[llvm] [AMDGPU] When allocating VGPRs, VGPR spills are not part of the prologue (PR #109439)

Jay Foad via llvm-commits llvm-commits at lists.llvm.org
Fri Sep 20 08:50:37 PDT 2024


https://github.com/jayfoad created https://github.com/llvm/llvm-project/pull/109439

PRs #69924 and #72140 modified SIInstrInfo::isBasicBlockPrologue to skip
over EXEC modifications and spills when allocating VGPRs. But treating
VGPR spills as part of the prologue can confuse the register allocator
as in #109294, so restrict it to SGPR spills, which were inserted during
SGPR allocation which is done in an earlier pass.

Fixes: #109294
Fixes: SWDEV-485841


>From c8fbbe4904679dc81b3c9fb5d5d8ac1ceff37498 Mon Sep 17 00:00:00 2001
From: Jay Foad <jay.foad at amd.com>
Date: Fri, 20 Sep 2024 16:27:30 +0100
Subject: [PATCH] [AMDGPU] When allocating VGPRs, VGPR spills are not part of
 the prologue

PRs #69924 and #72140 modified SIInstrInfo::isBasicBlockPrologue to skip
over EXEC modifications and spills when allocating VGPRs. But treating
VGPR spills as part of the prologue can confuse the register allocator
as in #109294, so restrict it to SGPR spills, which were inserted during
SGPR allocation which is done in an earlier pass.

Fixes: #109294
Fixes: SWDEV-485841
---
 llvm/lib/Target/AMDGPU/SIInstrInfo.cpp | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
index 97e8b08270d615..509c5c56e15f57 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -8884,8 +8884,9 @@ bool SIInstrInfo::isBasicBlockPrologue(const MachineInstr &MI,
   // FIXME: Copies inserted in the block prolog for live-range split should also
   // be included.
   return IsNullOrVectorRegister &&
-         (isSpill(Opcode) || (!MI.isTerminator() && Opcode != AMDGPU::COPY &&
-                              MI.modifiesRegister(AMDGPU::EXEC, &RI)));
+         (isSGPRSpill(Opcode) ||
+          (!MI.isTerminator() && Opcode != AMDGPU::COPY &&
+           MI.modifiesRegister(AMDGPU::EXEC, &RI)));
 }
 
 MachineInstrBuilder



More information about the llvm-commits mailing list