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/cvtv2f32.ll

98 lines
3.9 KiB
LLVM
Raw Normal View History

[X86][SSE] Regenerated uitofp <2 x i32> -> <2 x float> conversion tests Demonstrate difference in codegen discussed on PR14760 llvm-svn: 276526
2016-07-23 23:55:42 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-linux-pc -mcpu=corei7 | FileCheck %s --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-linux-pc -mcpu=corei7 | FileCheck %s --check-prefix=X64
DAGCombiner: Avoid generating illegal vector INT_TO_FP nodes DAGCombiner::reduceBuildVecConvertToConvertBuildVec() was making two mistakes: 1. It was checking the legality of scalar INT_TO_FP nodes and then generating vector nodes. 2. It was passing the result value type to TargetLoweringInfo::getOperationAction() when it should have been passing the value type of the first operand. llvm-svn: 171420
2013-01-03 06:13:01 +08:00
[X86][SSE] Let 64-bit targets use the fast 2i32-2f32 UINT_TO_FP conversion as well as 32-bit The 2i32-2i64 legalization means that we can use the slightly quicker double bits + fptrunc approach for the same results llvm-svn: 277271
2016-07-30 22:06:59 +08:00
; uitofp <2 x i32> codegen from buildvector or legalization is different but gives the same results
; across the full 0 - 0xFFFFFFFF u32 range.
Add custom conversion from v2u32 to v2f32 in 32-bit mode - As there's no 64-bit GPRs in 32-bit mode, a custom conversion from v2u32 to v2f32 is added to improve the efficiency of the code generated. llvm-svn: 166545
2012-10-24 12:09:32 +08:00
[X86][SSE] Add test for (v2f32 uitofp(build_vector(i32, i32))) (PR35732) To compare against (v2f32 build_vector(f32 uitofp(i32), f32 uitofp(i32))) llvm-svn: 321583
2017-12-30 19:20:56 +08:00
define <2 x float> @uitofp_2i32_cvt_buildvector(i32 %x, i32 %y, <2 x float> %v) {
; X32-LABEL: uitofp_2i32_cvt_buildvector:
[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
; X32: # %bb.0:
[X86][SSE] Regenerated uitofp <2 x i32> -> <2 x float> conversion tests Demonstrate difference in codegen discussed on PR14760 llvm-svn: 276526
2016-07-23 23:55:42 +08:00
; X32-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; X32-NEXT: movdqa {{.*#+}} xmm2 = [1258291200,1258291200,1258291200,1258291200]
; X32-NEXT: pblendw {{.*#+}} xmm2 = xmm1[0],xmm2[1],xmm1[2],xmm2[3],xmm1[4],xmm2[5],xmm1[6],xmm2[7]
; X32-NEXT: psrld $16, %xmm1
; X32-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0],mem[1],xmm1[2],mem[3],xmm1[4],mem[5],xmm1[6],mem[7]
; X32-NEXT: addps {{\.LCPI.*}}, %xmm1
; X32-NEXT: addps %xmm2, %xmm1
; X32-NEXT: mulps %xmm1, %xmm0
; X32-NEXT: retl
;
[X86][SSE] Add test for (v2f32 uitofp(build_vector(i32, i32))) (PR35732) To compare against (v2f32 build_vector(f32 uitofp(i32), f32 uitofp(i32))) llvm-svn: 321583
2017-12-30 19:20:56 +08:00
; X64-LABEL: uitofp_2i32_cvt_buildvector:
[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
; X64: # %bb.0:
[X86][SSE] Regenerated uitofp <2 x i32> -> <2 x float> conversion tests Demonstrate difference in codegen discussed on PR14760 llvm-svn: 276526
2016-07-23 23:55:42 +08:00
; X64-NEXT: movd %edi, %xmm1
; X64-NEXT: pinsrd $1, %esi, %xmm1
; X64-NEXT: movdqa {{.*#+}} xmm2 = [1258291200,1258291200,1258291200,1258291200]
; X64-NEXT: pblendw {{.*#+}} xmm2 = xmm1[0],xmm2[1],xmm1[2],xmm2[3],xmm1[4],xmm2[5],xmm1[6],xmm2[7]
; X64-NEXT: psrld $16, %xmm1
; X64-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0],mem[1],xmm1[2],mem[3],xmm1[4],mem[5],xmm1[6],mem[7]
