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/xop-ifma.ll

130 lines
5.1 KiB
LLVM
Raw Normal View History

[X86][XOP] Add tests for integer fused multiply add Tests showing missed opportunities to use XOP's integer fma instructions Some of these are pretty awkward to match as they often have implicit sext/trunc stages but many just ignore overflow bits which makes things pretty straightforward. llvm-svn: 292017
2017-01-14 21:07:22 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+xop | FileCheck %s --check-prefix=XOP --check-prefix=XOP-AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+xop | FileCheck %s --check-prefix=XOP --check-prefix=XOP-AVX2
define <8 x i16> @test_mul_v8i16_add_v8i16(<8 x i16> %a0, <8 x i16> %a1, <8 x i16> %a2) {
; XOP-LABEL: test_mul_v8i16_add_v8i16:
[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
; XOP: # %bb.0:
[X86][XOP] Added support for VPMACSWW/VPMACSDD 'lossy' IFMA patterns VPMACSWW/VPMACSDD act as add( mul( x, y ), z ) - ignoring any upper bits from both the multiply and add stages llvm-svn: 292019
2017-01-15 01:13:52 +08:00
; XOP-NEXT: vpmacsww %xmm2, %xmm1, %xmm0, %xmm0
[X86][XOP] Add tests for integer fused multiply add Tests showing missed opportunities to use XOP's integer fma instructions Some of these are pretty awkward to match as they often have implicit sext/trunc stages but many just ignore overflow bits which makes things pretty straightforward. llvm-svn: 292017
2017-01-14 21:07:22 +08:00
; XOP-NEXT: retq
%1 = mul <8 x i16> %a0, %a1
%2 = add <8 x i16> %1, %a2
ret <8 x i16> %2
}
define <16 x i16> @test_mul_v16i16_add_v16i16(<16 x i16> %a0, <16 x i16> %a1, <16 x i16> %a2) {
; XOP-AVX1-LABEL: test_mul_v16i16_add_v16i16:
[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
; XOP-AVX1: # %bb.0:
[X86][XOP] Added support for VPMACSWW/VPMACSDD 'lossy' IFMA patterns VPMACSWW/VPMACSDD act as add( mul( x, y ), z ) - ignoring any upper bits from both the multiply and add stages llvm-svn: 292019
2017-01-15 01:13:52 +08:00
; XOP-AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; XOP-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
; XOP-AVX1-NEXT: vextractf128 $1, %ymm2, %xmm5
; XOP-AVX1-NEXT: vpmacsww %xmm5, %xmm3, %xmm4, %xmm3
; XOP-AVX1-NEXT: vpmacsww %xmm2, %xmm1, %xmm0, %xmm0
; XOP-AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0
[X86][XOP] Add tests for integer fused multiply add Tests showing missed opportunities to use XOP's integer fma instructions Some of these are pretty awkward to match as they often have implicit sext/trunc stages but many just ignore overflow bits which makes things pretty straightforward. llvm-svn: 292017
2017-01-14 21:07:22 +08:00
; XOP-AVX1-NEXT: retq
;
; XOP-AVX2-LABEL: test_mul_v16i16_add_v16i16:
[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
; XOP-AVX2: # %bb.0:
[X86][XOP] Add tests for integer fused multiply add Tests showing missed opportunities to use XOP's integer fma instructions Some of these are pretty awkward to match as they often have implicit sext/trunc stages but many just ignore overflow bits which makes things pretty straightforward. llvm-svn: 292017
2017-01-14 21:07:22 +08:00
; XOP-AVX2-NEXT: vpmullw %ymm1, %ymm0, %ymm0
; XOP-AVX2-NEXT: vpaddw %ymm0, %ymm2, %ymm0
; XOP-AVX2-NEXT: retq
