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/extract-store.ll

706 lines
21 KiB
LLVM
Raw Normal View History

[X86][SSE] Regenerate extraction+store memop tests Added tests for SSE2 as well as SSE41+AVX llvm-svn: 275876
2016-07-19 02:44:01 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; RUN: llc < %s -mtriple=i686-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X32 --check-prefix=SSE-X32 --check-prefix=SSE2-X32
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X64 --check-prefix=SSE-X64 --check-prefix=SSE2-X64
; RUN: llc < %s -mtriple=i686-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=X32 --check-prefix=SSE-X32 --check-prefix=SSE41-X32
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=X64 --check-prefix=SSE-X64 --check-prefix=SSE41-X64
; RUN: llc < %s -mtriple=i686-unknown -mattr=+avx | FileCheck %s --check-prefix=X32 --check-prefix=AVX-X32
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx | FileCheck %s --check-prefix=X64 --check-prefix=AVX-X64
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; RUN: llc < %s -O2 -mtriple=x86_64-linux-android -mattr=+mmx -enable-legalize-types-checking | FileCheck %s --check-prefix=X64 --check-prefix=SSE-X64 --check-prefix=SSE-F128
; RUN: llc < %s -O2 -mtriple=x86_64-linux-gnu -mattr=+mmx -enable-legalize-types-checking | FileCheck %s --check-prefix=X64 --check-prefix=SSE-X64 --check-prefix=SSE-F128
X86: Resolve a long standing FIXME and properly isel pextr[bw]. Generalize the AArch64 .td nodes for AssertZext and AssertSext. Use them to match the relevant pextr store instructions. The test widen_load-2.ll requires a slight change because with the stores gone, the remaining instructions are scheduled in a different order. Add test cases for SSE4 and AVX variants. Resolves rdar://13414672. Patch by Adam Nemet <anemet@apple.com>. llvm-svn: 200957
2014-02-07 08:16:33 +08:00
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
define void @extract_i8_0(i8* nocapture %dst, <16 x i8> %foo) nounwind {
; SSE2-X32-LABEL: extract_i8_0:
[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-X32: # %bb.0:
[X86][SSE] Improve extraction of elements from v16i8 (pre-SSE41) Without SSE41 (pextrb) we currently extract byte elements from a vector by spilling to stack and reloading the byte. This patch is an initial attempt at using MOVD/PEXTRW to extract the relevant DWORD/WORD from the vector and then shift+truncate to collect the correct byte. Extraction of multiple bytes this way would result in code bloat, but as explained in the patch we could probably afford to be more aggressive with the supported extractions before again falling back on spilling - possibly through counting the number of extracts and which DWORD/WORD they originate? Differential Revision: https://reviews.llvm.org/D29841 llvm-svn: 297568
2017-03-12 04:42:31 +08:00
; SSE2-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE2-X32-NEXT: movd %xmm0, %ecx
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE2-X32-NEXT: movb %cl, (%eax)
; SSE2-X32-NEXT: retl
;
; SSE2-X64-LABEL: extract_i8_0:
[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-X64: # %bb.0:
[X86][SSE] Improve extraction of elements from v16i8 (pre-SSE41) Without SSE41 (pextrb) we currently extract byte elements from a vector by spilling to stack and reloading the byte. This patch is an initial attempt at using MOVD/PEXTRW to extract the relevant DWORD/WORD from the vector and then shift+truncate to collect the correct byte. Extraction of multiple bytes this way would result in code bloat, but as explained in the patch we could probably afford to be more aggressive with the supported extractions before again falling back on spilling - possibly through counting the number of extracts and which DWORD/WORD they originate? Differential Revision: https://reviews.llvm.org/D29841 llvm-svn: 297568
2017-03-12 04:42:31 +08:00
; SSE2-X64-NEXT: movd %xmm0, %eax
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE2-X64-NEXT: movb %al, (%rdi)
; SSE2-X64-NEXT: retq
;
; SSE41-X32-LABEL: extract_i8_0:
[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-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE41-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE41-X32-NEXT: pextrb $0, %xmm0, (%eax)
; SSE41-X32-NEXT: retl
;
; SSE41-X64-LABEL: extract_i8_0:
[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-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE41-X64-NEXT: pextrb $0, %xmm0, (%rdi)
; SSE41-X64-NEXT: retq
;
; AVX-X32-LABEL: extract_i8_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX-X32-NEXT: vpextrb $0, %xmm0, (%eax)
; AVX-X32-NEXT: retl
;
; AVX-X64-LABEL: extract_i8_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X64-NEXT: vpextrb $0, %xmm0, (%rdi)
; AVX-X64-NEXT: retq
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
;
; SSE-F128-LABEL: extract_i8_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-F128: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE-F128-NEXT: movd %xmm0, %eax
; SSE-F128-NEXT: movb %al, (%rdi)
; SSE-F128-NEXT: retq
[X86][SSE] Regenerate extraction+store memop tests Added tests for SSE2 as well as SSE41+AVX llvm-svn: 275876
2016-07-19 02:44:01 +08:00
%vecext = extractelement <16 x i8> %foo, i32 0
store i8 %vecext, i8* %dst, align 1
ret void
}
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
define void @extract_i8_3(i8* nocapture %dst, <16 x i8> %foo) nounwind {
; SSE2-X32-LABEL: extract_i8_3:
[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-X32: # %bb.0:
