a10, i8 %a11, i8 %a12, i8 %a13, i8 %a14, i8 %a15) {
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-LABEL: test_buildvector_v16i8_register:
[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
; SSE2: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE2-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE2-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: movd {{.*#+}} xmm3 = mem[0],zero,zero,zero
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: movd %r9d, %xmm0
; SSE2-NEXT: movd %r8d, %xmm2
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSE2-NEXT: movd %ecx, %xmm0
; SSE2-NEXT: movd %edx, %xmm1
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: movd %esi, %xmm4
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movd %edi, %xmm0
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3],xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
[X86][SSE] Change BUILD_VECTOR interleaving ordering to improve coalescing/combine opportunities We currently generate BUILD_VECTOR as a tree of UNPCKL shuffles of the same type: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 2, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 1> Step 2: unpcklps X, Y ==> <3, 2, 1, 0> The issue is because we are not placing sequential vector elements together early enough, we fail to recognise many combinable patterns - consecutive scalar loads, extractions etc. Instead, this patch unpacks progressively larger sequential vector elements together: e.g. for v4f32: Step 1: unpcklps 0, 2 ==> X: <?, ?, 1, 0> : unpcklps 1, 3 ==> Y: <?, ?, 3, 2> Step 2: unpcklpd X, Y ==> <3, 2, 1, 0> This does mean that we are creating UNPCKL shuffle of different value types, but the relevant combines that benefit from this are quite capable of handling the additional BITCASTs that are now included in the shuffle tree. Differential Revision: https://reviews.llvm.org/D33864 llvm-svn: 304688
2017-06-05 04:12:04 +08:00
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm3[0]
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: retq
;
; SSE41-LABEL: test_buildvector_v16i8_register:
[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
; SSE41: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE41-NEXT: movd %edi, %xmm0
; SSE41-NEXT: pinsrb $1, %esi, %xmm0
; SSE41-NEXT: pinsrb $2, %edx, %xmm0
; SSE41-NEXT: pinsrb $3, %ecx, %xmm0
; SSE41-NEXT: pinsrb $4, %r8d, %xmm0
; SSE41-NEXT: pinsrb $5, %r9d, %xmm0
; SSE41-NEXT: pinsrb $6, {{[0-9]+}}(%rsp), %xmm0
; SSE41-NEXT: pinsrb $7, {{[0-9]+}}(%rsp), %xmm0
; SSE41-NEXT: pinsrb $8, {{[0-9]+}}(%rsp), %xmm0
; SSE41-NEXT: pinsrb $9, {{[0-9]+}}(%rsp), %xmm0
; SSE41-NEXT: pinsrb $10, {{[0-9]+}}(%rsp), %xmm0
; SSE41-NEXT: pinsrb $11, {{[0-9]+}}(%rsp), %xmm0
; SSE41-NEXT: pinsrb $12, {{[0-9]+}}(%rsp), %xmm0
; SSE41-NEXT: pinsrb $13, {{[0-9]+}}(%rsp), %xmm0
; SSE41-NEXT: pinsrb $14, {{[0-9]+}}(%rsp), %xmm0
; SSE41-NEXT: pinsrb $15, {{[0-9]+}}(%rsp), %xmm0
; SSE41-NEXT: retq
[X86][SSE] Add additional v4i32/v8i16/v16i8 build vector insertion tests With particular interest in cases where we don't make use of implicit zeroing or fail to break register dependencies llvm-svn: 294363
2017-02-08 06:03:37 +08:00
%ins0 = insertelement <16 x i8> undef, i8 %a0, i32 0
%ins1 = insertelement <16 x i8> %ins0, i8 %a1, i32 1
%ins2 = insertelement <16 x i8> %ins1, i8 %a2, i32 2
%ins3 = insertelement <16 x i8> %ins2, i8 %a3, i32 3
%ins4 = insertelement <16 x i8> %ins3, i8 %a4, i32 4
%ins5 = insertelement <16 x i8> %ins4, i8 %a5, i32 5
%ins6 = insertelement <16 x i8> %ins5, i8 %a6, i32 6
