Following tables summarize the list of supported features and dependencies for the AOCL libraries:
Library/Feature |
Vector |
Dynamic Dispatcher |
Precision |
ISA Optional Selection by the User |
|---|---|---|---|---|
AOCL-BLAS |
AVX2, AVX512 |
Yes |
Single, Double, Complex, Double Complex. Mixed Precision, and Low Precision (INT16, INT8, UINT8, BFLOAT16) - currently supported only for GEMM and GEMV APIs. |
Yes, using AOCL_ENABLE_ INSTRUCTION |
AOCL-Compression |
AVX2, AVX512 |
Yes |
N/A |
Yes, using AOCL_ENABLE_ INSTRUCTION |
AOCL-Cryptography |
AVX2, AVX512 |
Yes |
N/A |
Yes, using AOCL_ENABLE_ INSTRUCTION |
AOCL-DA |
AVX2, AVX512 |
Yes |
Single, Double |
Use AOCL_DA_ARCH to select Zen-specific code paths. Use AOCL_ENABLE_ INSTRUCTION for the underlying BLAS library |
AOCL-DLP |
AVX2, AVX512 |
Yes |
Low Precision |
Yes using AOCL_ENABLE_ INSTRUCTION |
AOCL-FFTW |
AVX2, AVX512 |
Yes for Linux with GCC and AOCC. No for Windows with Clang. MSVC compiler has not been used on Windows. |
Single, Double, Long-double, Quad |
No |
AOCL-FFTZ |
AVX128, AVX256, AVX512 |
Yes |
Single, Double |
No |
AOCL-LAPACK |
AVX2, AVX512 |
Partially (requires AVX2 support) |
Single, Double, Complex, Double Complex |
Yes, using AOCL_ENABLE_ INSTRUCTION |
AOCL-LibM |
AVX2, AVX512 |
Yes |
Single, Double, Complex, Double Complex |
No |
AOCL-LibMem |
AVX2, AVX512 |
Yes |
N/A |
No |
AOCL-RNG |
AVX2, AVX512 |
Yes |
Single, Double, Integer |
Yes, using AOCL_ENABLE_ INSTRUCTION |
AOCL-ScaLAPACK |
Dependent on the underlying BLAS and LAPACK libraries |
Dependent on the underlying BLAS and LAPACK libraries |
Single, Double, Complex, Double Complex |
Dependent on the underlying BLAS and LAPACK libraries |
AOCL-SecureRNG |
N/A |
N/A |
N/A |
N/A |
AOCL-Sparse |
AVX2, AVX512 |
Partial (only for selected APIs) |
Single, Double, Complex, Double Complex |
Partial (only for selected APIs) using AOCL_ENABLE_ INSTRUCTION |
AOCL-Utils |
N/A |
N/A |
N/A |
N/A |
Library/Feature |
glibc Dependency |
Single-threaded |
Multi-threaded |
MPI |
|---|---|---|---|---|
AOCL-BLAS |
Yes |
Yes |
Yes |
No |
AOCL-Compression |
Yes |
Yes |
Partial (for LZ4, LZ4HC, Snappy, ZLIB, and ZSTD) |
No |
AOCL-Cryptography |
Yes |
Yes |
No |
No |
AOCL-DA |
Yes |
Yes |
Yes |
No |
AOCL-DLP |
Yes |
Yes |
Yes |
No |
AOCL-FFTW |
Yes |
Yes |
Yes |
Yes |
AOCL-FFTZ |
Yes |
Yes |
Yes |
No |
AOCL-LAPACK |
Yes |
Yes |
Yes |
No |
AOCL-LibM |
Yes |
Yes |
No |
No |
AOCL-LibMem |
Yes |
Yes |
No |
No |
AOCL-RNG |
Yes |
Yes |
No |
No |
AOCL-ScaLAPACK |
Yes |
Yes, dependent on the underlying BLAS and LAPACK libraries |
Yes, dependent on the underlying BLAS and LAPACK libraries |
Yes |
AOCL-SecureRNG |
No |
Yes |
No |
No |
AOCL-Sparse |
Yes |
Yes |
Partial (only for selected APIs) |
No |
AOCL-Utils |
Yes |
Yes |
No |
No |
Dynamic Dispatch facilitates building a single binary compatible with all the AMD “Zen” architectures. At runtime, this feature enables optimizations specific to the detected AMD “Zen” architecture.
You can find the flags to enable/disable (the applicable features in AOCL Feature Support Matrix - 1 and AOCL Feature Support Matrix - 2) in the individual library sections.
Additionally, AMD provides Spack (https://spack.io/) recipes for installing AOCL-BLAS, AOCL-Compression, AOCL-Cryptography, AOCL-DA, AOCL-FFTW, AOCL-FFTZ, AOCL-DLP, AOCL-LAPACK, AOCL-LibM, AOCL-ScaLAPACK, AOCL-Sparse, and AOCL-Utils libraries.
For more information on the AOCL release and installers, refer the AMD Developer Central (https://www.amd.com/en/developer/aocl.html).
For any issues or queries on the libraries, send an email to toolchainsupport@amd.com.
To determine the underlying architecture of your AMD system, refer to Check AMD Server Processor Architecture.