[llvm] [AMDGPU]Optimize SGPR spills (PR #93668)

Thu Jun 20 01:49:33 PDT 2024

vg0204 wrote:

> > > [kernel-hip-amdgcn-amd-amdhsa-gfx908.zip](https://github.com/user-attachments/files/15905813/kernel-hip-amdgcn-amd-amdhsa-gfx908.zip)
> > 
> > 
> > > 
> > 
> > 
> > > To accurately reproduce the assembly file, use the following clang command:
> > 
> > 
> > > 
> > 
> > 
> > > 
> > 
> > 
> > > clang -cc1 -mcode-object-version=4 -mllvm --amdhsa-code-object-version=4 -triple amdgcn-amd-amdhsa -aux-triple x86_64-unknown-linux-gnu -S -disable-free -mrelocation-model pic -pic-level 2 -mframe-pointer=none -aux-target-cpu x86-64 -mllvm -amdgpu-internalize-symbols -target-cpu gfx908 -O3 -vectorize-loops -vectorize-slp -faddrsig -o tmp.s -x ir kernel-hip-amdgcn-amd-amdhsa-gfx908.bc
> > 
> > 
> > > 
> > 
> > 
> > Getting this while trying to reproduce.
> > ![dumpError](https://private-user-images.githubusercontent.com/35700483/341291612-f09aa238-13a4-4fd9-b570-0d0606096138.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.TCRUw_nPOe5nRgpAmmVwVmzAx1pXqwfarWHPeJx-iRo)
> 
> This is due to mixing upstream and amd-staging with the different debug info

Can you please elaborate?

https://github.com/llvm/llvm-project/pull/93668