%1 = mul <16 x i16> %a0, %a1
%2 = add <16 x i16> %a2, %1
ret <16 x i16> %2
}
define <4 x i32> @test_mul_v4i32_add_v4i32(<4 x i32> %a0, <4 x i32> %a1, <4 x i32> %a2) {
; XOP-LABEL: test_mul_v4i32_add_v4i32:
[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
; XOP: # %bb.0:
[X86][XOP] Added support for VPMACSWW/VPMACSDD 'lossy' IFMA patterns VPMACSWW/VPMACSDD act as add( mul( x, y ), z ) - ignoring any upper bits from both the multiply and add stages llvm-svn: 292019
2017-01-15 01:13:52 +08:00
; XOP-NEXT: vpmacsdd %xmm2, %xmm1, %xmm0, %xmm0
[X86][XOP] Add tests for integer fused multiply add Tests showing missed opportunities to use XOP's integer fma instructions Some of these are pretty awkward to match as they often have implicit sext/trunc stages but many just ignore overflow bits which makes things pretty straightforward. llvm-svn: 292017
2017-01-14 21:07:22 +08:00
; XOP-NEXT: retq
%1 = mul <4 x i32> %a0, %a1
%2 = add <4 x i32> %1, %a2
ret <4 x i32> %2
}
define <8 x i32> @test_mul_v8i32_add_v8i32(<8 x i32> %a0, <8 x i32> %a1, <8 x i32> %a2) {
; XOP-AVX1-LABEL: test_mul_v8i32_add_v8i32:
[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
; XOP-AVX1: # %bb.0:
[X86][XOP] Added support for VPMACSWW/VPMACSDD 'lossy' IFMA patterns VPMACSWW/VPMACSDD act as add( mul( x, y ), z ) - ignoring any upper bits from both the multiply and add stages llvm-svn: 292019
2017-01-15 01:13:52 +08:00
; XOP-AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; XOP-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
; XOP-AVX1-NEXT: vextractf128 $1, %ymm2, %xmm5
; XOP-AVX1-NEXT: vpmacsdd %xmm5, %xmm3, %xmm4, %xmm3
; XOP-AVX1-NEXT: vpmacsdd %xmm2, %xmm1, %xmm0, %xmm0
; XOP-AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0
[X86][XOP] Add tests for integer fused multiply add Tests showing missed opportunities to use XOP's integer fma instructions Some of these are pretty awkward to match as they often have implicit sext/trunc stages but many just ignore overflow bits which makes things pretty straightforward. llvm-svn: 292017
2017-01-14 21:07:22 +08:00
; XOP-AVX1-NEXT: retq
;
; XOP-AVX2-LABEL: test_mul_v8i32_add_v8i32:
[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
; XOP-AVX2: # %bb.0:
[X86][XOP] Add tests for integer fused multiply add Tests showing missed opportunities to use XOP's integer fma instructions Some of these are pretty awkward to match as they often have implicit sext/trunc stages but many just ignore overflow bits which makes things pretty straightforward. llvm-svn: 292017
2017-01-14 21:07:22 +08:00
; XOP-AVX2-NEXT: vpmulld %ymm1, %ymm0, %ymm0
; XOP-AVX2-NEXT: vpaddd %ymm0, %ymm2, %ymm0
; XOP-AVX2-NEXT: retq
%1 = mul <8 x i32> %a0, %a1
%2 = add <8 x i32> %a2, %1
ret <8 x i32> %2
}
define <4 x i64> @test_mulx_v4i32_add_v4i64(<4 x i32> %a0, <4 x i32> %a1, <4 x i64> %a2) {
; XOP-AVX1-LABEL: test_mulx_v4i32_add_v4i64:
[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
; XOP-AVX1: # %bb.0:
[X86][XOP] Added support for VPMACSDQH/VPMACSDQL 'extension' IFMA patterns VPMACSDQH/VPMACSDQL act as VPADDQ( VPMULDQ( x, y ), z ) - multiply+extending either the odd/even 4i32 input elements and adding to v2i64 accumulator llvm-svn: 292020
2017-01-15 02:08:54 +08:00
; XOP-AVX1-NEXT: vpmovsxdq %xmm0, %xmm3
