1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
llvm-mirror/test/CodeGen/AMDGPU/si-lower-control-flow-unreachable-block.ll
cdevadas 4033a61f5d Resubmit: [AMDGPU] Invert the handling of skip insertion.
The current implementation of skip insertion (SIInsertSkip) makes it a
mandatory pass required for correctness. Initially, the idea was to
have an optional pass. This patch inserts the s_cbranch_execz upfront
during SILowerControlFlow to skip over the sections of code when no
lanes are active. Later, SIRemoveShortExecBranches removes the skips
for short branches, unless there is a sideeffect and the skip branch is
really necessary.

This new pass will replace the handling of skip insertion in the
existing SIInsertSkip Pass.

Differential revision: https://reviews.llvm.org/D68092
2020-01-22 13:18:32 +09:00

79 lines
1.9 KiB
LLVM

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; GCN-LABEL: {{^}}lower_control_flow_unreachable_terminator:
; GCN: v_cmp_eq_u32
; GCN: s_and_saveexec_b64
; GCN-NEXT: ; %bb.{{[0-9]+}}: ; %unreachable
; GCN: ds_write_b32
; GCN: ; divergent unreachable
; GCN-NEXT: ; %bb.{{[0-9]+}}: ; %UnifiedReturnBlock
; GCN: s_endpgm
define amdgpu_kernel void @lower_control_flow_unreachable_terminator() #0 {
bb:
%tmp15 = tail call i32 @llvm.amdgcn.workitem.id.y()
%tmp63 = icmp eq i32 %tmp15, 32
br i1 %tmp63, label %unreachable, label %ret
unreachable:
store volatile i32 0, i32 addrspace(3)* undef, align 4
unreachable
ret:
ret void
}
; GCN-LABEL: {{^}}lower_control_flow_unreachable_terminator_swap_block_order:
; GCN: v_cmp_ne_u32
; GCN: s_and_saveexec_b64
; GCN-NEXT: ; %bb.{{[0-9]+}}: ; %unreachable
; GCN: ds_write_b32
; GCN: ; divergent unreachable
; GCN: ; %bb.{{[0-9]+}}:
; GCN-NEXT: s_endpgm
define amdgpu_kernel void @lower_control_flow_unreachable_terminator_swap_block_order() #0 {
bb:
%tmp15 = tail call i32 @llvm.amdgcn.workitem.id.y()
%tmp63 = icmp eq i32 %tmp15, 32
br i1 %tmp63, label %ret, label %unreachable
ret:
ret void
unreachable:
store volatile i32 0, i32 addrspace(3)* undef, align 4
unreachable
}
; GCN-LABEL: {{^}}uniform_lower_control_flow_unreachable_terminator:
; GCN: s_cmp_lg_u32
; GCN: s_cbranch_scc0 [[UNREACHABLE:BB[0-9]+_[0-9]+]]
; GCN-NEXT: %bb.{{[0-9]+}}: ; %ret
; GCN-NEXT: s_endpgm
; GCN: [[UNREACHABLE]]:
; GCN: ds_write_b32
define amdgpu_kernel void @uniform_lower_control_flow_unreachable_terminator(i32 %arg0) #0 {
bb:
%tmp63 = icmp eq i32 %arg0, 32
br i1 %tmp63, label %unreachable, label %ret
unreachable:
store volatile i32 0, i32 addrspace(3)* undef, align 4
unreachable
ret:
ret void
}
declare i32 @llvm.amdgcn.workitem.id.y() #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }
attributes #2 = { nounwind }