AOCL-DLP

AOCL-DLP (Deep Learning Primitives) is a high-performance library that provides optimized deep learning primitives for AMD processors. The library implements Low Precision GEMM (LPGEMM) operations for deep learning applications with support for multiple data types, post-operations, and quantization techniques. Select kernels have been optimized for AMD EPYC™  processors, leveraging AVX2, AVX512, AVX512_VNNI, and AVX512_BF16 instruction sets.

AOCL-DLP provides APIs for GEMM operations with various precision formats, comprehensive post-operations for fused computations, batch GEMM support, symmetric quantization routines, and parallel execution via OpenMP.

Highlights of AOCL-DLP 5.3

• Added new GEMM APIs for pure FP16, F32×S8, BF16×S8→BF16 (with on-the-fly quantization), and BF16×U4 asymmetric weight-only quantization
• Delivered full JIT code generation for S8×S8 and U8×S8 GEMM/GEMV paths, including post-ops and column-major support
• Optimized BF16 and F32 JIT generators with AVX-512 GEMV, RD/k=1 kernel frameworks, BF16×S4 WOQ JIT, and batch GEMM JIT for int8
• Improved multi-threading with new thread-local/library-level APIs, smart factorization, PGO support, and small matrix optimizations

You can find the package containing AOCL-DLP Library binaries that include optimizations for AMD processors, examples, and documentation in the Downloads section.

Documentation

• AOCL-DLP API Guide
• Source code: GitHub
• Wiki: Github Wiki

Downloads