[X86][SSE] Improve extraction of elements from v16i8 (pre-SSE41) Without SSE41 (pextrb) we currently extract byte elements from a vector by spilling to stack and reloading the byte. This patch is an initial attempt at using MOVD/PEXTRW to extract the relevant DWORD/WORD from the vector and then shift+truncate to collect the correct byte. Extraction of multiple bytes this way would result in code bloat, but as explained in the patch we could probably afford to be more aggressive with the supported extractions before again falling back on spilling - possibly through counting the number of extracts and which DWORD/WORD they originate? Differential Revision: https://reviews.llvm.org/D29841 llvm-svn: 297568
2017-03-12 04:42:31 +08:00
; SSE2-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE2-X32-NEXT: movd %xmm0, %ecx
; SSE2-X32-NEXT: shrl $24, %ecx
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE2-X32-NEXT: movb %cl, (%eax)
; SSE2-X32-NEXT: retl
;
; SSE2-X64-LABEL: extract_i8_3:
[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-X64: # %bb.0:
[X86][SSE] Improve extraction of elements from v16i8 (pre-SSE41) Without SSE41 (pextrb) we currently extract byte elements from a vector by spilling to stack and reloading the byte. This patch is an initial attempt at using MOVD/PEXTRW to extract the relevant DWORD/WORD from the vector and then shift+truncate to collect the correct byte. Extraction of multiple bytes this way would result in code bloat, but as explained in the patch we could probably afford to be more aggressive with the supported extractions before again falling back on spilling - possibly through counting the number of extracts and which DWORD/WORD they originate? Differential Revision: https://reviews.llvm.org/D29841 llvm-svn: 297568
2017-03-12 04:42:31 +08:00
; SSE2-X64-NEXT: movd %xmm0, %eax
; SSE2-X64-NEXT: shrl $24, %eax
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE2-X64-NEXT: movb %al, (%rdi)
; SSE2-X64-NEXT: retq
;
; SSE41-X32-LABEL: extract_i8_3:
[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-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE41-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE41-X32-NEXT: pextrb $3, %xmm0, (%eax)
; SSE41-X32-NEXT: retl
;
; SSE41-X64-LABEL: extract_i8_3:
[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-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE41-X64-NEXT: pextrb $3, %xmm0, (%rdi)
; SSE41-X64-NEXT: retq
;
; AVX-X32-LABEL: extract_i8_3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX-X32-NEXT: vpextrb $3, %xmm0, (%eax)
; AVX-X32-NEXT: retl
;
; AVX-X64-LABEL: extract_i8_3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X64-NEXT: vpextrb $3, %xmm0, (%rdi)
; AVX-X64-NEXT: retq
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
;
; SSE-F128-LABEL: extract_i8_3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-F128: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE-F128-NEXT: movd %xmm0, %eax
; SSE-F128-NEXT: shrl $24, %eax
; SSE-F128-NEXT: movb %al, (%rdi)
; SSE-F128-NEXT: retq
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
%vecext = extractelement <16 x i8> %foo, i32 3
store i8 %vecext, i8* %dst, align 1
ret void
}
define void @extract_i8_15(i8* nocapture %dst, <16 x i8> %foo) nounwind {
; SSE2-X32-LABEL: extract_i8_15:
[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-X32: # %bb.0:
[X86][SSE] Improve extraction of elements from v16i8 (pre-SSE41) Without SSE41 (pextrb) we currently extract byte elements from a vector by spilling to stack and reloading the byte. This patch is an initial attempt at using MOVD/PEXTRW to extract the relevant DWORD/WORD from the vector and then shift+truncate to collect the correct byte. Extraction of multiple bytes this way would result in code bloat, but as explained in the patch we could probably afford to be more aggressive with the supported extractions before again falling back on spilling - possibly through counting the number of extracts and which DWORD/WORD they originate? Differential Revision: https://reviews.llvm.org/D29841 llvm-svn: 297568
2017-03-12 04:42:31 +08:00
; SSE2-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE2-X32-NEXT: pextrw $7, %xmm0, %ecx
; SSE2-X32-NEXT: movb %ch, (%eax)
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE2-X32-NEXT: retl
;
; SSE2-X64-LABEL: extract_i8_15:
[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-X64: # %bb.0:
[X86][SSE] Improve extraction of elements from v16i8 (pre-SSE41) Without SSE41 (pextrb) we currently extract byte elements from a vector by spilling to stack and reloading the byte. This patch is an initial attempt at using MOVD/PEXTRW to extract the relevant DWORD/WORD from the vector and then shift+truncate to collect the correct byte. Extraction of multiple bytes this way would result in code bloat, but as explained in the patch we could probably afford to be more aggressive with the supported extractions before again falling back on spilling - possibly through counting the number of extracts and which DWORD/WORD they originate? Differential Revision: https://reviews.llvm.org/D29841 llvm-svn: 297568
2017-03-12 04:42:31 +08:00
; SSE2-X64-NEXT: pextrw $7, %xmm0, %eax
[X86] Remove 'NOREX' comment from the printing of _NOREX instructions. Some of the NOREX instructions are used in 32-bit mode making this printing confusing. It also doesn't provide a lot of value since you can see the h-register being used by the instruction. llvm-svn: 323174
