[x86] Add some tests for specific patterns of lane-flips combined with

in-lane shuffles that aren't always handled well by the current vector
shuffle lowering.

No functionality change yet, that will follow in a subsequent commit.

llvm-svn: 221938
This commit is contained in:
Chandler Carruth 2014-11-13 22:49:44 +00:00
parent a0c1b09c6a
commit 99b261ce6d
1 changed files with 334 additions and 0 deletions
llvm/test/CodeGen/X86

View File

@ -686,6 +686,173 @@ define <8 x float> @shuffle_v8f32_f511235a(<8 x float> %a, <8 x float> %b) {
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_32103210(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_32103210:
; AVX1: # BB#0:
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_32103210:
; AVX2: # BB#0:
; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [3,2,1,0,3,2,1,0]
; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 3, i32 2, i32 1, i32 0>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_76547654(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_76547654:
; AVX1: # BB#0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_76547654:
; AVX2: # BB#0:
; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [7,6,5,4,7,6,5,4]
; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 7, i32 6, i32 5, i32 4>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_76543210(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_76543210:
; AVX1: # BB#0:
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_76543210:
; AVX2: # BB#0:
; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [7,6,5,4,3,2,1,0]
; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_3210ba98(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_3210ba98:
; AVX1: # BB#0:
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_3210ba98:
; AVX2: # BB#0:
; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <u,u,u,u,3,2,1,0>
; AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1
; AVX2-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 11, i32 10, i32 9, i32 8>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_3210fedc(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_3210fedc:
; AVX1: # BB#0:
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_3210fedc:
; AVX2: # BB#0:
; AVX2-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_7654fedc(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_7654fedc:
; AVX1: # BB#0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_7654fedc:
; AVX2: # BB#0:
; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <7,6,5,4,u,u,u,u>
; AVX2-NEXT: vpermps %ymm0, %ymm2, %ymm0
; AVX2-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 15, i32 14, i32 13, i32 12>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_fedc7654(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_fedc7654:
; AVX1: # BB#0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,2,1,0]
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_fedc7654:
; AVX2: # BB#0:
; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <7,6,5,4,u,u,u,u>
; AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1
; AVX2-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 15, i32 14, i32 13, i32 12, i32 7, i32 6, i32 5, i32 4>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_ba987654(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_ba987654:
; AVX1: # BB#0:
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,2,1,0]
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_ba987654:
; AVX2: # BB#0:
; AVX2-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_ba983210(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_ba983210:
; AVX1: # BB#0:
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,2,1,0]
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_ba983210:
; AVX2: # BB#0:
; AVX2-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4>
ret <8 x float> %shuffle
}
define <8 x i32> @shuffle_v8i32_00000000(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_00000000:
; AVX1: # BB#0:
@ -1570,6 +1737,173 @@ define <8 x i32> @shuffle_v8i32_6caa87e5(<8 x i32> %a, <8 x i32> %b) {
ret <8 x i32> %shuffle
}
define <8 x i32> @shuffle_v8i32_32103210(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_32103210:
; AVX1: # BB#0:
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_32103210:
; AVX2: # BB#0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [3,2,1,0,3,2,1,0]
; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 3, i32 2, i32 1, i32 0>
ret <8 x i32> %shuffle
}
define <8 x i32> @shuffle_v8i32_76547654(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_76547654:
; AVX1: # BB#0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_76547654:
; AVX2: # BB#0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [7,6,5,4,7,6,5,4]
; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 7, i32 6, i32 5, i32 4>
ret <8 x i32> %shuffle
}
define <8 x i32> @shuffle_v8i32_76543210(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_76543210:
; AVX1: # BB#0:
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_76543210:
; AVX2: # BB#0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [7,6,5,4,3,2,1,0]
; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
ret <8 x i32> %shuffle
}
define <8 x i32> @shuffle_v8i32_3210ba98(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_3210ba98:
; AVX1: # BB#0:
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_3210ba98:
; AVX2: # BB#0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = <u,u,u,u,3,2,1,0>
; AVX2-NEXT: vpermd %ymm1, %ymm2, %ymm1
; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5,6,7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 11, i32 10, i32 9, i32 8>
ret <8 x i32> %shuffle
}
define <8 x i32> @shuffle_v8i32_3210fedc(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_3210fedc:
; AVX1: # BB#0:
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_3210fedc:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5,6,7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12>
ret <8 x i32> %shuffle
}
define <8 x i32> @shuffle_v8i32_7654fedc(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_7654fedc:
; AVX1: # BB#0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_7654fedc:
; AVX2: # BB#0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = <7,6,5,4,u,u,u,u>
; AVX2-NEXT: vpermd %ymm0, %ymm2, %ymm0
; AVX2-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5,6,7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 15, i32 14, i32 13, i32 12>
ret <8 x i32> %shuffle
}
define <8 x i32> @shuffle_v8i32_fedc7654(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_fedc7654:
; AVX1: # BB#0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,2,1,0]
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_fedc7654:
; AVX2: # BB#0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = <7,6,5,4,u,u,u,u>
; AVX2-NEXT: vpermd %ymm1, %ymm2, %ymm1
; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 15, i32 14, i32 13, i32 12, i32 7, i32 6, i32 5, i32 4>
ret <8 x i32> %shuffle
}
define <8 x i32> @shuffle_v8i32_ba987654(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_ba987654:
; AVX1: # BB#0:
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,2,1,0]
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_ba987654:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4>
ret <8 x i32> %shuffle
}
define <8 x i32> @shuffle_v8i32_ba983210(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_ba983210:
; AVX1: # BB#0:
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,2,1,0]
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_ba983210:
; AVX2: # BB#0:
; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[3,2,1,0,7,6,5,4]
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4>
ret <8 x i32> %shuffle
}
define <8 x float> @splat_mem_v8f32_2(float* %p) {
; ALL-LABEL: splat_mem_v8f32_2:
; ALL: # BB#0: