6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-07-25 13:24:46 +00:00
Code Issues Projects Releases Wiki Activity

[NVPTX] Fix handling of vector arguments

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177847 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Justin Holewinski
2013-03-24 21:17:47 +00:00
parent d28e30fcf4
commit 1ce53cb526
3 changed files with 83 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
test/CodeGen/NVPTX/vector-args.ll Normal file
View File

@@ -0,0 +1,27 @@
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
define float @foo(<2 x float> %a) {
; CHECK: .func (.param .b32 func_retval0) foo
; CHECK: .param .align 8 .b8 foo_param_0[8]
; CHECK: ld.param.f32 %f{{[0-9]+}}
; CHECK: ld.param.f32 %f{{[0-9]+}}
%t1 = fmul <2 x float> %a, %a
%t2 = extractelement <2 x float> %t1, i32 0
%t3 = extractelement <2 x float> %t1, i32 1
%t4 = fadd float %t2, %t3
ret float %t4
}
define float @bar(<4 x float> %a) {
; CHECK: .func (.param .b32 func_retval0) bar
; CHECK: .param .align 16 .b8 bar_param_0[16]
; CHECK: ld.param.f32 %f{{[0-9]+}}
; CHECK: ld.param.f32 %f{{[0-9]+}}
%t1 = fmul <4 x float> %a, %a
%t2 = extractelement <4 x float> %t1, i32 0
%t3 = extractelement <4 x float> %t1, i32 1
%t4 = fadd float %t2, %t3
ret float %t4
}