2018-01-23 13:37:00 +08:00
; SSE2-X64-NEXT: movb %ah, (%rdi)
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE2-X64-NEXT: retq
;
; SSE41-X32-LABEL: extract_i8_15:
[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-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE41-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE41-X32-NEXT: pextrb $15, %xmm0, (%eax)
; SSE41-X32-NEXT: retl
;
; SSE41-X64-LABEL: extract_i8_15:
[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-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE41-X64-NEXT: pextrb $15, %xmm0, (%rdi)
; SSE41-X64-NEXT: retq
;
; AVX-X32-LABEL: extract_i8_15:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX-X32-NEXT: vpextrb $15, %xmm0, (%eax)
; AVX-X32-NEXT: retl
;
; AVX-X64-LABEL: extract_i8_15:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X64-NEXT: vpextrb $15, %xmm0, (%rdi)
; AVX-X64-NEXT: retq
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
;
; SSE-F128-LABEL: extract_i8_15:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-F128: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE-F128-NEXT: pextrw $7, %xmm0, %eax
[X86] Remove 'NOREX' comment from the printing of _NOREX instructions. Some of the NOREX instructions are used in 32-bit mode making this printing confusing. It also doesn't provide a lot of value since you can see the h-register being used by the instruction. llvm-svn: 323174
2018-01-23 13:37:00 +08:00
; SSE-F128-NEXT: movb %ah, (%rdi)
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE-F128-NEXT: retq
X86: Resolve a long standing FIXME and properly isel pextr[bw]. Generalize the AArch64 .td nodes for AssertZext and AssertSext. Use them to match the relevant pextr store instructions. The test widen_load-2.ll requires a slight change because with the stores gone, the remaining instructions are scheduled in a different order. Add test cases for SSE4 and AVX variants. Resolves rdar://13414672. Patch by Adam Nemet <anemet@apple.com>. llvm-svn: 200957
2014-02-07 08:16:33 +08:00
%vecext = extractelement <16 x i8> %foo, i32 15
store i8 %vecext, i8* %dst, align 1
ret void
}
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
define void @extract_i16_0(i16* nocapture %dst, <8 x i16> %foo) nounwind {
; SSE2-X32-LABEL: extract_i16_0:
[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-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE2-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE2-X32-NEXT: movd %xmm0, %ecx
; SSE2-X32-NEXT: movw %cx, (%eax)
; SSE2-X32-NEXT: retl
;
; SSE2-X64-LABEL: extract_i16_0:
[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-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE2-X64-NEXT: movd %xmm0, %eax
; SSE2-X64-NEXT: movw %ax, (%rdi)
; SSE2-X64-NEXT: retq
;
; SSE41-X32-LABEL: extract_i16_0:
[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-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE41-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE41-X32-NEXT: pextrw $0, %xmm0, (%eax)
; SSE41-X32-NEXT: retl
;
; SSE41-X64-LABEL: extract_i16_0:
[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-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE41-X64-NEXT: pextrw $0, %xmm0, (%rdi)
; SSE41-X64-NEXT: retq
;
; AVX-X32-LABEL: extract_i16_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX-X32-NEXT: vpextrw $0, %xmm0, (%eax)
; AVX-X32-NEXT: retl
;
; AVX-X64-LABEL: extract_i16_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X64-NEXT: vpextrw $0, %xmm0, (%rdi)
; AVX-X64-NEXT: retq
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
;
; SSE-F128-LABEL: extract_i16_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-F128: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE-F128-NEXT: movd %xmm0, %eax
; SSE-F128-NEXT: movw %ax, (%rdi)
; SSE-F128-NEXT: retq
[X86][SSE] Regenerate extraction+store memop tests Added tests for SSE2 as well as SSE41+AVX llvm-svn: 275876
2016-07-19 02:44:01 +08:00
%vecext = extractelement <8 x i16> %foo, i32 0
store i16 %vecext, i16* %dst, align 1
ret void
}
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
define void @extract_i16_7(i16* nocapture %dst, <8 x i16> %foo) nounwind {
; SSE2-X32-LABEL: extract_i16_7:
[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-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE2-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE2-X32-NEXT: pextrw $7, %xmm0, %ecx
; SSE2-X32-NEXT: movw %cx, (%eax)
; SSE2-X32-NEXT: retl
;
; SSE2-X64-LABEL: extract_i16_7:
[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-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE2-X64-NEXT: pextrw $7, %xmm0, %eax
; SSE2-X64-NEXT: movw %ax, (%rdi)
; SSE2-X64-NEXT: retq
;
; SSE41-X32-LABEL: extract_i16_7:
[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-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE41-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE41-X32-NEXT: pextrw $7, %xmm0, (%eax)
; SSE41-X32-NEXT: retl
;
; SSE41-X64-LABEL: extract_i16_7:
[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-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE41-X64-NEXT: pextrw $7, %xmm0, (%rdi)
; SSE41-X64-NEXT: retq
;
; AVX-X32-LABEL: extract_i16_7:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX-X32-NEXT: vpextrw $7, %xmm0, (%eax)
; AVX-X32-NEXT: retl
;
; AVX-X64-LABEL: extract_i16_7:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X64-NEXT: vpextrw $7, %xmm0, (%rdi)
; AVX-X64-NEXT: retq
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
;
