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/peephole-cvt-sse.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

40 lines
1.4 KiB
LLVM
Raw Normal View History

[X86] Loosen memory folding requirements for cvtdq2pd and cvtps2pd instructions. According to spec cvtdq2pd and cvtps2pd instructions don't require memory operand to be aligned to 16 bytes. This patch removes this requirement from the memory folding table. Differential Revision: https://reviews.llvm.org/D23919 llvm-svn: 280402
2016-09-02 02:50:02 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-pc-linux -mattr=+sse4.2 < %s | FileCheck %s --check-prefix=X86-64
; RUN: llc -mtriple=i386-pc-linux -mattr=+sse4.2 < %s | FileCheck %s --check-prefix=I386
; Check that unaligned loads merge with cvtdq2pd and cvtps2pd.
define <2 x double> @peephole_cvtps2pd(<4 x float>* %a0) {
; X86-64-LABEL: peephole_cvtps2pd:
[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
; X86-64: # %bb.0:
[X86] Loosen memory folding requirements for cvtdq2pd and cvtps2pd instructions. According to spec cvtdq2pd and cvtps2pd instructions don't require memory operand to be aligned to 16 bytes. This patch removes this requirement from the memory folding table. Differential Revision: https://reviews.llvm.org/D23919 llvm-svn: 280402
2016-09-02 02:50:02 +08:00
; X86-64-NEXT: cvtps2pd (%rdi), %xmm0
; X86-64-NEXT: retq
;
; I386-LABEL: peephole_cvtps2pd:
[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
; I386: # %bb.0:
[X86] Loosen memory folding requirements for cvtdq2pd and cvtps2pd instructions. According to spec cvtdq2pd and cvtps2pd instructions don't require memory operand to be aligned to 16 bytes. This patch removes this requirement from the memory folding table. Differential Revision: https://reviews.llvm.org/D23919 llvm-svn: 280402
2016-09-02 02:50:02 +08:00
; I386-NEXT: movl {{[0-9]+}}(%esp), %eax
; I386-NEXT: cvtps2pd (%eax), %xmm0
; I386-NEXT: retl
%1 = load <4 x float>, <4 x float>* %a0, align 1
%2 = shufflevector <4 x float> %1, <4 x float> undef, <2 x i32> <i32 0, i32 1>
%3 = fpext <2 x float> %2 to <2 x double>
ret <2 x double> %3
}
define <2 x double> @peephole_cvtdq2pd(<4 x i32>* %a0) {
; X86-64-LABEL: peephole_cvtdq2pd:
[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
; X86-64: # %bb.0:
[X86] Loosen memory folding requirements for cvtdq2pd and cvtps2pd instructions. According to spec cvtdq2pd and cvtps2pd instructions don't require memory operand to be aligned to 16 bytes. This patch removes this requirement from the memory folding table. Differential Revision: https://reviews.llvm.org/D23919 llvm-svn: 280402
2016-09-02 02:50:02 +08:00
; X86-64-NEXT: cvtdq2pd (%rdi), %xmm0
; X86-64-NEXT: retq
;
; I386-LABEL: peephole_cvtdq2pd:
[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
; I386: # %bb.0:
[X86] Loosen memory folding requirements for cvtdq2pd and cvtps2pd instructions. According to spec cvtdq2pd and cvtps2pd instructions don't require memory operand to be aligned to 16 bytes. This patch removes this requirement from the memory folding table. Differential Revision: https://reviews.llvm.org/D23919 llvm-svn: 280402
2016-09-02 02:50:02 +08:00
; I386-NEXT: movl {{[0-9]+}}(%esp), %eax
; I386-NEXT: cvtdq2pd (%eax), %xmm0
; I386-NEXT: retl
%1 = load <4 x i32>, <4 x i32>* %a0, align 1
%2 = shufflevector <4 x i32> %1, <4 x i32> undef, <2 x i32> <i32 0, i32 1>
%3 = sitofp <2 x i32> %2 to <2 x double>
ret <2 x double> %3
}