%ins7 = insertelement <16 x i8> %ins6, i8 %a7, i32 7
%ins8 = insertelement <16 x i8> %ins7, i8 %a8, i32 8
%ins9 = insertelement <16 x i8> %ins8, i8 %a9, i32 9
%ins10 = insertelement <16 x i8> %ins9, i8 %a10, i32 10
%ins11 = insertelement <16 x i8> %ins10, i8 %a11, i32 11
%ins12 = insertelement <16 x i8> %ins11, i8 %a12, i32 12
%ins13 = insertelement <16 x i8> %ins12, i8 %a13, i32 13
%ins14 = insertelement <16 x i8> %ins13, i8 %a14, i32 14
%ins15 = insertelement <16 x i8> %ins14, i8 %a15, i32 15
ret <16 x i8> %ins15
}
define <16 x i8> @test_buildvector_v16i8_partial(i8 %a2, i8 %a6, i8 %a8, i8 %a11, i8 %a12, i8 %a15) {
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-LABEL: test_buildvector_v16i8_partial:
[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
; SSE2: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movzbl %dil, %eax
; SSE2-NEXT: pinsrw $1, %eax, %xmm0
; SSE2-NEXT: movzbl %sil, %eax
; SSE2-NEXT: pinsrw $3, %eax, %xmm0
; SSE2-NEXT: movzbl %dl, %eax
; SSE2-NEXT: pinsrw $4, %eax, %xmm0
; SSE2-NEXT: shll $8, %ecx
; SSE2-NEXT: pinsrw $5, %ecx, %xmm0
; SSE2-NEXT: movzbl %r8b, %eax
; SSE2-NEXT: pinsrw $6, %eax, %xmm0
; SSE2-NEXT: shll $8, %r9d
; SSE2-NEXT: pinsrw $7, %r9d, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: test_buildvector_v16i8_partial:
[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
; SSE41: # %bb.0:
[X86][SSE] Attempt to break register dependencies during lowerBuildVector LowerBuildVectorv16i8/LowerBuildVectorv8i16 insert values into a UNDEF vector if the build vector doesn't contain any zero elements, resulting in register dependencies with a previous use of the register. This patch attempts to break the register dependency by either always zeroing the vector before hand or (if we're inserting to the 0'th element) by using VZEXT_MOVL(SCALAR_TO_VECTOR(i32 AEXT(Elt))) which lowers to (V)MOVD and performs a similar function. Additionally (V)MOVD is a shorter instruction than PINSRB/PINSRW. We already do something similar for SSE41 PINSRD. On pre-SSE41 LowerBuildVectorv16i8 we go a little further and use VZEXT_MOVL(SCALAR_TO_VECTOR(i32 ZEXT(Elt))) if the build vector contains zeros to avoid the vector zeroing at the cost of a scalar zero extension, which can probably be brought over to the other cases in a future patch in some cases (load folding etc.) Differential Revision: https://reviews.llvm.org/D29720 llvm-svn: 294581
2017-02-09 19:50:19 +08:00
; SSE41-NEXT: pxor %xmm0, %xmm0
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE41-NEXT: pinsrb $2, %edi, %xmm0
; SSE41-NEXT: pinsrb $6, %esi, %xmm0
; SSE41-NEXT: pinsrb $8, %edx, %xmm0
; SSE41-NEXT: pinsrb $11, %ecx, %xmm0
; SSE41-NEXT: pinsrb $12, %r8d, %xmm0
; SSE41-NEXT: pinsrb $15, %r9d, %xmm0
; SSE41-NEXT: retq
[X86][SSE] Add additional v4i32/v8i16/v16i8 build vector insertion tests With particular interest in cases where we don't make use of implicit zeroing or fail to break register dependencies llvm-svn: 294363
2017-02-08 06:03:37 +08:00
%ins0 = insertelement <16 x i8> undef, i8 undef, i32 0
%ins1 = insertelement <16 x i8> %ins0, i8 undef, i32 1
%ins2 = insertelement <16 x i8> %ins1, i8 %a2, i32 2
%ins3 = insertelement <16 x i8> %ins2, i8 undef, i32 3
%ins4 = insertelement <16 x i8> %ins3, i8 undef, i32 4
%ins5 = insertelement <16 x i8> %ins4, i8 undef, i32 5
%ins6 = insertelement <16 x i8> %ins5, i8 %a6, i32 6
%ins7 = insertelement <16 x i8> %ins6, i8 undef, i32 7
%ins8 = insertelement <16 x i8> %ins7, i8 %a8, i32 8
%ins9 = insertelement <16 x i8> %ins8, i8 undef, i32 9