; SSE-F128-LABEL: extract_i16_7:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-F128: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE-F128-NEXT: pextrw $7, %xmm0, %eax
; SSE-F128-NEXT: movw %ax, (%rdi)
; SSE-F128-NEXT: retq
SelectionDAG: Handle out-of-bounds index in extract vector element Summary: This patch correctly handles undef case of EXTRACT_VECTOR_ELT node where the element index is constant and not less than vector size. Test Plan: CodeGen for X86 test included. Also one incorrect regression test fixed. Reviewers: qcolombet, chandlerc, hfinkel Reviewed By: hfinkel Subscribers: hfinkel, llvm-commits Differential Revision: http://reviews.llvm.org/D9250 llvm-svn: 236584
2015-05-06 18:19:14 +08:00
%vecext = extractelement <8 x i16> %foo, i32 7
store i16 %vecext, i16* %dst, align 1
ret void
}
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
define void @extract_i32_0(i32* nocapture %dst, <4 x i32> %foo) nounwind {
; SSE-X32-LABEL: extract_i32_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE-X32-NEXT: movss %xmm0, (%eax)
; SSE-X32-NEXT: retl
;
; SSE-X64-LABEL: extract_i32_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE-X64-NEXT: movss %xmm0, (%rdi)
; SSE-X64-NEXT: retq
;
; AVX-X32-LABEL: extract_i32_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX-X32-NEXT: vmovss %xmm0, (%eax)
; AVX-X32-NEXT: retl
;
; AVX-X64-LABEL: extract_i32_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X64-NEXT: vmovss %xmm0, (%rdi)
; AVX-X64-NEXT: retq
%vecext = extractelement <4 x i32> %foo, i32 0
store i32 %vecext, i32* %dst, align 1
ret void
}
define void @extract_i32_3(i32* nocapture %dst, <4 x i32> %foo) nounwind {
; SSE2-X32-LABEL: extract_i32_3:
[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-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE2-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE2-X32-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; SSE2-X32-NEXT: movd %xmm0, (%eax)
; SSE2-X32-NEXT: retl
;
; SSE2-X64-LABEL: extract_i32_3:
[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-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE2-X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; SSE2-X64-NEXT: movd %xmm0, (%rdi)
; SSE2-X64-NEXT: retq
;
; SSE41-X32-LABEL: extract_i32_3:
[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-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE41-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
[X86][SSE] Add extractps/pextrd equivalence to domain tables Differential Revision: https://reviews.llvm.org/D39135 llvm-svn: 316274
2017-10-22 04:19:48 +08:00
; SSE41-X32-NEXT: extractps $3, %xmm0, (%eax)
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE41-X32-NEXT: retl
;
; SSE41-X64-LABEL: extract_i32_3:
[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-X64: # %bb.0:
[X86][SSE] Add extractps/pextrd equivalence to domain tables Differential Revision: https://reviews.llvm.org/D39135 llvm-svn: 316274
2017-10-22 04:19:48 +08:00
; SSE41-X64-NEXT: extractps $3, %xmm0, (%rdi)
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE41-X64-NEXT: retq
;
; AVX-X32-LABEL: extract_i32_3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
[X86][SSE] Add extractps/pextrd equivalence to domain tables Differential Revision: https://reviews.llvm.org/D39135 llvm-svn: 316274
2017-10-22 04:19:48 +08:00
; AVX-X32-NEXT: vextractps $3, %xmm0, (%eax)
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X32-NEXT: retl
;
; AVX-X64-LABEL: extract_i32_3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X64: # %bb.0:
[X86][SSE] Add extractps/pextrd equivalence to domain tables Differential Revision: https://reviews.llvm.org/D39135 llvm-svn: 316274
2017-10-22 04:19:48 +08:00
; AVX-X64-NEXT: vextractps $3, %xmm0, (%rdi)
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X64-NEXT: retq
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
;
; SSE-F128-LABEL: extract_i32_3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-F128: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE-F128-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; SSE-F128-NEXT: movd %xmm0, (%rdi)
; SSE-F128-NEXT: retq
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
%vecext = extractelement <4 x i32> %foo, i32 3
store i32 %vecext, i32* %dst, align 1
ret void
}
define void @extract_i64_0(i64* nocapture %dst, <2 x i64> %foo) nounwind {
; SSE-X32-LABEL: extract_i64_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE-X32-NEXT: movlps %xmm0, (%eax)
; SSE-X32-NEXT: retl
;
; SSE-X64-LABEL: extract_i64_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE-X64-NEXT: movlps %xmm0, (%rdi)
; SSE-X64-NEXT: retq
;
; AVX-X32-LABEL: extract_i64_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX-X32-NEXT: vmovlps %xmm0, (%eax)
; AVX-X32-NEXT: retl
;
; AVX-X64-LABEL: extract_i64_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X64-NEXT: vmovlps %xmm0, (%rdi)
; AVX-X64-NEXT: retq
%vecext = extractelement <2 x i64> %foo, i32 0
store i64 %vecext, i64* %dst, align 1
ret void
}
define void @extract_i64_1(i64* nocapture %dst, <2 x i64> %foo) nounwind {
; SSE-X32-LABEL: extract_i64_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
; SSE-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
[X86][SSE] Attempt to combine 64-bit and 32-bit shuffles to unary shuffles before bit shifts We are combining shuffles to bit shifts before unary permutes, which means we can't fold loads plus the destination register is destructive llvm-svn: 306978
2017-07-02 22:16:25 +08:00
