maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AMDGPU] Fix missing waitcnt issue 

Ignore out of order counters when merging brackets. The fact that
there was a pending event in the old state does not guarantee that
the waitcnt was generated, so we still need to conservatively re-process
the block.

The patch fixes a correctness issue where the block was not re-processed
and the waitcnt not inserted in consequence.

Differential Revision: https://reviews.llvm.org/D117544
This commit is contained in:
Piotr Sobczak 2022-01-17 17:51:23 +01:00
parent be8742b6c9
commit 8dfb417e67
2 changed files with 37 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
View File

@ -1382,7 +1382,6 @@ bool WaitcntBrackets::merge(const WaitcntBrackets &Other) {
for (auto T : inst_counter_types()) {
// Merge event flags for this counter
const bool OldOutOfOrder = counterOutOfOrder(T);
const unsigned OldEvents = PendingEvents & WaitEventMaskForInst[T];
const unsigned OtherEvents = Other.PendingEvents & WaitEventMaskForInst[T];
if (OtherEvents & ~OldEvents)
@ -1425,7 +1424,7 @@ bool WaitcntBrackets::merge(const WaitcntBrackets &Other) {
}
}
if (RegStrictDom && !OldOutOfOrder)
if (RegStrictDom)
StrictDom = true;
}

36
llvm/test/CodeGen/AMDGPU/waitcnt.mir
View File

@ -44,6 +44,10 @@
define amdgpu_kernel void @subregs16bit() {
ret void
}
define amdgpu_kernel void @waitcnt_backedge() {
ret void
}
...
---
@ -332,3 +336,35 @@ body: |
$vgpr1 = FLAT_LOAD_USHORT killed $vgpr2_vgpr3, 0, 0, implicit $exec, implicit $flat_scr
V_NOP_e32 implicit $exec, implicit $vgpr0_lo16, implicit $vgpr1_lo16
...
---
# Waitcnt required before the use of $sgpr10_sgpr11, as the S_LOAD also writes
# to $sgpr10_sgpr11, and can occur first in the program running order.
# CHECK-LABEL: name: waitcnt_backedge
# CHECK: S_WAITCNT
# CHECK: $sgpr10_sgpr11 = S_CSELECT_B64
# CHECK: $sgpr10_sgpr11 = S_LOAD_DWORDX2_IMM
name: waitcnt_backedge
body: |
bb.0:
renamable $sgpr4_sgpr5_sgpr6_sgpr7 = S_LOAD_DWORDX4_IMM renamable $sgpr2_sgpr3, 32, 0 :: (load (s128) from `i32 addrspace(4)* undef`, addrspace 4)
bb.4:
renamable $sgpr10_sgpr11 = S_CSELECT_B64 -1, 0, implicit killed $scc
renamable $vgpr1 = BUFFER_LOAD_DWORD_OFFEN killed renamable $vgpr5, renamable $sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 1, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
renamable $sgpr10_sgpr11 = S_LOAD_DWORDX2_IMM killed renamable $sgpr0_sgpr1, 0, 0 :: (load (s64) from `i32 addrspace(4)* undef`, align 4, addrspace 4)
S_CBRANCH_SCC0 %bb.9, implicit killed $scc
bb.9:
renamable $vgpr1 = V_CNDMASK_B32_e64 0, 0, 0, 1, killed $sgpr14_sgpr15, implicit $exec
S_CBRANCH_SCC0 %bb.14, implicit killed $scc
bb.10:
S_BRANCH %bb.4
bb.14:
S_ENDPGM 0
...