maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86] Add PR39921 HADD pairwise reduction test and AVX2 test coverage 

llvm-svn: 359409
This commit is contained in:
Simon Pilgrim 2019-04-28 21:04:47 +00:00
parent 85bacd0f95
commit 65f12f66f6
1 changed files with 107 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

129
llvm/test/CodeGen/X86/phaddsub.ll
View File

@ -1,8 +1,10 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+ssse3 | FileCheck %s --check-prefixes=SSSE3,SSSE3-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+ssse3,fast-hops | FileCheck %s --check-prefixes=SSSE3,SSSE3-FAST
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx,fast-hops | FileCheck %s --check-prefixes=AVX,AVX-FAST
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX-SLOW,AVX1,AVX1-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx,fast-hops | FileCheck %s --check-prefixes=AVX,AVX-FAST,AVX1,AVX1-FAST
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX-SLOW,AVX2,AVX2-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx2,fast-hops | FileCheck %s --check-prefixes=AVX,AVX-FAST,AVX2,AVX2-FAST
define <8 x i16> @phaddw1(<8 x i16> %x, <8 x i16> %y) {
; SSSE3-LABEL: phaddw1:
@ -473,17 +475,24 @@ define <4 x i32> @phaddd_single_source3(<4 x i32> %x) {
; SSSE3-FAST-NEXT: phaddd %xmm0, %xmm0
; SSSE3-FAST-NEXT: retq
;
; AVX-SLOW-LABEL: phaddd_single_source3:
; AVX-SLOW: # %bb.0:
; AVX-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,1,0,1]
; AVX-SLOW-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
; AVX-SLOW-NEXT: vpaddd %xmm0, %xmm1, %xmm0
; AVX-SLOW-NEXT: retq
; AVX1-SLOW-LABEL: phaddd_single_source3:
; AVX1-SLOW: # %bb.0:
; AVX1-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,1,0,1]
; AVX1-SLOW-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
; AVX1-SLOW-NEXT: vpaddd %xmm0, %xmm1, %xmm0
; AVX1-SLOW-NEXT: retq
;
; AVX-FAST-LABEL: phaddd_single_source3:
; AVX-FAST: # %bb.0:
; AVX-FAST-NEXT: vphaddd %xmm0, %xmm0, %xmm0
; AVX-FAST-NEXT: retq
;
; AVX2-SLOW-LABEL: phaddd_single_source3:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpbroadcastd %xmm0, %xmm1
; AVX2-SLOW-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
; AVX2-SLOW-NEXT: vpaddd %xmm0, %xmm1, %xmm0
; AVX2-SLOW-NEXT: retq
%l = shufflevector <4 x i32> %x, <4 x i32> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 undef>
%r = shufflevector <4 x i32> %x, <4 x i32> undef, <4 x i32> <i32 undef, i32 undef, i32 1, i32 undef>
%add = add <4 x i32> %l, %r
@ -564,19 +573,27 @@ define <4 x i32> @phaddd_single_source6(<4 x i32> %x) {
; SSSE3-FAST-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
; SSSE3-FAST-NEXT: retq
;
; AVX-SLOW-LABEL: phaddd_single_source6:
; AVX-SLOW: # %bb.0:
; AVX-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,1,0,1]
; AVX-SLOW-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
; AVX-SLOW-NEXT: vpaddd %xmm0, %xmm1, %xmm0
; AVX-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
; AVX-SLOW-NEXT: retq
; AVX1-SLOW-LABEL: phaddd_single_source6:
; AVX1-SLOW: # %bb.0:
; AVX1-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,1,0,1]
; AVX1-SLOW-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
; AVX1-SLOW-NEXT: vpaddd %xmm0, %xmm1, %xmm0
; AVX1-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
; AVX1-SLOW-NEXT: retq
;
; AVX-FAST-LABEL: phaddd_single_source6:
; AVX-FAST: # %bb.0:
; AVX-FAST-NEXT: vphaddd %xmm0, %xmm0, %xmm0
; AVX-FAST-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
; AVX-FAST-NEXT: retq
;
; AVX2-SLOW-LABEL: phaddd_single_source6:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpbroadcastd %xmm0, %xmm1
; AVX2-SLOW-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
; AVX2-SLOW-NEXT: vpaddd %xmm0, %xmm1, %xmm0
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
; AVX2-SLOW-NEXT: retq
%l = shufflevector <4 x i32> %x, <4 x i32> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 undef>
%r = shufflevector <4 x i32> %x, <4 x i32> undef, <4 x i32> <i32 undef, i32 undef, i32 1, i32 undef>
%add = add <4 x i32> %l, %r
@ -737,19 +754,27 @@ define <8 x i16> @phaddw_single_source6(<8 x i16> %x) {
; SSSE3-FAST-NEXT: psrldq {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
; SSSE3-FAST-NEXT: retq
;
; AVX-SLOW-LABEL: phaddw_single_source6:
; AVX-SLOW: # %bb.0:
; AVX-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,1,0,1]
; AVX-SLOW-NEXT: vpmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