; SSE-X32-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE-X32-NEXT: movq %xmm0, (%eax)
; SSE-X32-NEXT: retl
;
; SSE2-X64-LABEL: extract_i64_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-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE2-X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE2-X64-NEXT: movq %xmm0, (%rdi)
; SSE2-X64-NEXT: retq
;
; SSE41-X64-LABEL: extract_i64_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-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; SSE41-X64-NEXT: pextrq $1, %xmm0, (%rdi)
; SSE41-X64-NEXT: retq
;
; AVX-X32-LABEL: extract_i64_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
; AVX-X32: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
[X86] Teach execution domain fixing to convert between VPERMILPS and VPSHUFD. llvm-svn: 313507
2017-09-18 11:29:47 +08:00
; AVX-X32-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,3,0,1]
; AVX-X32-NEXT: vmovlps %xmm0, (%eax)
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X32-NEXT: retl
;
; AVX-X64-LABEL: extract_i64_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
; AVX-X64: # %bb.0:
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; AVX-X64-NEXT: vpextrq $1, %xmm0, (%rdi)
; AVX-X64-NEXT: retq
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
;
; SSE-F128-LABEL: extract_i64_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
; SSE-F128: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE-F128-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE-F128-NEXT: movq %xmm0, (%rdi)
; SSE-F128-NEXT: retq
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
%vecext = extractelement <2 x i64> %foo, i32 1
store i64 %vecext, i64* %dst, align 1
ret void
}
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
define void @extract_f32_0(float* nocapture %dst, <4 x float> %foo) nounwind {
; SSE-X32-LABEL: extract_f32_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-X32: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE-X32-NEXT: movss %xmm0, (%eax)
; SSE-X32-NEXT: retl
;
; SSE-X64-LABEL: extract_f32_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-X64: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; SSE-X64-NEXT: movss %xmm0, (%rdi)
; SSE-X64-NEXT: retq
;
; AVX-X32-LABEL: extract_f32_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X32: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX-X32-NEXT: vmovss %xmm0, (%eax)
; AVX-X32-NEXT: retl
;
; AVX-X64-LABEL: extract_f32_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X64: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; AVX-X64-NEXT: vmovss %xmm0, (%rdi)
; AVX-X64-NEXT: retq
%vecext = extractelement <4 x float> %foo, i32 0
store float %vecext, float* %dst, align 1
ret void
}
define void @extract_f32_3(float* nocapture %dst, <4 x float> %foo) nounwind {
; SSE2-X32-LABEL: extract_f32_3:
[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-X32: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; SSE2-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE2-X32-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; SSE2-X32-NEXT: movss %xmm0, (%eax)
; SSE2-X32-NEXT: retl
;
; SSE2-X64-LABEL: extract_f32_3:
[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-X64: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; SSE2-X64-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; SSE2-X64-NEXT: movss %xmm0, (%rdi)
; SSE2-X64-NEXT: retq
;
; SSE41-X32-LABEL: extract_f32_3:
[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-X32: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; SSE41-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE41-X32-NEXT: extractps $3, %xmm0, (%eax)
; SSE41-X32-NEXT: retl
;
; SSE41-X64-LABEL: extract_f32_3:
[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-X64: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; SSE41-X64-NEXT: extractps $3, %xmm0, (%rdi)
; SSE41-X64-NEXT: retq
;
; AVX-X32-LABEL: extract_f32_3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X32: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX-X32-NEXT: vextractps $3, %xmm0, (%eax)
; AVX-X32-NEXT: retl
;
; AVX-X64-LABEL: extract_f32_3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X64: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; AVX-X64-NEXT: vextractps $3, %xmm0, (%rdi)
; AVX-X64-NEXT: retq
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
;
; SSE-F128-LABEL: extract_f32_3:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-F128: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE-F128-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; SSE-F128-NEXT: movss %xmm0, (%rdi)
; SSE-F128-NEXT: retq
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
%vecext = extractelement <4 x float> %foo, i32 3
store float %vecext, float* %dst, align 1
ret void
}
define void @extract_f64_0(double* nocapture %dst, <2 x double> %foo) nounwind {
; SSE-X32-LABEL: extract_f64_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-X32: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE-X32-NEXT: movlps %xmm0, (%eax)
; SSE-X32-NEXT: retl
;
; SSE-X64-LABEL: extract_f64_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-X64: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; SSE-X64-NEXT: movlps %xmm0, (%rdi)
; SSE-X64-NEXT: retq
;
; AVX-X32-LABEL: extract_f64_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X32: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX-X32-NEXT: vmovlps %xmm0, (%eax)
; AVX-X32-NEXT: retl
;
