diff options
| author | Bruno Cardoso Lopes <bruno.cardoso@gmail.com> | 2011-07-21 01:55:47 +0000 |
|---|---|---|
| committer | Bruno Cardoso Lopes <bruno.cardoso@gmail.com> | 2011-07-21 01:55:47 +0000 |
| commit | 65b74e1d00eef81b596b4c207fba069aa1eb8214 (patch) | |
| tree | e4f8ca2a664f9674f641caee534c42d5d2053a01 /test | |
| parent | 9283b668a1d0b41b83292e7b3577ec34a4ed2810 (diff) | |
| download | external_llvm-65b74e1d00eef81b596b4c207fba069aa1eb8214.zip external_llvm-65b74e1d00eef81b596b4c207fba069aa1eb8214.tar.gz external_llvm-65b74e1d00eef81b596b4c207fba069aa1eb8214.tar.bz2 | |
Add support for 256-bit versions of VPERMIL instruction. This is a new
instruction introduced in AVX, which can operate on 128 and 256-bit vectors.
It considers a 256-bit vector as two independent 128-bit lanes. It can permute
any 32 or 64 elements inside a lane, and restricts the second lane to
have the same permutation of the first one. With the improved splat support
introduced early today, adding codegen for this instruction enable more
efficient 256-bit code:
Instead of:
vextractf128 $0, %ymm0, %xmm0
punpcklbw %xmm0, %xmm0
punpckhbw %xmm0, %xmm0
vinsertf128 $0, %xmm0, %ymm0, %ymm1
vinsertf128 $1, %xmm0, %ymm1, %ymm0
vextractf128 $1, %ymm0, %xmm1
shufps $1, %xmm1, %xmm1
movss %xmm1, 28(%rsp)
movss %xmm1, 24(%rsp)
movss %xmm1, 20(%rsp)
movss %xmm1, 16(%rsp)
vextractf128 $0, %ymm0, %xmm0
shufps $1, %xmm0, %xmm0
movss %xmm0, 12(%rsp)
movss %xmm0, 8(%rsp)
movss %xmm0, 4(%rsp)
movss %xmm0, (%rsp)
vmovaps (%rsp), %ymm0
We get:
vextractf128 $0, %ymm0, %xmm0
punpcklbw %xmm0, %xmm0
punpckhbw %xmm0, %xmm0
vinsertf128 $0, %xmm0, %ymm0, %ymm1
vinsertf128 $1, %xmm0, %ymm1, %ymm0
vpermilps $85, %ymm0, %ymm0
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@135662 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test')
| -rw-r--r-- | test/CodeGen/X86/avx-256-splat.ll | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/test/CodeGen/X86/avx-256-splat.ll b/test/CodeGen/X86/avx-256-splat.ll new file mode 100644 index 0000000..27ff926 --- /dev/null +++ b/test/CodeGen/X86/avx-256-splat.ll @@ -0,0 +1,16 @@ +; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s + +; FIXME: use avx versions for punpcklbw and punpckhbw + +; CHECK: vextractf128 $0 +; CHECK-NEXT: punpcklbw +; CHECK-NEXT: punpckhbw +; CHECK-NEXT: vinsertf128 $0 +; CHECK-NEXT: vinsertf128 $1 +; CHECK-NEXT: vpermilps $85 +define <32 x i8> @funcA(<32 x i8> %a) nounwind uwtable readnone ssp { +entry: + %shuffle = shufflevector <32 x i8> %a, <32 x i8> undef, <32 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5> + ret <32 x i8> %shuffle +} + |