[llvm] [GlobalISel][AMDGPU] Do not cache UsesAGPRs from empty functions. (PR #124799)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-amdgpu

Author: David Green (davemgreen)

<details>
<summary>Changes</summary>

After we fall back from global-isel to SDAG, the verifier gets called, which calls getReservedRegs which uses SIMachineFunctionInfo::usesAGPRs which caches the result of UsesAGPRs. Because we have just fallen-back the function is empty and it incorrectly gets cached to false. This patch makes sure we don't try to cache incorrect information from a function in an empty state.

---
Full diff: https://github.com/llvm/llvm-project/pull/124799.diff


2 Files Affected:

- (modified) llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp (+6) 
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.gfx950.ll (+1-1) 


``````````diff
diff --git a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
index c5efb89d8b2dbc..64026cd237d179 100644
--- a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
@@ -788,6 +788,12 @@ bool SIMachineFunctionInfo::usesAGPRs(const MachineFunction &MF) const {
   if (UsesAGPRs)
     return *UsesAGPRs;
 
+  // Assume we cannot get any useful information about an empty function, but do
+  // not cache the result as we may not have useful information yet (for example
+  // after a Global-ISel fallback).
+  if (MF.empty())
+    return false;
+
   if (!mayNeedAGPRs()) {
     UsesAGPRs = false;
     return false;
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.gfx950.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.gfx950.ll
index d9ee276c3f076e..44cb4e803ffad6 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.gfx950.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.gfx950.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
 ; RUN: llc -mtriple=amdgcn -mcpu=gfx950 -global-isel=0 < %s | FileCheck -enable-var-scope --check-prefixes=GCN,SDAG %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx950 -global-isel=1 -global-isel-abort=2 < %s | FileCheck -enable-var-scope --check-prefixes=GCN,GISEL %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx950 -global-isel=1 -global-isel-abort=2 -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,GISEL %s
 
 declare <4 x float> @llvm.amdgcn.mfma.f32.16x16x32.f16(<8 x half>, <8 x half>, <4 x float>, i32 immarg, i32 immarg, i32 immarg)
 declare <16 x float> @llvm.amdgcn.mfma.f32.32x32x16.f16(<8 x half>, <8 x half>, <16 x float>, i32 immarg, i32 immarg, i32 immarg)

``````````

</details>


https://github.com/llvm/llvm-project/pull/124799