%ins10 = insertelement <16 x i8> %ins9, i8 undef, i32 10
%ins11 = insertelement <16 x i8> %ins10, i8 %a11, i32 11
%ins12 = insertelement <16 x i8> %ins11, i8 %a12, i32 12
%ins13 = insertelement <16 x i8> %ins12, i8 undef, i32 13
%ins14 = insertelement <16 x i8> %ins13, i8 undef, i32 14
%ins15 = insertelement <16 x i8> %ins14, i8 %a15, i32 15
ret <16 x i8> %ins15
}
define <16 x i8> @test_buildvector_v16i8_register_zero(i8 %a0, i8 %a4, i8 %a6, i8 %a8, i8 %a11, i8 %a12, i8 %a15) {
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-LABEL: test_buildvector_v16i8_register_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
; SSE2: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: movzbl %sil, %eax
[X86][SSE] Attempt to break register dependencies during lowerBuildVector LowerBuildVectorv16i8/LowerBuildVectorv8i16 insert values into a UNDEF vector if the build vector doesn't contain any zero elements, resulting in register dependencies with a previous use of the register. This patch attempts to break the register dependency by either always zeroing the vector before hand or (if we're inserting to the 0'th element) by using VZEXT_MOVL(SCALAR_TO_VECTOR(i32 AEXT(Elt))) which lowers to (V)MOVD and performs a similar function. Additionally (V)MOVD is a shorter instruction than PINSRB/PINSRW. We already do something similar for SSE41 PINSRD. On pre-SSE41 LowerBuildVectorv16i8 we go a little further and use VZEXT_MOVL(SCALAR_TO_VECTOR(i32 ZEXT(Elt))) if the build vector contains zeros to avoid the vector zeroing at the cost of a scalar zero extension, which can probably be brought over to the other cases in a future patch in some cases (load folding etc.) Differential Revision: https://reviews.llvm.org/D29720 llvm-svn: 294581
2017-02-09 19:50:19 +08:00
; SSE2-NEXT: movzbl %dil, %esi
; SSE2-NEXT: movd %esi, %xmm0
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: pinsrw $2, %eax, %xmm0
; SSE2-NEXT: movzbl %dl, %eax
; SSE2-NEXT: pinsrw $3, %eax, %xmm0
; SSE2-NEXT: movzbl %cl, %eax
; SSE2-NEXT: pinsrw $4, %eax, %xmm0
; SSE2-NEXT: shll $8, %r8d
; SSE2-NEXT: pinsrw $5, %r8d, %xmm0
; SSE2-NEXT: movzbl %r9b, %eax
; SSE2-NEXT: pinsrw $6, %eax, %xmm0
; SSE2-NEXT: movl {{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: shll $8, %eax
; SSE2-NEXT: pinsrw $7, %eax, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: test_buildvector_v16i8_register_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
; SSE41: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE41-NEXT: pxor %xmm0, %xmm0
; SSE41-NEXT: pinsrb $0, %edi, %xmm0
; SSE41-NEXT: pinsrb $4, %esi, %xmm0
; SSE41-NEXT: pinsrb $6, %edx, %xmm0
; SSE41-NEXT: pinsrb $8, %ecx, %xmm0
; SSE41-NEXT: pinsrb $11, %r8d, %xmm0
; SSE41-NEXT: pinsrb $12, %r9d, %xmm0
; SSE41-NEXT: pinsrb $15, {{[0-9]+}}(%rsp), %xmm0
; SSE41-NEXT: retq
[X86][SSE] Add additional v4i32/v8i16/v16i8 build vector insertion tests With particular interest in cases where we don't make use of implicit zeroing or fail to break register dependencies llvm-svn: 294363
2017-02-08 06:03:37 +08:00
%ins0 = insertelement <16 x i8> undef, i8 %a0, i32 0
%ins1 = insertelement <16 x i8> %ins0, i8 0, i32 1
%ins2 = insertelement <16 x i8> %ins1, i8 0, i32 2
%ins3 = insertelement <16 x i8> %ins2, i8 0, i32 3
%ins4 = insertelement <16 x i8> %ins3, i8 %a4, i32 4
%ins5 = insertelement <16 x i8> %ins4, i8 0, i32 5
%ins6 = insertelement <16 x i8> %ins5, i8 %a6, i32 6
%ins7 = insertelement <16 x i8> %ins6, i8 0, i32 7
%ins8 = insertelement <16 x i8> %ins7, i8 %a8, i32 8
%ins9 = insertelement <16 x i8> %ins8, i8 0, i32 9