; X64-NEXT: addps {{.*}}(%rip), %xmm1
; X64-NEXT: addps %xmm2, %xmm1
; X64-NEXT: mulps %xmm1, %xmm0
; X64-NEXT: retq
Teach DAG combine to fold (buildvec (Xint2fp x)) to (Xint2fp (buildvec x)) - If more than 1 elemennts are defined and target supports the vectorized conversion, use the vectorized one instead to reduce the strength on conversion operation. llvm-svn: 166546
2012-10-24 12:14:18 +08:00
%t1 = uitofp i32 %x to float
%t2 = insertelement <2 x float> undef, float %t1, i32 0
%t3 = uitofp i32 %y to float
%t4 = insertelement <2 x float> %t2, float %t3, i32 1
%t5 = fmul <2 x float> %v, %t4
ret <2 x float> %t5
}
[X86][SSE] Add test for (v2f32 uitofp(build_vector(i32, i32))) (PR35732) To compare against (v2f32 build_vector(f32 uitofp(i32), f32 uitofp(i32))) llvm-svn: 321583
2017-12-30 19:20:56 +08:00
define <2 x float> @uitofp_2i32_buildvector_cvt(i32 %x, i32 %y, <2 x float> %v) {
; X32-LABEL: uitofp_2i32_buildvector_cvt:
; X32: # %bb.0:
; X32-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X32-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; X32-NEXT: unpcklpd {{.*#+}} xmm2 = xmm2[0],xmm1[0]
[X86] Standardize floating point assembly comments Consistently try to use APFloat::toString for floating point constant comments to get rid of differences between Constant / ConstantDataSequential values - it should help stop some of the linux-windows buildbot failures matching NaN/INF etc. as well. Differential Revision: https://reviews.llvm.org/D52702 llvm-svn: 343562
2018-10-02 17:08:51 +08:00
; X32-NEXT: movapd {{.*#+}} xmm1 = [4503599627370496,4503599627370496]
[X86][SSE] Add test for (v2f32 uitofp(build_vector(i32, i32))) (PR35732) To compare against (v2f32 build_vector(f32 uitofp(i32), f32 uitofp(i32))) llvm-svn: 321583
2017-12-30 19:20:56 +08:00
; X32-NEXT: orpd %xmm1, %xmm2
; X32-NEXT: subpd %xmm1, %xmm2
; X32-NEXT: cvtpd2ps %xmm2, %xmm1
; X32-NEXT: mulps %xmm1, %xmm0
; X32-NEXT: retl
;
; X64-LABEL: uitofp_2i32_buildvector_cvt:
; X64: # %bb.0:
; X64-NEXT: movd %esi, %xmm1
; X64-NEXT: movd %edi, %xmm2
; X64-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm1[0]
[X86] Standardize floating point assembly comments Consistently try to use APFloat::toString for floating point constant comments to get rid of differences between Constant / ConstantDataSequential values - it should help stop some of the linux-windows buildbot failures matching NaN/INF etc. as well. Differential Revision: https://reviews.llvm.org/D52702 llvm-svn: 343562
2018-10-02 17:08:51 +08:00
; X64-NEXT: movdqa {{.*#+}} xmm1 = [4503599627370496,4503599627370496]
[X86][SSE] Add test for (v2f32 uitofp(build_vector(i32, i32))) (PR35732) To compare against (v2f32 build_vector(f32 uitofp(i32), f32 uitofp(i32))) llvm-svn: 321583
2017-12-30 19:20:56 +08:00
; X64-NEXT: por %xmm1, %xmm2
; X64-NEXT: subpd %xmm1, %xmm2
; X64-NEXT: cvtpd2ps %xmm2, %xmm1
; X64-NEXT: mulps %xmm1, %xmm0
; X64-NEXT: retq
%t1 = insertelement <2 x i32> undef, i32 %x, i32 0
%t2 = insertelement <2 x i32> %t1, i32 %y, i32 1
%t3 = uitofp <2 x i32> %t2 to <2 x float>
%t4 = fmul <2 x float> %v, %t3
ret <2 x float> %t4
}
[X86][SSE] Updated test so that both are applying the post-multiply This is to ensure that there are no diffs other than due to buildvector/legalization llvm-svn: 276882
2016-07-27 23:30:20 +08:00
define <2 x float> @uitofp_2i32_legalized(<2 x i32> %in, <2 x float> %v) {
[X86][SSE] Regenerated uitofp <2 x i32> -> <2 x float> conversion tests Demonstrate difference in codegen discussed on PR14760 llvm-svn: 276526