; XOP-AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
[X86][XOP] Add tests for integer fused multiply add Tests showing missed opportunities to use XOP's integer fma instructions Some of these are pretty awkward to match as they often have implicit sext/trunc stages but many just ignore overflow bits which makes things pretty straightforward. llvm-svn: 292017
2017-01-14 21:07:22 +08:00
; XOP-AVX1-NEXT: vpmovsxdq %xmm0, %xmm0
[X86][XOP] Added support for VPMACSDQH/VPMACSDQL 'extension' IFMA patterns VPMACSDQH/VPMACSDQL act as VPADDQ( VPMULDQ( x, y ), z ) - multiply+extending either the odd/even 4i32 input elements and adding to v2i64 accumulator llvm-svn: 292020
2017-01-15 02:08:54 +08:00
; XOP-AVX1-NEXT: vpmovsxdq %xmm1, %xmm4
; XOP-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
[X86][XOP] Add tests for integer fused multiply add Tests showing missed opportunities to use XOP's integer fma instructions Some of these are pretty awkward to match as they often have implicit sext/trunc stages but many just ignore overflow bits which makes things pretty straightforward. llvm-svn: 292017
2017-01-14 21:07:22 +08:00
; XOP-AVX1-NEXT: vpmovsxdq %xmm1, %xmm1
[X86][XOP] Added support for VPMACSDQH/VPMACSDQL 'extension' IFMA patterns VPMACSDQH/VPMACSDQL act as VPADDQ( VPMULDQ( x, y ), z ) - multiply+extending either the odd/even 4i32 input elements and adding to v2i64 accumulator llvm-svn: 292020
2017-01-15 02:08:54 +08:00
; XOP-AVX1-NEXT: vextractf128 $1, %ymm2, %xmm5
; XOP-AVX1-NEXT: vpmacsdql %xmm5, %xmm1, %xmm0, %xmm0
; XOP-AVX1-NEXT: vpmacsdql %xmm2, %xmm4, %xmm3, %xmm1
; XOP-AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
[X86][XOP] Add tests for integer fused multiply add Tests showing missed opportunities to use XOP's integer fma instructions Some of these are pretty awkward to match as they often have implicit sext/trunc stages but many just ignore overflow bits which makes things pretty straightforward. llvm-svn: 292017
2017-01-14 21:07:22 +08:00
; XOP-AVX1-NEXT: retq
;
; XOP-AVX2-LABEL: test_mulx_v4i32_add_v4i64:
[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
; XOP-AVX2: # %bb.0:
[X86] Combine vXi64 multiplies to MULDQ/MULUDQ during DAG combine instead of lowering. Previously we used a custom lowering for this because of the AVX1 splitting requirement. But we can do the split during DAG combine if we check the types and subtarget llvm-svn: 329510
2018-04-08 03:09:52 +08:00
; XOP-AVX2-NEXT: vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; XOP-AVX2-NEXT: vpmovzxdq {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
[X86][XOP] Add tests for integer fused multiply add Tests showing missed opportunities to use XOP's integer fma instructions Some of these are pretty awkward to match as they often have implicit sext/trunc stages but many just ignore overflow bits which makes things pretty straightforward. llvm-svn: 292017
2017-01-14 21:07:22 +08:00
; XOP-AVX2-NEXT: vpmuldq %ymm1, %ymm0, %ymm0
; XOP-AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0
; XOP-AVX2-NEXT: retq
%1 = sext <4 x i32> %a0 to <4 x i64>
%2 = sext <4 x i32> %a1 to <4 x i64>
%3 = mul <4 x i64> %1, %2
%4 = add <4 x i64> %3, %a2
ret <4 x i64> %4
}
define <2 x i64> @test_pmuldq_lo_v4i32_add_v2i64(<4 x i32> %a0, <4 x i32> %a1, <2 x i64> %a2) {
