Summary: - Other counters are accidentally cleared.
Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D71866
assert(II->getOpcode() == AMDGPU::S_WAITCNT_VSCNT);
assert(II->getOperand(0).getReg() == AMDGPU::SGPR_NULL);
ScoreBrackets.applyWaitcnt(
- AMDGPU::Waitcnt(0, 0, 0, II->getOperand(1).getImm()));
+ AMDGPU::Waitcnt(~0u, ~0u, ~0u, II->getOperand(1).getImm()));
}
}
}
--- /dev/null
+# RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass si-insert-waitcnts -o - %s | FileCheck -check-prefix=GFX10 %s
+
+# GFX10-LABEL: waitcnt-vscnt
+# GFX10: GLOBAL_ATOMIC_ADD_RTN
+# GFX10-NEXT: S_WAITCNT 49279
+---
+name: waitcnt-vscnt
+machineFunctionInfo:
+ isEntryFunction: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1
+ $sgpr4 = S_LOAD_DWORD_IMM $sgpr0_sgpr1, 4, 0, 0 :: (dereferenceable invariant load 4 from `i32 addrspace(4)* undef`)
+ S_WAITCNT_VSCNT undef $sgpr_null, 0
+ $vgpr0 = GLOBAL_ATOMIC_ADD_RTN $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec :: (load store syncscope("agent") seq_cst 4, addrspace 1)
+ S_CMP_LG_U32 killed $sgpr4, 0, implicit-def $scc
+...