[llvm] [AMDGPU][SIPreEmitPeephole] mustRetainExeczBranch: estimate ThenBlock cost using MachineTraceInfo (PR #111117)
Matt Arsenault via llvm-commits
llvm-commits at lists.llvm.org
Fri Oct 4 02:32:33 PDT 2024
Juan Manuel Martinez =?utf-8?q?Caamaño?= <juamarti at amd.com>,
Juan Manuel Martinez =?utf-8?q?Caamaño?= <juamarti at amd.com>
Message-ID:
In-Reply-To: <llvm.org/llvm/llvm-project/pull/111117 at github.com>
================
@@ -304,11 +311,20 @@ bool SIPreEmitPeephole::getBlockDestinations(
return true;
}
-bool SIPreEmitPeephole::mustRetainExeczBranch(
- const MachineBasicBlock &From, const MachineBasicBlock &To) const {
- unsigned NumInstr = 0;
- const MachineFunction *MF = From.getParent();
+bool SIPreEmitPeephole::mustRetainExeczBranch(const MachineBasicBlock &Head,
+ const MachineBasicBlock &From,
+ const MachineBasicBlock &To) {
+ const auto *FromIt = find(Head.successors(), &From);
+ assert(FromIt != Head.succ_end());
+
+ auto BranchProb = Head.getSuccProbability(FromIt);
+ assert(!BranchProb.isUnknown());
+ unsigned BranchCost = TII->getSchedModel().computeInstrLatency(
+ &*Head.getFirstTerminator(), false);
----------------
arsenm wrote:
Ought to just pass in the branch instruction the caller already found, rather than doing the block scan again in getFirstTerminator
https://github.com/llvm/llvm-project/pull/111117
More information about the llvm-commits
mailing list