diff options
| author | Andrew Trick <atrick@apple.com> | 2013-06-24 09:13:20 +0000 |
|---|---|---|
| committer | Andrew Trick <atrick@apple.com> | 2013-06-24 09:13:20 +0000 |
| commit | 98a9b72e8c56dc13a2617de84503a3d78352789c (patch) | |
| tree | fd31bd17c5362627889925766aad73d8cdaddb32 /test/CodeGen/X86/gather-addresses.ll | |
| parent | 4ee72398a15cd7b8e217bb3d34a4e9e0e72caca1 (diff) | |
| download | llvm-98a9b72e8c56dc13a2617de84503a3d78352789c.tar.gz llvm-98a9b72e8c56dc13a2617de84503a3d78352789c.tar.bz2 llvm-98a9b72e8c56dc13a2617de84503a3d78352789c.tar.xz | |
Temporarily enable MI-Sched on X86.
Sorry for the unit test churn. I'll try to make the change permanently
next time.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@184705 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/X86/gather-addresses.ll')
| -rw-r--r-- | test/CodeGen/X86/gather-addresses.ll | 38 |
1 files changed, 26 insertions, 12 deletions
diff --git a/test/CodeGen/X86/gather-addresses.ll b/test/CodeGen/X86/gather-addresses.ll index 72a50961b2..d1abd71618 100644 --- a/test/CodeGen/X86/gather-addresses.ll +++ b/test/CodeGen/X86/gather-addresses.ll @@ -1,21 +1,35 @@ -; RUN: llc -mtriple=x86_64-linux -mcpu=nehalem < %s | FileCheck %s -; RUN: llc -mtriple=x86_64-win32 -mcpu=nehalem < %s | FileCheck %s +; RUN: llc -mtriple=x86_64-linux -mcpu=nehalem < %s | FileCheck %s --check-prefix=LIN +; RUN: llc -mtriple=x86_64-win32 -mcpu=nehalem < %s | FileCheck %s --check-prefix=WIN ; rdar://7398554 ; When doing vector gather-scatter index calculation with 32-bit indices, ; bounce the vector off of cache rather than shuffling each individual ; element out of the index vector. -; CHECK: andps ([[H:%rdx|%r8]]), %xmm0 -; CHECK: movaps %xmm0, {{(-24)?}}(%rsp) -; CHECK: movslq {{(-24)?}}(%rsp), %rax -; CHECK: movsd ([[P:%rdi|%rcx]],%rax,8), %xmm0 -; CHECK: movslq {{-20|4}}(%rsp), %rax -; CHECK: movhpd ([[P]],%rax,8), %xmm0 -; CHECK: movslq {{-16|8}}(%rsp), %rax -; CHECK: movsd ([[P]],%rax,8), %xmm1 -; CHECK: movslq {{-12|12}}(%rsp), %rax -; CHECK: movhpd ([[P]],%rax,8), %xmm1 +; CHECK: foo: +; LIN: movaps (%rsi), %xmm0 +; LIN: andps (%rdx), %xmm0 +; LIN: movaps %xmm0, -24(%rsp) +; LIN: movslq -24(%rsp), %rsi +; LIN: movslq -20(%rsp), %rcx +; LIN: movslq -16(%rsp), %rdx +; LIN: movslq -12(%rsp), %rax +; LIN: movsd (%rdi,%rsi,8), %xmm0 +; LIN: movhpd (%rdi,%rcx,8), %xmm0 +; LIN: movsd (%rdi,%rdx,8), %xmm1 +; LIN: movhpd (%rdi,%rax,8), %xmm1 + +; WIN: movaps (%rdx), %xmm0 +; WIN: andps (%r8), %xmm0 +; WIN: movaps %xmm0, (%rsp) +; WIN: movslq (%rsp), %rax +; WIN: movslq 4(%rsp), %rdx +; WIN: movslq 8(%rsp), %r9 +; WIN: movslq 12(%rsp), %r8 +; WIN: movsd (%rcx,%rax,8), %xmm0 +; WIN: movhpd (%rcx,%rdx,8), %xmm0 +; WIN: movsd (%rcx,%r9,8), %xmm1 +; WIN: movhpd (%rcx,%r8,8), %xmm1 define <4 x double> @foo(double* %p, <4 x i32>* %i, <4 x i32>* %h) nounwind { %a = load <4 x i32>* %i |