From c8ea114741cecf9c812b5e90eaa28919328df650 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault@amd.com>
Date: Fri, 27 Jun 2025 21:05:03 +0900
Subject: AMDGPU: Introduce a pass to replace VGPR MFMAs with AGPR (#145024)

In gfx90a-gfx950, it's possible to emit MFMAs which use AGPRs or VGPRs
for vdst and src2. We do not want to do use the AGPR form, unless
required by register pressure as it requires cross bank register
copies from most other instructions. Currently we select the AGPR
or VGPR version depending on a crude heuristic for whether it's possible
AGPRs will be required. We really need the register allocation to
be complete to make a good decision, which is what this pass is for.

This adds the pass, but does not yet remove the selection patterns
for AGPRs. This is a WIP, and NFC-ish. It should be a no-op on any
currently selected code. It also does not yet trigger on the real
examples of interest, which require handling batches of MFMAs at
once.
---
 llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp')

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index d2e4825cf3c8..c3536113e9be 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -534,6 +534,7 @@ extern "C" LLVM_ABI LLVM_EXTERNAL_VISIBILITY void LLVMInitializeAMDGPUTarget() {
   initializeAMDGPULowerModuleLDSLegacyPass(*PR);
   initializeAMDGPULowerBufferFatPointersPass(*PR);
   initializeAMDGPUReserveWWMRegsLegacyPass(*PR);
+  initializeAMDGPURewriteAGPRCopyMFMALegacyPass(*PR);
   initializeAMDGPURewriteOutArgumentsPass(*PR);
   initializeAMDGPURewriteUndefForPHILegacyPass(*PR);
   initializeSIAnnotateControlFlowLegacyPass(*PR);
@@ -1577,6 +1578,8 @@ void GCNPassConfig::addOptimizedRegAlloc() {
 bool GCNPassConfig::addPreRewrite() {
   if (EnableRegReassign)
     addPass(&GCNNSAReassignID);
+
+  addPass(&AMDGPURewriteAGPRCopyMFMALegacyID);
   return true;
 }
 
-- 
cgit v1.2.3