diff options
| author | Mark Searles <m.c.searles@gmail.com> | 2018-04-19 15:42:30 +0000 |
|---|---|---|
| committer | Mark Searles <m.c.searles@gmail.com> | 2018-04-19 15:42:30 +0000 |
| commit | 1bc6e71f32ebadefc319c65b3f650e08e39d6aa7 (patch) | |
| tree | bbb954896e398ff8029b87d948ef765e7c5a9eba /llvm/test | |
| parent | 9b20c245ca36998cb2ac6e81543f87b781a9d06b (diff) | |
| download | bcm5719-llvm-1bc6e71f32ebadefc319c65b3f650e08e39d6aa7.tar.gz bcm5719-llvm-1bc6e71f32ebadefc319c65b3f650e08e39d6aa7.zip | |
[AMDGPU] Do not only rely on BB number when finding bottom loop
We should also check that the "bottom" basic block of a loopis a successor of the "header" basic block, otherwise we don't propagate the information correctly when the CFG is complex. This fixes an important rendering problem with Wolfsentein 2, because of one vector-memory wait was missing.
Differential Revision: https://reviews.llvm.org/D43831
llvm-svn: 330337
Diffstat (limited to 'llvm/test')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/waitcnt-back-edge-loop.mir | 59 |
1 files changed, 59 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/waitcnt-back-edge-loop.mir b/llvm/test/CodeGen/AMDGPU/waitcnt-back-edge-loop.mir new file mode 100644 index 00000000000..2d9ec03132b --- /dev/null +++ b/llvm/test/CodeGen/AMDGPU/waitcnt-back-edge-loop.mir @@ -0,0 +1,59 @@ +# RUN: llc -o - %s -march=amdgcn -mcpu=fiji -run-pass=si-insert-waitcnts -verify-machineinstrs | FileCheck -check-prefix=GCN %s + +# GCN-LABEL: waitcnt-back-edge-loop +# GCN: bb.2 +# GCN: S_WAITCNT 112 +# GCN: $vgpr5 = V_CVT_I32_F32_e32 killed $vgpr5, implicit $exec + +--- +name: waitcnt-back-edge-loop +body: | + bb.0: + successors: %bb.1 + + $vgpr1 = V_MOV_B32_e32 0, implicit $exec, implicit-def $vgpr1_vgpr2 + $vgpr2 = V_MOV_B32_e32 0, implicit $exec, implicit-def $vgpr1_vgpr2 + $vgpr4 = FLAT_LOAD_DWORD $vgpr1_vgpr2, 0, 0, 0, implicit $exec, implicit $flat_scr :: (volatile load 4 from `float addrspace(1)* null`, addrspace 1) + $vgpr0 = FLAT_LOAD_DWORD $vgpr1_vgpr2, 0, 0, 0, implicit $exec, implicit $flat_scr :: (volatile load 4 from `float addrspace(1)* null`, addrspace 1) + $sgpr0_sgpr1 = V_CMP_EQ_U32_e64 3, killed $sgpr4, implicit $exec + $vgpr3 = V_CNDMASK_B32_e64 -1082130432, 1065353216, killed $sgpr0_sgpr1, implicit $exec + $vgpr5 = V_MOV_B32_e32 $vgpr0, implicit $exec, implicit $exec + S_BRANCH %bb.1 + + bb.3: + successors: %bb.1 + + $vgpr5 = FLAT_LOAD_DWORD $vgpr1_vgpr2, 0, 0, 0, implicit $exec, implicit $flat_scr :: (volatile load 4 from `float addrspace(1)* null`, addrspace 1) + + bb.1: + successors: %bb.5, %bb.2 + + $vgpr5 = V_CVT_I32_F32_e32 killed $vgpr5, implicit $exec + V_CMP_NE_U32_e32 0, $vgpr5, implicit-def $vcc, implicit $exec + $vcc = S_AND_B64 $exec, killed $vcc, implicit-def dead $scc + S_CBRANCH_VCCZ %bb.5, implicit killed $vcc + + bb.2: + successors: %bb.4, %bb.3 + + V_CMP_EQ_U32_e32 9, killed $vgpr5, implicit-def $vcc, implicit $exec + $vcc = S_AND_B64 $exec, killed $vcc, implicit-def dead $scc + S_CBRANCH_VCCZ %bb.3, implicit killed $vcc + + bb.4: + successors: %bb.3, %bb.1 + + $vgpr5 = FLAT_LOAD_DWORD $vgpr1_vgpr2, 0, 0, 0, implicit $exec, implicit $flat_scr :: (volatile load 4 from `float addrspace(1)* null`, addrspace 1) + $vgpr4 = V_CVT_I32_F32_e32 $vgpr5, implicit $exec + V_CMP_EQ_U32_e32 2, killed $vgpr4, implicit-def $vcc, implicit $exec + $vcc = S_AND_B64 $exec, killed $vcc, implicit-def dead $scc + $vgpr4 = V_MOV_B32_e32 $vgpr5, implicit $exec, implicit $exec + S_CBRANCH_VCCZ %bb.1, implicit killed $vcc + S_BRANCH %bb.3 + + bb.5: + + $vgpr4 = V_MAC_F32_e32 killed $vgpr0, killed $vgpr3, killed $vgpr4, implicit $exec + EXP_DONE 12, killed $vgpr4, undef $vgpr0, undef $vgpr0, undef $vgpr0, 0, 0, 15, implicit $exec + S_ENDPGM +... |