; AVX-X64-LABEL: extract_f64_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X64: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; AVX-X64-NEXT: vmovlps %xmm0, (%rdi)
; AVX-X64-NEXT: retq
%vecext = extractelement <2 x double> %foo, i32 0
store double %vecext, double* %dst, align 1
ret void
}
define void @extract_f64_1(double* nocapture %dst, <2 x double> %foo) nounwind {
; SSE-X32-LABEL: extract_f64_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
; SSE-X32: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE-X32-NEXT: movhpd %xmm0, (%eax)
; SSE-X32-NEXT: retl
;
; SSE-X64-LABEL: extract_f64_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
; SSE-X64: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; SSE-X64-NEXT: movhpd %xmm0, (%rdi)
; SSE-X64-NEXT: retq
;
; AVX-X32-LABEL: extract_f64_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
; AVX-X32: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX-X32-NEXT: vmovhpd %xmm0, (%eax)
; AVX-X32-NEXT: retl
;
; AVX-X64-LABEL: extract_f64_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
; AVX-X64: # %bb.0:
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; AVX-X64-NEXT: vmovhpd %xmm0, (%rdi)
; AVX-X64-NEXT: retq
%vecext = extractelement <2 x double> %foo, i32 1
store double %vecext, double* %dst, align 1
ret void
}
[X86] Keep EXTRACT_VECTOR_ELT result type as f128 for Android x86_64. Android x86_64 target uses f128 type and stores f128 values in %xmm* registers. SoftenFloatRes_EXTRACT_VECTOR_ELT should not convert result value from f128 to i128. Differential Revision: http://reviews.llvm.org/D32102 llvm-svn: 300583
2017-04-19 04:15:18 +08:00
define void @extract_f128_0(fp128* nocapture %dst, <2 x fp128> %foo) nounwind {
[X86][DAG] Switch X86 Target to post-legalized store merge Move store merge to happen after intrinsic lowering to allow lowered stores to be merged. Some regressions due in MergeConsecutiveStores to missing insert_subvector that are addressed in follow up patch. Reviewers: craig.topper, efriedma, RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D34559 llvm-svn: 310710
2017-08-11 21:21:35 +08:00
; SSE-X32-LABEL: extract_f128_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-X32: # %bb.0:
[X86][DAG] Switch X86 Target to post-legalized store merge Move store merge to happen after intrinsic lowering to allow lowered stores to be merged. Some regressions due in MergeConsecutiveStores to missing insert_subvector that are addressed in follow up patch. Reviewers: craig.topper, efriedma, RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D34559 llvm-svn: 310710
2017-08-11 21:21:35 +08:00
; SSE-X32-NEXT: pushl %edi
; SSE-X32-NEXT: pushl %esi
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %edx
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %esi
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %edi
; SSE-X32-NEXT: movl %esi, 12(%edi)
; SSE-X32-NEXT: movl %edx, 8(%edi)
; SSE-X32-NEXT: movl %ecx, 4(%edi)
; SSE-X32-NEXT: movl %eax, (%edi)
; SSE-X32-NEXT: popl %esi
; SSE-X32-NEXT: popl %edi
; SSE-X32-NEXT: retl
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
;
; SSE2-X64-LABEL: extract_f128_0:
[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-X64: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE2-X64-NEXT: movq %rdx, 8(%rdi)
; SSE2-X64-NEXT: movq %rsi, (%rdi)
; SSE2-X64-NEXT: retq
;
; SSE41-X64-LABEL: extract_f128_0:
[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-X64: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE41-X64-NEXT: movq %rdx, 8(%rdi)
; SSE41-X64-NEXT: movq %rsi, (%rdi)
; SSE41-X64-NEXT: retq
;
[X86][DAG] Switch X86 Target to post-legalized store merge Move store merge to happen after intrinsic lowering to allow lowered stores to be merged. Some regressions due in MergeConsecutiveStores to missing insert_subvector that are addressed in follow up patch. Reviewers: craig.topper, efriedma, RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D34559 llvm-svn: 310710
2017-08-11 21:21:35 +08:00
; AVX-X32-LABEL: extract_f128_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X32: # %bb.0:
[X86][DAG] Switch X86 Target to post-legalized store merge Move store merge to happen after intrinsic lowering to allow lowered stores to be merged. Some regressions due in MergeConsecutiveStores to missing insert_subvector that are addressed in follow up patch. Reviewers: craig.topper, efriedma, RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D34559 llvm-svn: 310710
2017-08-11 21:21:35 +08:00
; AVX-X32-NEXT: vmovups {{[0-9]+}}(%esp), %xmm0
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX-X32-NEXT: vmovups %xmm0, (%eax)
; AVX-X32-NEXT: retl
;
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; AVX-X64-LABEL: extract_f128_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX-X64: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; AVX-X64-NEXT: movq %rdx, 8(%rdi)
; AVX-X64-NEXT: movq %rsi, (%rdi)
; AVX-X64-NEXT: retq
;
[X86] Keep EXTRACT_VECTOR_ELT result type as f128 for Android x86_64. Android x86_64 target uses f128 type and stores f128 values in %xmm* registers. SoftenFloatRes_EXTRACT_VECTOR_ELT should not convert result value from f128 to i128. Differential Revision: http://reviews.llvm.org/D32102 llvm-svn: 300583
2017-04-19 04:15:18 +08:00
; SSE-F128-LABEL: extract_f128_0:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSE-F128: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE-F128-NEXT: movaps %xmm0, (%rdi)