%ins10 = insertelement <16 x i8> %ins9, i8 0, i32 10
%ins11 = insertelement <16 x i8> %ins10, i8 %a11, i32 11
%ins12 = insertelement <16 x i8> %ins11, i8 %a12, i32 12
%ins13 = insertelement <16 x i8> %ins12, i8 0, i32 13
%ins14 = insertelement <16 x i8> %ins13, i8 0, i32 14
%ins15 = insertelement <16 x i8> %ins14, i8 %a15, i32 15
ret <16 x i8> %ins15
}
define <16 x i8> @test_buildvector_v16i8_register_zero_2(i8 %a2, i8 %a3, i8 %a6, i8 %a8, i8 %a11, i8 %a12, i8 %a15) {
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-LABEL: test_buildvector_v16i8_register_zero_2:
[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
; SSE2: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE2-NEXT: shll $8, %esi
; SSE2-NEXT: movzbl %dil, %eax
; SSE2-NEXT: orl %esi, %eax
; SSE2-NEXT: pxor %xmm0, %xmm0
; SSE2-NEXT: pinsrw $1, %eax, %xmm0
; SSE2-NEXT: movzbl %dl, %eax
; SSE2-NEXT: pinsrw $3, %eax, %xmm0
; SSE2-NEXT: movzbl %cl, %eax
; SSE2-NEXT: pinsrw $4, %eax, %xmm0
; SSE2-NEXT: shll $8, %r8d
; SSE2-NEXT: pinsrw $5, %r8d, %xmm0
; SSE2-NEXT: movzbl %r9b, %eax
; SSE2-NEXT: pinsrw $6, %eax, %xmm0
; SSE2-NEXT: movl {{[0-9]+}}(%rsp), %eax
; SSE2-NEXT: shll $8, %eax
; SSE2-NEXT: pinsrw $7, %eax, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: test_buildvector_v16i8_register_zero_2:
[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
; SSE41: # %bb.0:
[X86][SSE] Add SSE2 build vector insertion tests llvm-svn: 294365
2017-02-08 06:23:12 +08:00
; SSE41-NEXT: pxor %xmm0, %xmm0
; SSE41-NEXT: pinsrb $2, %edi, %xmm0
; SSE41-NEXT: pinsrb $3, %esi, %xmm0
; SSE41-NEXT: pinsrb $6, %edx, %xmm0
; SSE41-NEXT: pinsrb $8, %ecx, %xmm0
; SSE41-NEXT: pinsrb $11, %r8d, %xmm0
; SSE41-NEXT: pinsrb $12, %r9d, %xmm0
; SSE41-NEXT: pinsrb $15, {{[0-9]+}}(%rsp), %xmm0
; SSE41-NEXT: retq
[X86][SSE] Add additional v4i32/v8i16/v16i8 build vector insertion tests With particular interest in cases where we don't make use of implicit zeroing or fail to break register dependencies llvm-svn: 294363
2017-02-08 06:03:37 +08:00
%ins0 = insertelement <16 x i8> undef, i8 0, i32 0
%ins1 = insertelement <16 x i8> %ins0, i8 0, i32 1
%ins2 = insertelement <16 x i8> %ins1, i8 %a2, i32 2
%ins3 = insertelement <16 x i8> %ins2, i8 %a3, i32 3
%ins4 = insertelement <16 x i8> %ins3, i8 0, i32 4
%ins5 = insertelement <16 x i8> %ins4, i8 0, i32 5
%ins6 = insertelement <16 x i8> %ins5, i8 %a6, i32 6
%ins7 = insertelement <16 x i8> %ins6, i8 0, i32 7
%ins8 = insertelement <16 x i8> %ins7, i8 %a8, i32 8
%ins9 = insertelement <16 x i8> %ins8, i8 0, i32 9
%ins10 = insertelement <16 x i8> %ins9, i8 0, i32 10
%ins11 = insertelement <16 x i8> %ins10, i8 %a11, i32 11
%ins12 = insertelement <16 x i8> %ins11, i8 %a12, i32 12
%ins13 = insertelement <16 x i8> %ins12, i8 0, i32 13
%ins14 = insertelement <16 x i8> %ins13, i8 0, i32 14
%ins15 = insertelement <16 x i8> %ins14, i8 %a15, i32 15
ret <16 x i8> %ins15
}
[DAGCombine] reduceBuildVecToShuffle - ensure EXTRACT_VECTOR_ELT index is in range From OSS Fuzz Test Case #5688 llvm-svn: 323535
2018-01-26 23:50:20 +08:00
; OSS-Fuzz #5688
; https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=5688
define <4 x i32> @ossfuzz5688(i32 %a0) {
; CHECK-LABEL: ossfuzz5688:
; CHECK: # %bb.0:
; CHECK-NEXT: retq
%1 = insertelement <4 x i32> zeroinitializer, i32 -2147483648, i32 %a0
%2 = extractelement <4 x i32> %1, i32 %a0
%3 = extractelement <4 x i32> <i32 30, i32 53, i32 42, i32 12>, i32 %2
%4 = extractelement <4 x i32> zeroinitializer, i32 %2
%5 = insertelement <4 x i32> undef, i32 %3, i32 undef
store i32 %4, i32* undef
ret <4 x i32> %5
}