Prominent Intel Compiler Engineer Heads Off To AMD
James Brodman worked for the last 15 years at Intel on their ISPC SIMD compiler and then in more recent years on the Intel DPC++ compiler and SYCL support as part of Intel's oneAPI initiative. Rather interestingly, this compiler expert has now joined AMD.
James Brodman announced last week on LinkedIn that he was leaving Intel and recapped his years of working on ISPC and then SYCL/DPC++ as a big part of their modern oneAPI initiative for programming across different hardware and even SYCL on competitor hardware platforms.
Brodman also co-authored a book on SYCL and Data Parallel C++ during his tenure at Intel.
It turns out he was heading off to AMD. He confirmed yesterday he joined AMD as a Fellow.
Brodman didn't outline what his plans are at AMD but presumably still in the compiler realm with a focus on parallel programming. It will be interesting to see what AMD has cooking on the compiler front -- there's been increasing activity for many months now from MLIR and IREE to enhancing their AMDGPU back-end -- and what improvements could be coming around their SYCL support and given his experience would be a big asset for enhancing their LLVM-based compiler efforts for ROCm and AMDXDNA.
James Brodman announced last week on LinkedIn that he was leaving Intel and recapped his years of working on ISPC and then SYCL/DPC++ as a big part of their modern oneAPI initiative for programming across different hardware and even SYCL on competitor hardware platforms.
Brodman also co-authored a book on SYCL and Data Parallel C++ during his tenure at Intel.
It turns out he was heading off to AMD. He confirmed yesterday he joined AMD as a Fellow.
Brodman didn't outline what his plans are at AMD but presumably still in the compiler realm with a focus on parallel programming. It will be interesting to see what AMD has cooking on the compiler front -- there's been increasing activity for many months now from MLIR and IREE to enhancing their AMDGPU back-end -- and what improvements could be coming around their SYCL support and given his experience would be a big asset for enhancing their LLVM-based compiler efforts for ROCm and AMDXDNA.