mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-11-16 11:05:54 +00:00
0488fb649a
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
34 lines
1.2 KiB
LLVM
34 lines
1.2 KiB
LLVM
; RUN: llc < %s -march=x86 -mattr=+sse2 > %t
|
|
; RUN: grep shll %t | grep 12
|
|
; RUN: grep pslldq %t | grep 12
|
|
; RUN: grep psrldq %t | grep 8
|
|
; RUN: grep psrldq %t | grep 12
|
|
; There are no MMX operations in @t1
|
|
|
|
define void @t1(i32 %a, x86_mmx* %P) nounwind {
|
|
%tmp12 = shl i32 %a, 12
|
|
%tmp21 = insertelement <2 x i32> undef, i32 %tmp12, i32 1
|
|
%tmp22 = insertelement <2 x i32> %tmp21, i32 0, i32 0
|
|
%tmp23 = bitcast <2 x i32> %tmp22 to x86_mmx
|
|
store x86_mmx %tmp23, x86_mmx* %P
|
|
ret void
|
|
}
|
|
|
|
define <4 x float> @t2(<4 x float>* %P) nounwind {
|
|
%tmp1 = load <4 x float>* %P
|
|
%tmp2 = shufflevector <4 x float> %tmp1, <4 x float> zeroinitializer, <4 x i32> < i32 4, i32 4, i32 4, i32 0 >
|
|
ret <4 x float> %tmp2
|
|
}
|
|
|
|
define <4 x float> @t3(<4 x float>* %P) nounwind {
|
|
%tmp1 = load <4 x float>* %P
|
|
%tmp2 = shufflevector <4 x float> %tmp1, <4 x float> zeroinitializer, <4 x i32> < i32 2, i32 3, i32 4, i32 4 >
|
|
ret <4 x float> %tmp2
|
|
}
|
|
|
|
define <4 x float> @t4(<4 x float>* %P) nounwind {
|
|
%tmp1 = load <4 x float>* %P
|
|
%tmp2 = shufflevector <4 x float> zeroinitializer, <4 x float> %tmp1, <4 x i32> < i32 7, i32 0, i32 0, i32 0 >
|
|
ret <4 x float> %tmp2
|
|
}
|