; XOP-LABEL: test_pmuldq_lo_v4i32_add_v2i64:
[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
; XOP: # %bb.0:
[X86][XOP] Added support for VPMACSDQH/VPMACSDQL 'extension' IFMA patterns VPMACSDQH/VPMACSDQL act as VPADDQ( VPMULDQ( x, y ), z ) - multiply+extending either the odd/even 4i32 input elements and adding to v2i64 accumulator llvm-svn: 292020
2017-01-15 02:08:54 +08:00
; XOP-NEXT: vpmacsdql %xmm2, %xmm1, %xmm0, %xmm0
[X86][XOP] Add tests for integer fused multiply add Tests showing missed opportunities to use XOP's integer fma instructions Some of these are pretty awkward to match as they often have implicit sext/trunc stages but many just ignore overflow bits which makes things pretty straightforward. llvm-svn: 292017
2017-01-14 21:07:22 +08:00
; XOP-NEXT: retq
%1 = call <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32> %a0, <4 x i32> %a1)
%2 = add <2 x i64> %1, %a2
ret <2 x i64> %2
}
define <2 x i64> @test_pmuldq_hi_v4i32_add_v2i64(<4 x i32> %a0, <4 x i32> %a1, <2 x i64> %a2) {
; XOP-LABEL: test_pmuldq_hi_v4i32_add_v2i64:
[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
; XOP: # %bb.0:
[X86][XOP] Added support for VPMACSDQH/VPMACSDQL 'extension' IFMA patterns VPMACSDQH/VPMACSDQL act as VPADDQ( VPMULDQ( x, y ), z ) - multiply+extending either the odd/even 4i32 input elements and adding to v2i64 accumulator llvm-svn: 292020
2017-01-15 02:08:54 +08:00
; XOP-NEXT: vpmacsdqh %xmm2, %xmm1, %xmm0, %xmm0
[X86][XOP] Add tests for integer fused multiply add Tests showing missed opportunities to use XOP's integer fma instructions Some of these are pretty awkward to match as they often have implicit sext/trunc stages but many just ignore overflow bits which makes things pretty straightforward. llvm-svn: 292017
2017-01-14 21:07:22 +08:00
; XOP-NEXT: retq
%1 = shufflevector <4 x i32> %a0, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 3, i32 undef>
%2 = shufflevector <4 x i32> %a1, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 3, i32 undef>
%3 = call <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32> %1, <4 x i32> %2)
%4 = add <2 x i64> %3, %a2
ret <2 x i64> %4
}
define <4 x i32> @test_pmaddwd_v8i16_add_v4i32(<8 x i16> %a0, <8 x i16> %a1, <4 x i32> %a2) {
; XOP-LABEL: test_pmaddwd_v8i16_add_v4i32:
[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
; XOP: # %bb.0:
[X86][XOP] Added support for VPMADCSWD 'extend+hadd' IFMA patterns VPMADCSWD act as VPADDD( VPMADDWD( x, y ), z ) - multiply+extend+hadd and add to v4i32 accumulator llvm-svn: 292021
2017-01-15 02:52:13 +08:00
; XOP-NEXT: vpmadcswd %xmm2, %xmm1, %xmm0, %xmm0
[X86][XOP] Add tests for integer fused multiply add Tests showing missed opportunities to use XOP's integer fma instructions Some of these are pretty awkward to match as they often have implicit sext/trunc stages but many just ignore overflow bits which makes things pretty straightforward. llvm-svn: 292017
2017-01-14 21:07:22 +08:00
; XOP-NEXT: retq
%1 = call <4 x i32> @llvm.x86.sse2.pmadd.wd(<8 x i16> %a0, <8 x i16> %a1)
%2 = add <4 x i32> %1, %a2
ret <4 x i32> %2
}
declare <4 x i32> @llvm.x86.sse2.pmadd.wd(<8 x i16>, <8 x i16>) nounwind readnone
declare <2 x i64> @llvm.x86.sse41.pmuldq(<4 x i32>, <4 x i32>) nounwind readnone