[X86] Keep EXTRACT_VECTOR_ELT result type as f128 for Android x86_64. Android x86_64 target uses f128 type and stores f128 values in %xmm* registers. SoftenFloatRes_EXTRACT_VECTOR_ELT should not convert result value from f128 to i128. Differential Revision: http://reviews.llvm.org/D32102 llvm-svn: 300583
2017-04-19 04:15:18 +08:00
; SSE-F128-NEXT: retq
%vecext = extractelement <2 x fp128> %foo, i32 0
store fp128 %vecext, fp128* %dst, align 1
ret void
}
define void @extract_f128_1(fp128* nocapture %dst, <2 x fp128> %foo) nounwind {
[X86][DAG] Switch X86 Target to post-legalized store merge Move store merge to happen after intrinsic lowering to allow lowered stores to be merged. Some regressions due in MergeConsecutiveStores to missing insert_subvector that are addressed in follow up patch. Reviewers: craig.topper, efriedma, RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D34559 llvm-svn: 310710
2017-08-11 21:21:35 +08:00
; SSE-X32-LABEL: extract_f128_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
; SSE-X32: # %bb.0:
[X86][DAG] Switch X86 Target to post-legalized store merge Move store merge to happen after intrinsic lowering to allow lowered stores to be merged. Some regressions due in MergeConsecutiveStores to missing insert_subvector that are addressed in follow up patch. Reviewers: craig.topper, efriedma, RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D34559 llvm-svn: 310710
2017-08-11 21:21:35 +08:00
; SSE-X32-NEXT: pushl %edi
; SSE-X32-NEXT: pushl %esi
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %edx
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %esi
; SSE-X32-NEXT: movl {{[0-9]+}}(%esp), %edi
; SSE-X32-NEXT: movl %esi, 12(%edi)
; SSE-X32-NEXT: movl %edx, 8(%edi)
; SSE-X32-NEXT: movl %ecx, 4(%edi)
; SSE-X32-NEXT: movl %eax, (%edi)
; SSE-X32-NEXT: popl %esi
; SSE-X32-NEXT: popl %edi
; SSE-X32-NEXT: retl
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
;
; SSE2-X64-LABEL: extract_f128_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-X64: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE2-X64-NEXT: movq %r8, 8(%rdi)
; SSE2-X64-NEXT: movq %rcx, (%rdi)
; SSE2-X64-NEXT: retq
;
; SSE41-X64-LABEL: extract_f128_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-X64: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE41-X64-NEXT: movq %r8, 8(%rdi)
; SSE41-X64-NEXT: movq %rcx, (%rdi)
; SSE41-X64-NEXT: retq
;
[X86][DAG] Switch X86 Target to post-legalized store merge Move store merge to happen after intrinsic lowering to allow lowered stores to be merged. Some regressions due in MergeConsecutiveStores to missing insert_subvector that are addressed in follow up patch. Reviewers: craig.topper, efriedma, RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D34559 llvm-svn: 310710
2017-08-11 21:21:35 +08:00
; AVX-X32-LABEL: extract_f128_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
; AVX-X32: # %bb.0:
[X86][DAG] Switch X86 Target to post-legalized store merge Move store merge to happen after intrinsic lowering to allow lowered stores to be merged. Some regressions due in MergeConsecutiveStores to missing insert_subvector that are addressed in follow up patch. Reviewers: craig.topper, efriedma, RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D34559 llvm-svn: 310710
2017-08-11 21:21:35 +08:00
; AVX-X32-NEXT: vmovups {{[0-9]+}}(%esp), %xmm0
; AVX-X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; AVX-X32-NEXT: vmovups %xmm0, (%eax)
; AVX-X32-NEXT: retl
;
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; AVX-X64-LABEL: extract_f128_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
; AVX-X64: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; AVX-X64-NEXT: movq %r8, 8(%rdi)
; AVX-X64-NEXT: movq %rcx, (%rdi)
; AVX-X64-NEXT: retq
;
[X86] Keep EXTRACT_VECTOR_ELT result type as f128 for Android x86_64. Android x86_64 target uses f128 type and stores f128 values in %xmm* registers. SoftenFloatRes_EXTRACT_VECTOR_ELT should not convert result value from f128 to i128. Differential Revision: http://reviews.llvm.org/D32102 llvm-svn: 300583
2017-04-19 04:15:18 +08:00
; SSE-F128-LABEL: extract_f128_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
; SSE-F128: # %bb.0:
Regenerate extract-store.ll tests llvm-svn: 306131
2017-06-24 01:19:44 +08:00
; SSE-F128-NEXT: movaps %xmm1, (%rdi)
[X86] Keep EXTRACT_VECTOR_ELT result type as f128 for Android x86_64. Android x86_64 target uses f128 type and stores f128 values in %xmm* registers. SoftenFloatRes_EXTRACT_VECTOR_ELT should not convert result value from f128 to i128. Differential Revision: http://reviews.llvm.org/D32102 llvm-svn: 300583
2017-04-19 04:15:18 +08:00
; SSE-F128-NEXT: retq
%vecext = extractelement <2 x fp128> %foo, i32 1
store fp128 %vecext, fp128* %dst, align 1
ret void
}
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
define void @extract_i8_undef(i8* nocapture %dst, <16 x i8> %foo) nounwind {
; X32-LABEL: extract_i8_undef:
[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 more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; X32-NEXT: retl
;
; X64-LABEL: extract_i8_undef:
[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 more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; X64-NEXT: retq
SelectionDAG: Handle out-of-bounds index in extract vector element Summary: This patch correctly handles undef case of EXTRACT_VECTOR_ELT node where the element index is constant and not less than vector size. Test Plan: CodeGen for X86 test included. Also one incorrect regression test fixed. Reviewers: qcolombet, chandlerc, hfinkel Reviewed By: hfinkel Subscribers: hfinkel, llvm-commits Differential Revision: http://reviews.llvm.org/D9250 llvm-svn: 236584
