mirror of
https://github.com/RPCSX/llvm.git
synced 2024-11-26 13:10:34 +00:00
4177e6fff5
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159525 91177308-0d34-0410-b5e6-96231b3b80d8
31 lines
1.0 KiB
LLVM
31 lines
1.0 KiB
LLVM
; RUN: opt < %s -scalarrepl -S > %t
|
|
; RUN: grep "ret <16 x float> %A" %t
|
|
; RUN: grep "ret <16 x float> zeroinitializer" %t
|
|
target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64"
|
|
|
|
define <16 x float> @foo(<16 x float> %A) nounwind {
|
|
%tmp = alloca <16 x float>, align 16
|
|
%tmp2 = alloca <16 x float>, align 16
|
|
store <16 x float> %A, <16 x float>* %tmp
|
|
%s = bitcast <16 x float>* %tmp to i8*
|
|
%s2 = bitcast <16 x float>* %tmp2 to i8*
|
|
call void @llvm.memcpy.i64(i8* %s2, i8* %s, i64 64, i32 16)
|
|
|
|
%R = load <16 x float>* %tmp2
|
|
ret <16 x float> %R
|
|
}
|
|
|
|
define <16 x float> @foo2(<16 x float> %A) nounwind {
|
|
%tmp2 = alloca <16 x float>, align 16
|
|
|
|
%s2 = bitcast <16 x float>* %tmp2 to i8*
|
|
call void @llvm.memset.i64(i8* %s2, i8 0, i64 64, i32 16)
|
|
|
|
%R = load <16 x float>* %tmp2
|
|
ret <16 x float> %R
|
|
}
|
|
|
|
|
|
declare void @llvm.memcpy.i64(i8* nocapture, i8* nocapture, i64, i32) nounwind
|
|
declare void @llvm.memset.i64(i8* nocapture, i8, i64, i32) nounwind
|