mirror of
https://github.com/RPCSX/llvm.git
synced 2025-01-07 12:30:44 +00:00
7eba65d30c
For some reason there are both of these available, except for scalar 64-bit compares which only has u64. I'm not sure why there are both (I'm guessing it's for the one bit inputs we don't use), but for consistency always using the unsigned one. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@282832 91177308-0d34-0410-b5e6-96231b3b80d8
50 lines
1.5 KiB
LLVM
50 lines
1.5 KiB
LLVM
; RUN: llc -mtriple=amdgcn--amdhsa -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #0
|
|
; GCN-LABEL: {{^}}convergent_inlineasm:
|
|
; GCN: BB#0:
|
|
; GCN: v_cmp_ne_u32_e64
|
|
; GCN: ; mask branch
|
|
; GCN: BB{{[0-9]+_[0-9]+}}:
|
|
define void @convergent_inlineasm(i64 addrspace(1)* nocapture %arg) {
|
|
bb:
|
|
%tmp = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tmp1 = tail call i64 asm "v_cmp_ne_u32_e64 $0, 0, $1", "=s,v"(i32 1) #1
|
|
%tmp2 = icmp eq i32 %tmp, 8
|
|
br i1 %tmp2, label %bb3, label %bb5
|
|
|
|
bb3: ; preds = %bb
|
|
%tmp4 = getelementptr i64, i64 addrspace(1)* %arg, i32 %tmp
|
|
store i64 %tmp1, i64 addrspace(1)* %arg, align 8
|
|
br label %bb5
|
|
|
|
bb5: ; preds = %bb3, %bb
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}nonconvergent_inlineasm:
|
|
; GCN: ; mask branch
|
|
|
|
; GCN: BB{{[0-9]+_[0-9]+}}:
|
|
; GCN: v_cmp_ne_u32_e64
|
|
|
|
; GCN: BB{{[0-9]+_[0-9]+}}:
|
|
define void @nonconvergent_inlineasm(i64 addrspace(1)* nocapture %arg) {
|
|
bb:
|
|
%tmp = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tmp1 = tail call i64 asm "v_cmp_ne_u32_e64 $0, 0, $1", "=s,v"(i32 1)
|
|
%tmp2 = icmp eq i32 %tmp, 8
|
|
br i1 %tmp2, label %bb3, label %bb5
|
|
|
|
bb3: ; preds = %bb
|
|
%tmp4 = getelementptr i64, i64 addrspace(1)* %arg, i32 %tmp
|
|
store i64 %tmp1, i64 addrspace(1)* %arg, align 8
|
|
br label %bb5
|
|
|
|
bb5: ; preds = %bb3, %bb
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind readnone }
|
|
attributes #1 = { convergent nounwind readnone }
|