2016-07-23 23:55:42 +08:00
; X32-LABEL: uitofp_2i32_legalized:
[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
; X32: # %bb.0:
[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
; X32-NEXT: xorps %xmm2, %xmm2
; X32-NEXT: blendps {{.*#+}} xmm2 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
[X86] Standardize floating point assembly comments Consistently try to use APFloat::toString for floating point constant comments to get rid of differences between Constant / ConstantDataSequential values - it should help stop some of the linux-windows buildbot failures matching NaN/INF etc. as well. Differential Revision: https://reviews.llvm.org/D52702 llvm-svn: 343562
2018-10-02 17:08:51 +08:00
; X32-NEXT: movaps {{.*#+}} xmm0 = [4503599627370496,4503599627370496]
[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
; X32-NEXT: orps %xmm0, %xmm2
[X86][SSE] Updated test so that both are applying the post-multiply This is to ensure that there are no diffs other than due to buildvector/legalization llvm-svn: 276882
2016-07-27 23:30:20 +08:00
; X32-NEXT: subpd %xmm0, %xmm2
; X32-NEXT: cvtpd2ps %xmm2, %xmm0
; X32-NEXT: mulps %xmm1, %xmm0
[X86][SSE] Regenerated uitofp <2 x i32> -> <2 x float> conversion tests Demonstrate difference in codegen discussed on PR14760 llvm-svn: 276526
2016-07-23 23:55:42 +08:00
; X32-NEXT: retl
;
; X64-LABEL: uitofp_2i32_legalized:
[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
; X64: # %bb.0:
[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
; X64-NEXT: xorps %xmm2, %xmm2
; X64-NEXT: blendps {{.*#+}} xmm2 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
[X86] Standardize floating point assembly comments Consistently try to use APFloat::toString for floating point constant comments to get rid of differences between Constant / ConstantDataSequential values - it should help stop some of the linux-windows buildbot failures matching NaN/INF etc. as well. Differential Revision: https://reviews.llvm.org/D52702 llvm-svn: 343562
2018-10-02 17:08:51 +08:00
; X64-NEXT: movaps {{.*#+}} xmm0 = [4503599627370496,4503599627370496]
[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
; X64-NEXT: orps %xmm0, %xmm2
[X86][SSE] Let 64-bit targets use the fast 2i32-2f32 UINT_TO_FP conversion as well as 32-bit The 2i32-2i64 legalization means that we can use the slightly quicker double bits + fptrunc approach for the same results llvm-svn: 277271
2016-07-30 22:06:59 +08:00
; X64-NEXT: subpd %xmm0, %xmm2
; X64-NEXT: cvtpd2ps %xmm2, %xmm0
[X86][SSE] Updated test so that both are applying the post-multiply This is to ensure that there are no diffs other than due to buildvector/legalization llvm-svn: 276882
2016-07-27 23:30:20 +08:00
; X64-NEXT: mulps %xmm1, %xmm0
[X86][SSE] Regenerated uitofp <2 x i32> -> <2 x float> conversion tests Demonstrate difference in codegen discussed on PR14760 llvm-svn: 276526
2016-07-23 23:55:42 +08:00
; X64-NEXT: retq
[X86][SSE] Updated test so that both are applying the post-multiply This is to ensure that there are no diffs other than due to buildvector/legalization llvm-svn: 276882
2016-07-27 23:30:20 +08:00
%t1 = uitofp <2 x i32> %in to <2 x float>
%t2 = fmul <2 x float> %v, %t1
ret <2 x float> %t2
Add custom conversion from v2u32 to v2f32 in 32-bit mode - As there's no 64-bit GPRs in 32-bit mode, a custom conversion from v2u32 to v2f32 is added to improve the efficiency of the code generated. llvm-svn: 166545
2012-10-24 12:09:32 +08:00
}