Compiler profile guided optimization (PGO) techniques have paid off well for increasing CPU performance via application/workload-specific profiles fed back to the compiler to make more informed decisions. AMD compiler engineers have been working on crafting device-side PGO for their AMDGPU LLVM back-end for allowing ROCm/HIP workloads to achieve greater GPU performance. An initial merge request is now open for upstream LLVM...
Source: https://www.phoronix.com/news/AMD-LLVM-Device-Side-PGO-ROCm
Aggregated via Linux News
Source: https://www.phoronix.com/news/AMD-LLVM-Device-Side-PGO-ROCm
Aggregated via Linux News

