1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-24 05:23:45 +02:00
llvm-mirror/test/CodeGen/AMDGPU/branch-condition-and.ll
Matt Arsenault 594fa2719f AMDGPU: Unify divergent function exits.
StructurizeCFG can't handle cases with multiple
returns creating regions with multiple exits.
Create a copy of UnifyFunctionExitNodes that only
unifies exit nodes that skips exit nodes
with uniform branch sources.

llvm-svn: 298729
2017-03-24 19:52:05 +00:00

45 lines
1.5 KiB
LLVM

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; This used to crash because during intermediate control flow lowering, there
; was a sequence
; s_mov_b64 s[0:1], exec
; s_and_b64 s[2:3], s[0:1], s[2:3] ; def & use of the same register pair
; ...
; s_mov_b64_term exec, s[2:3]
; that was not treated correctly.
;
; GCN-LABEL: {{^}}ham:
; GCN-DAG: v_cmp_lt_f32_e64 [[OTHERCC:s\[[0-9]+:[0-9]+\]]],
; GCN-DAG: v_cmp_lt_f32_e32 vcc,
; GCN: s_and_b64 [[AND:s\[[0-9]+:[0-9]+\]]], vcc, [[OTHERCC]]
; GCN: s_and_saveexec_b64 [[SAVED:s\[[0-9]+:[0-9]+\]]], [[AND]]
; GCN: s_xor_b64 {{s\[[0-9]+:[0-9]+\]}}, exec, [[SAVED]]
; GCN: ; mask branch [[BB5:BB[0-9]+_[0-9]+]]
; GCN-NEXT: BB{{[0-9]+_[0-9]+}}: ; %bb4
; GCN: ds_write_b32
; GCN: s_waitcnt
; GCN-NEXT: [[BB5]]
; GCN: s_or_b64 exec, exec
; GCN-NEXT: s_endpgm
; GCN-NEXT: .Lfunc_end
define amdgpu_ps void @ham(float %arg, float %arg1) #0 {
bb:
%tmp = fcmp ogt float %arg, 0.000000e+00
%tmp2 = fcmp ogt float %arg1, 0.000000e+00
%tmp3 = and i1 %tmp, %tmp2
br i1 %tmp3, label %bb4, label %bb5
bb4: ; preds = %bb
store volatile i32 4, i32 addrspace(3)* undef
unreachable
bb5: ; preds = %bb
ret void
}
attributes #0 = { nounwind readonly "InitialPSInputAddr"="36983" }
attributes #1 = { nounwind readnone }