[llvm] [RISCV] Override default sched policy (PR #115445)

[Pengcheng Wang via llvm-commits]

https://github.com/wangpc-pp created https://github.com/llvm/llvm-project/pull/115445

This is based on other targets like PPC/AArch64 and some experiments.

Disclaimer: I haven't tested it on many cores, maybe we should make
some options being features. I believe downstreams must have tried
this before, so feedbacks are welcome.


>From 074c3c32e7f52c44b8dfb798fccd530978f9fe0e Mon Sep 17 00:00:00 2001
From: Wang Pengcheng <wangpengcheng.pp at bytedance.com>
Date: Fri, 8 Nov 2024 17:04:46 +0800
Subject: [PATCH] [RISCV] Override default sched policy

This is based on other targets like PPC/AArch64 and some experiments.

Disclaimer: I haven't tested it on many cores, maybe we should make
some options being features. I believe downstreams must have tried
this before, so feedbacks are welcome.
---
 llvm/lib/Target/RISCV/RISCVSubtarget.cpp | 23 +++++++++++++++++++++++
 llvm/lib/Target/RISCV/RISCVSubtarget.h   |  3 +++
 2 files changed, 26 insertions(+)

diff --git a/llvm/lib/Target/RISCV/RISCVSubtarget.cpp b/llvm/lib/Target/RISCV/RISCVSubtarget.cpp
index e7db1ededf383b..f43c520422f13d 100644
--- a/llvm/lib/Target/RISCV/RISCVSubtarget.cpp
+++ b/llvm/lib/Target/RISCV/RISCVSubtarget.cpp
@@ -16,6 +16,7 @@
 #include "RISCV.h"
 #include "RISCVFrameLowering.h"
 #include "RISCVTargetMachine.h"
+#include "llvm/CodeGen/MachineScheduler.h"
 #include "llvm/CodeGen/MacroFusion.h"
 #include "llvm/CodeGen/ScheduleDAGMutation.h"
 #include "llvm/MC/TargetRegistry.h"
@@ -199,3 +200,25 @@ unsigned RISCVSubtarget::getMinimumJumpTableEntries() const {
              ? RISCVMinimumJumpTableEntries
              : TuneInfo->MinimumJumpTableEntries;
 }
+
+void RISCVSubtarget::overrideSchedPolicy(MachineSchedPolicy &Policy,
+                                         unsigned NumRegionInstrs) const {
+  // Do bidirectional scheduling since it provides a more balanced scheduling
+  // leading to better performance. This will increase compile time.
+  Policy.OnlyTopDown = false;
+  Policy.OnlyBottomUp = false;
+
+  // Enabling or Disabling the latency heuristic is a close call: It seems to
+  // help nearly no benchmark on out-of-order architectures, on the other hand
+  // it regresses register pressure on a few benchmarking.
+  // FIXME: This is from AArch64, but we haven't evaluated it on RISC-V.
+  Policy.DisableLatencyHeuristic = true;
+
+  // Spilling is generally expensive on all RISC-V cores, so always enable
+  // register-pressure tracking. This will increase compile time.
+  Policy.ShouldTrackPressure = true;
+
+  // Enabling ShouldTrackLaneMasks when vector instructions are supported.
+  // TODO: Add extensions that need register pairs as well?
+  Policy.ShouldTrackLaneMasks = hasVInstructions();
+}
diff --git a/llvm/lib/Target/RISCV/RISCVSubtarget.h b/llvm/lib/Target/RISCV/RISCVSubtarget.h
index f59a3737ae76f9..f2c0a3d85c998a 100644
--- a/llvm/lib/Target/RISCV/RISCVSubtarget.h
+++ b/llvm/lib/Target/RISCV/RISCVSubtarget.h
@@ -327,6 +327,9 @@ class RISCVSubtarget : public RISCVGenSubtargetInfo {
   unsigned getTailDupAggressiveThreshold() const {
     return TuneInfo->TailDupAggressiveThreshold;
   }
+
+  void overrideSchedPolicy(MachineSchedPolicy &Policy,
+                           unsigned NumRegionInstrs) const override;
 };
 } // End llvm namespace