[llvm-branch-commits] [llvm] AMDGPU: Mark strict_fp16_to_fp as expand (PR #177417)

[Matt Arsenault via llvm-branch-commits]

https://github.com/arsenm created https://github.com/llvm/llvm-project/pull/177417

This prevents a regression in a future change.

>From 2a174aa04469a9aed5da143753adbd1234c20dc0 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault at amd.com>
Date: Thu, 22 Jan 2026 18:31:05 +0100
Subject: [PATCH] AMDGPU: Mark strict_fp16_to_fp as expand

This prevents a regression in a future change.
---
 llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
index c5e720ce26bc0..d61eb9d11937b 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -481,7 +481,8 @@ AMDGPUTargetLowering::AMDGPUTargetLowering(const TargetMachine &TM,
        MVT::v4i64,  MVT::v8f64,  MVT::v8i64,  MVT::v16f64, MVT::v16i64},
       Custom);
 
-  setOperationAction(ISD::FP16_TO_FP, MVT::f64, Expand);
+  setOperationAction({ISD::FP16_TO_FP, ISD::STRICT_FP16_TO_FP}, MVT::f64,
+                     Expand);
   setOperationAction(ISD::FP_TO_FP16, {MVT::f64, MVT::f32}, Custom);
 
   const MVT ScalarIntVTs[] = { MVT::i32, MVT::i64 };