; AVX-SLOW-NEXT: vpaddw %xmm0, %xmm1, %xmm0
; AVX-SLOW-NEXT: vpsrldq {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
; AVX-SLOW-NEXT: retq
; AVX1-SLOW-LABEL: phaddw_single_source6:
; AVX1-SLOW: # %bb.0:
; AVX1-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,1,0,1]
; AVX1-SLOW-NEXT: vpmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
; AVX1-SLOW-NEXT: vpaddw %xmm0, %xmm1, %xmm0
; AVX1-SLOW-NEXT: vpsrldq {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
; AVX1-SLOW-NEXT: retq
;
; AVX-FAST-LABEL: phaddw_single_source6:
; AVX-FAST: # %bb.0:
; AVX-FAST-NEXT: vphaddw %xmm0, %xmm0, %xmm0
; AVX-FAST-NEXT: vpsrldq {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
; AVX-FAST-NEXT: retq
;
; AVX2-SLOW-LABEL: phaddw_single_source6:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpbroadcastw %xmm0, %xmm1
; AVX2-SLOW-NEXT: vpmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
; AVX2-SLOW-NEXT: vpaddw %xmm0, %xmm1, %xmm0
; AVX2-SLOW-NEXT: vpsrldq {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
; AVX2-SLOW-NEXT: retq
%l = shufflevector <8 x i16> %x, <8 x i16> undef, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 0, i32 undef, i32 undef, i32 undef>
%r = shufflevector <8 x i16> %x, <8 x i16> undef, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 1, i32 undef, i32 undef, i32 undef>
%add = add <8 x i16> %l, %r
@ -757,6 +782,66 @@ define <8 x i16> @phaddw_single_source6(<8 x i16> %x) {
ret <8 x i16> %shuffle2
}
; PR39921
define i32 @pairwise_reduction_8i32(<8 x i32> %rdx) {
; SSSE3-SLOW-LABEL: pairwise_reduction_8i32:
; SSSE3-SLOW: # %bb.0:
; SSSE3-SLOW-NEXT: phaddd %xmm1, %xmm0
; SSSE3-SLOW-NEXT: pshufd {{.*#+}} xmm1 = xmm0[0,2,2,3]
; SSSE3-SLOW-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,3,2,3]
; SSSE3-SLOW-NEXT: paddd %xmm1, %xmm0
; SSSE3-SLOW-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
; SSSE3-SLOW-NEXT: paddd %xmm0, %xmm1
; SSSE3-SLOW-NEXT: movd %xmm1, %eax
; SSSE3-SLOW-NEXT: retq
;
; SSSE3-FAST-LABEL: pairwise_reduction_8i32:
; SSSE3-FAST: # %bb.0:
; SSSE3-FAST-NEXT: phaddd %xmm1, %xmm0
; SSSE3-FAST-NEXT: phaddd %xmm0, %xmm0
; SSSE3-FAST-NEXT: phaddd %xmm0, %xmm0
; SSSE3-FAST-NEXT: movd %xmm0, %eax
; SSSE3-FAST-NEXT: retq
;
; AVX-SLOW-LABEL: pairwise_reduction_8i32:
; AVX-SLOW: # %bb.0:
; AVX-SLOW-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX-SLOW-NEXT: vshufps {{.*#+}} xmm2 = xmm0[0,2],xmm1[0,2]
; AVX-SLOW-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
; AVX-SLOW-NEXT: vpaddd %xmm0, %xmm2, %xmm0
; AVX-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,2,2,3]
; AVX-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,3,2,3]
; AVX-SLOW-NEXT: vpaddd %xmm0, %xmm1, %xmm0
; AVX-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
; AVX-SLOW-NEXT: vpaddd %xmm1, %xmm0, %xmm0
; AVX-SLOW-NEXT: vmovd %xmm0, %eax
; AVX-SLOW-NEXT: vzeroupper
; AVX-SLOW-NEXT: retq
;
; AVX-FAST-LABEL: pairwise_reduction_8i32:
; AVX-FAST: # %bb.0:
; AVX-FAST-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX-FAST-NEXT: vshufps {{.*#+}} xmm2 = xmm0[0,2],xmm1[0,2]
; AVX-FAST-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
; AVX-FAST-NEXT: vpaddd %xmm0, %xmm2, %xmm0
; AVX-FAST-NEXT: vphaddd %xmm0, %xmm0, %xmm0
; AVX-FAST-NEXT: vphaddd %xmm0, %xmm0, %xmm0
; AVX-FAST-NEXT: vmovd %xmm0, %eax
; AVX-FAST-NEXT: vzeroupper
; AVX-FAST-NEXT: retq
%rdx.shuf.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6,i32 undef, i32 undef, i32 undef, i32 undef>
%rdx.shuf.0.1 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7,i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx = add <8 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1
%rdx.shuf.1.0 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef,<8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%rdx.shuf.1.1 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef,<8 x i32> <i32 1, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx8 = add <8 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1
%rdx.shuf.2.0 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef,<8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%rdx.shuf.2.1 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef,<8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1
%r = extractelement <8 x i32> %bin.rdx9, i32 0
ret i32 %r
}
define i32 @PR39936_v8i32(<8 x i32>) {
; SSSE3-SLOW-LABEL: PR39936_v8i32:
; SSSE3-SLOW: # %bb.0: