[llvm] [AMDGPU] Price only the fmul that fuses into an fadd/fsub as free (PR #226009)

[Dmitry Sidorov via llvm-commits]

================
@@ -0,0 +1,36 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
+; RUN: opt -passes=slp-vectorizer -S -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -slp-threshold=1 < %s | FileCheck %s
+; RUN: opt -passes=slp-vectorizer -S -mtriple=amdgcn-amd-amdhsa -mcpu=gfx942 -slp-threshold=1 < %s | FileCheck %s
+; RUN: opt -passes=slp-vectorizer -S -mtriple=amdgcn-amd-amdhsa -mcpu=gfx950 -slp-threshold=1 < %s | FileCheck %s
----------------
MrSidims wrote:

Why -slp-threshold=1?

https://github.com/llvm/llvm-project/pull/226009