diff options
author | Dale Johannesen <dalej@apple.com> | 2010-09-30 23:57:10 +0000 |
---|---|---|
committer | Dale Johannesen <dalej@apple.com> | 2010-09-30 23:57:10 +0000 |
commit | 0488fb649a56b7fc89a5814df5308813f9e5a85d (patch) | |
tree | 21913bb81960866b73c6b49f29782c142563304c /test/CodeGen/X86/mmx-insert-element.ll | |
parent | a7e3b564773cc45a1b08383c09fe86b17b3ffe92 (diff) | |
download | llvm-0488fb649a56b7fc89a5814df5308813f9e5a85d.tar.gz llvm-0488fb649a56b7fc89a5814df5308813f9e5a85d.tar.bz2 llvm-0488fb649a56b7fc89a5814df5308813f9e5a85d.tar.xz |
Massive rewrite of MMX:
The x86_mmx type is used for MMX intrinsics, parameters and
return values where these use MMX registers, and is also
supported in load, store, and bitcast.
Only the above operations generate MMX instructions, and optimizations
do not operate on or produce MMX intrinsics.
MMX-sized vectors <2 x i32> etc. are lowered to XMM or split into
smaller pieces. Optimizations may occur on these forms and the
result casted back to x86_mmx, provided the result feeds into a
previous existing x86_mmx operation.
The point of all this is prevent optimizations from introducing
MMX operations, which is unsafe due to the EMMS problem.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115243 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/X86/mmx-insert-element.ll')
-rw-r--r-- | test/CodeGen/X86/mmx-insert-element.ll | 10 |
1 files changed, 6 insertions, 4 deletions
diff --git a/test/CodeGen/X86/mmx-insert-element.ll b/test/CodeGen/X86/mmx-insert-element.ll index a063ee1d6c..9f9bd8de2d 100644 --- a/test/CodeGen/X86/mmx-insert-element.ll +++ b/test/CodeGen/X86/mmx-insert-element.ll @@ -1,7 +1,9 @@ -; RUN: llc < %s -march=x86 -mattr=+mmx | not grep movq -; RUN: llc < %s -march=x86 -mattr=+mmx | grep psllq +; RUN: llc < %s -march=x86 -mattr=+mmx,+sse | grep movq +; RUN: llc < %s -march=x86 -mattr=+mmx,+sse | grep pshufd +; This is not an MMX operation; promoted to XMM. -define <2 x i32> @qux(i32 %A) nounwind { +define x86_mmx @qux(i32 %A) nounwind { %tmp3 = insertelement <2 x i32> < i32 0, i32 undef >, i32 %A, i32 1 ; <<2 x i32>> [#uses=1] - ret <2 x i32> %tmp3 + %tmp4 = bitcast <2 x i32> %tmp3 to x86_mmx + ret x86_mmx %tmp4 } |