================
@@ -1682,38 +1690,109 @@ bool WaitcntGeneratorPreGFX12::applyPreexistingWaitcnt(
/// required counters in \p Wait
bool WaitcntGeneratorPreGFX12::createNewWaitcnt(
MachineBasicBlock &Block, MachineBasicBlock::instr_iterator It,
- AMDGPU::Waitcnt Wait) {
+ AMDGPU::Waitcnt Wait, WaitcntBrackets *ScoreBrackets) {
assert(ST);
assert(isNormalMode(MaxCounter));
bool Modified = false;
const DebugLoc &DL = Block.findDebugLoc(It);
+ // Helper to emit expanded waitcnt sequence for profiling.
+ // Emits waitcnts from (Outstanding-1) down to Target, or just Target if
+ // nothing to expand. The EmitWaitcnt callback emits a single waitcnt.
+ auto EmitExpandedWaitcnt = [&](unsigned Outstanding, unsigned Target,
+ auto EmitWaitcnt) {
+ if (Outstanding > Target) {
----------------
jayfoad wrote:
You should not need this "if". The loop should work in all cases.
https://github.com/llvm/llvm-project/pull/169345
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
