mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-24 11:42:57 +01:00
8a358b3669
This was done through the aid of a terrible Perl creation. I will not paste any of the horrors here. Suffice to say, it require multiple staged rounds of replacements, state carried between, and a few nested-construct-parsing hacks that I'm not proud of. It happens, by luck, to be able to deal with all the TCL-quoting patterns in evidence in the LLVM test suite. If anyone is maintaining large out-of-tree test trees, feel free to poke me and I'll send you the steps I used to convert things, as well as answer any painful questions etc. IRC works best for this type of thing I find. Once converted, switch the LLVM lit config to use ShTests the same as Clang. In addition to being able to delete large amounts of Python code from 'lit', this will also simplify the entire test suite and some of lit's architecture. Finally, the test suite runs 33% faster on Linux now. ;] For my 16-hardware-thread (2x 4-core xeon e5520): 36s -> 24s llvm-svn: 159525
28 lines
1.2 KiB
LLVM
28 lines
1.2 KiB
LLVM
; RUN: llc < %s -march=x86 -mcpu=penryn > %t
|
|
; RUN: not grep movd %t
|
|
; RUN: grep "movss %xmm" %t | count 1
|
|
; RUN: grep "extractps \$1, %xmm0, " %t | count 1
|
|
; PR2647
|
|
|
|
external global float, align 16 ; <float*>:0 [#uses=2]
|
|
|
|
define internal void @""() nounwind {
|
|
load float* @0, align 16 ; <float>:1 [#uses=1]
|
|
insertelement <4 x float> undef, float %1, i32 0 ; <<4 x float>>:2 [#uses=1]
|
|
call <4 x float> @llvm.x86.sse.rsqrt.ss( <4 x float> %2 ) ; <<4 x float>>:3 [#uses=1]
|
|
extractelement <4 x float> %3, i32 0 ; <float>:4 [#uses=1]
|
|
store float %4, float* @0, align 16
|
|
ret void
|
|
}
|
|
define internal void @""() nounwind {
|
|
load float* @0, align 16 ; <float>:1 [#uses=1]
|
|
insertelement <4 x float> undef, float %1, i32 1 ; <<4 x float>>:2 [#uses=1]
|
|
call <4 x float> @llvm.x86.sse.rsqrt.ss( <4 x float> %2 ) ; <<4 x float>>:3 [#uses=1]
|
|
extractelement <4 x float> %3, i32 1 ; <float>:4 [#uses=1]
|
|
store float %4, float* @0, align 16
|
|
ret void
|
|
}
|
|
|
|
declare <4 x float> @llvm.x86.sse.rsqrt.ss(<4 x float>) nounwind readnone
|
|
|