2015-05-06 18:19:14 +08:00
%vecext = extractelement <16 x i8> %foo, i32 16 ; undef
store i8 %vecext, i8* %dst, align 1
ret void
}
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
define void @extract_i16_undef(i16* nocapture %dst, <8 x i16> %foo) nounwind {
; X32-LABEL: extract_i16_undef:
[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 more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; X32-NEXT: retl
;
; X64-LABEL: extract_i16_undef:
[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 more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; X64-NEXT: retq
SelectionDAG: Handle out-of-bounds index in extract vector element Summary: This patch correctly handles undef case of EXTRACT_VECTOR_ELT node where the element index is constant and not less than vector size. Test Plan: CodeGen for X86 test included. Also one incorrect regression test fixed. Reviewers: qcolombet, chandlerc, hfinkel Reviewed By: hfinkel Subscribers: hfinkel, llvm-commits Differential Revision: http://reviews.llvm.org/D9250 llvm-svn: 236584
2015-05-06 18:19:14 +08:00
%vecext = extractelement <8 x i16> %foo, i32 9 ; undef
X86: Resolve a long standing FIXME and properly isel pextr[bw]. Generalize the AArch64 .td nodes for AssertZext and AssertSext. Use them to match the relevant pextr store instructions. The test widen_load-2.ll requires a slight change because with the stores gone, the remaining instructions are scheduled in a different order. Add test cases for SSE4 and AVX variants. Resolves rdar://13414672. Patch by Adam Nemet <anemet@apple.com>. llvm-svn: 200957
2014-02-07 08:16:33 +08:00
store i16 %vecext, i16* %dst, align 1
ret void
}
[X86][SSE] Add more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
define void @extract_i32_undef(i32* nocapture %dst, <4 x i32> %foo) nounwind {
; X32-LABEL: extract_i32_undef:
[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 more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; X32-NEXT: retl
;
; X64-LABEL: extract_i32_undef:
[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 more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; X64-NEXT: retq
%vecext = extractelement <4 x i32> %foo, i32 6 ; undef
store i32 %vecext, i32* %dst, align 1
ret void
}
define void @extract_i64_undef(i64* nocapture %dst, <2 x i64> %foo) nounwind {
; X32-LABEL: extract_i64_undef:
[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 more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; X32-NEXT: retl
;
; X64-LABEL: extract_i64_undef:
[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 more thorough extract to store tests Added v4i32 and v2i64 tests and test on i686 as well as x86_64. llvm-svn: 294946
2017-02-13 21:40:12 +08:00
; X64-NEXT: retq
%vecext = extractelement <2 x i64> %foo, i32 2 ; undef
store i64 %vecext, i64* %dst, align 1
ret void
}
[X86][SSE] Add v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
define void @extract_f32_undef(float* nocapture %dst, <4 x float> %foo) nounwind {
; X32-LABEL: extract_f32_undef:
[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 v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; X32-NEXT: retl
;
; X64-LABEL: extract_f32_undef:
[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 v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; X64-NEXT: retq
%vecext = extractelement <4 x float> %foo, i32 6 ; undef
store float %vecext, float* %dst, align 1
ret void
}
define void @extract_f64_undef(double* nocapture %dst, <2 x double> %foo) nounwind {
; X32-LABEL: extract_f64_undef:
[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 v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; X32-NEXT: retl
;
; X64-LABEL: extract_f64_undef:
[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 v4f32 and v2f64 extract to store tests llvm-svn: 294952
2017-02-13 22:20:13 +08:00
; X64-NEXT: retq
%vecext = extractelement <2 x double> %foo, i32 2 ; undef
store double %vecext, double* %dst, align 1
ret void
}
[X86] Keep EXTRACT_VECTOR_ELT result type as f128 for Android x86_64. Android x86_64 target uses f128 type and stores f128 values in %xmm* registers. SoftenFloatRes_EXTRACT_VECTOR_ELT should not convert result value from f128 to i128. Differential Revision: http://reviews.llvm.org/D32102 llvm-svn: 300583
2017-04-19 04:15:18 +08:00
define void @extract_f128_undef(fp128* nocapture %dst, <2 x fp128> %foo) nounwind {
; X32-LABEL: extract_f128_undef:
[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] Keep EXTRACT_VECTOR_ELT result type as f128 for Android x86_64. Android x86_64 target uses f128 type and stores f128 values in %xmm* registers. SoftenFloatRes_EXTRACT_VECTOR_ELT should not convert result value from f128 to i128. Differential Revision: http://reviews.llvm.org/D32102 llvm-svn: 300583
2017-04-19 04:15:18 +08:00
; X32-NEXT: retl
;
; X64-LABEL: extract_f128_undef:
[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] Keep EXTRACT_VECTOR_ELT result type as f128 for Android x86_64. Android x86_64 target uses f128 type and stores f128 values in %xmm* registers. SoftenFloatRes_EXTRACT_VECTOR_ELT should not convert result value from f128 to i128. Differential Revision: http://reviews.llvm.org/D32102 llvm-svn: 300583
2017-04-19 04:15:18 +08:00
; X64-NEXT: retq
%vecext = extractelement <2 x fp128> %foo, i32 2 ; undef
store fp128 %vecext, fp128* %dst, align 1
ret void
}