RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
Code Issues Projects Releases Wiki Activity

[NVPTX] Add missing .v4 qualifier on vector store instruction

Browse Source 
llvm-svn: 213276
This commit is contained in:
Justin Holewinski 2014-07-17 16:58:56 +00:00
parent 86c034e0ff
commit 60265475a1
2 changed files with 13 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lib/Target/NVPTX/NVPTXInstrInfo.td
View File

@ -1917,7 +1917,7 @@ def StoreParamV2I8 : StoreParamV2Inst<Int16Regs, ".b8">;
def StoreParamV4I32 : NVPTXInst<(outs), (ins Int32Regs:$val, Int32Regs:$val2,
Int32Regs:$val3, Int32Regs:$val4,
i32imm:$a, i32imm:$b),
"st.param.b32\t[param$a+$b], {{$val, $val2, $val3, $val4}};",
"st.param.v4.b32\t[param$a+$b], {{$val, $val2, $val3, $val4}};",
[]>;
def StoreParamV4I16 : NVPTXInst<(outs), (ins Int16Regs:$val, Int16Regs:$val2,

12
test/CodeGen/NVPTX/vector-call.ll Normal file
View File

@ -0,0 +1,12 @@
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
target triple = "nvptx-unknown-cuda"
declare void @bar(<4 x i32>)
; CHECK-LABEL @foo
define void @foo(<4 x i32> %a) {
; CHECK: st.param.v4.b32
tail call void @bar(<4 x i32> %a)
ret void
}