[llvm] [AMDGPU] Create an AMDGPUIfConverter pass (PR #106415)

[Jay Foad via llvm-commits]

Juan Manuel Martinez =?utf-8?q?Caamaño?= <juamarti at amd.com>,
Juan Manuel Martinez =?utf-8?q?Caamaño?= <juamarti at amd.com>,
Juan Manuel Martinez =?utf-8?q?Caamaño?= <juamarti at amd.com>,
Juan Manuel Martinez =?utf-8?q?Caamaño?= <juamarti at amd.com>,
Juan Manuel Martinez =?utf-8?q?Caamaño?= <juamarti at amd.com>
Message-ID:
In-Reply-To: <llvm.org/llvm/llvm-project/pull/106415 at github.com>


jayfoad wrote:

Could you always generate v_cmp in this pass, and rely on `SIOptimizeExecMasking::tryRecordVCmpxAndSaveexecSequence` to convert it to v_cmpx if it's profitable? On GFX10.1 it's generally not a good idea to use v_cmpx because FeatureVcmpxExecWARHazard means you have to insert an s_wait_depctr instruction before it, which negates any performance imrpovement.

https://github.com/llvm/llvm-project/pull/106415