rocRAND

rocRAND code for ROCm 6.1.1 did not change. The library was rebuilt for the updated ROCm 6.1.1 stack.

Fixes

• Implemented workaround for regressions in XORWOW and LFSR on MI200

rocRAND code for ROCm 6.0.2 did not change. The library was rebuilt for the updated ROCm 6.0.2 stack.

rocRAND code for ROCm 6.0.0 did not change. The library was rebuilt for the updated ROCm 6.0.0 stack.

rocRAND code for ROCm 5.7.1 did not change. The library was rebuilt for the updated ROCm 5.7.1 stack.

rocRAND code for ROCm 5.7.0 did not change. The library was rebuilt for the updated ROCm 5.7.0 stack.

rocRAND code for ROCm 5.6.1 did not change. The library was rebuilt for the updated ROCm 5.6.1 stack.

rocRAND code for ROCm 5.6.0 did not change. The library was rebuilt for the updated ROCm 5.6.0 stack.

rocRAND code for ROCm 5.5.1 did not change. The library was rebuilt for the updated ROCm 5.5.1 stack.

Added

• MT19937 pseudo random number generator based on M. Matsumoto and T. Nishimura, 1998, Mersenne Twister: A 623-dimensionally equidistributed uniform pseudorandom number generator.
• New benchmark for the device API using Google Benchmark, benchmark_rocrand_device_api, replacing benchmark_rocrand_kernel. benchmark_rocrand_kernel is deprecated and will be removed in a future version. Likewise, benchmark_curand_host_api is added to replace benchmark_curand_generate and benchmark_curand_device_api is added to replace benchmark_curand_kernel.
• experimental HIP-CPU feature
• ThreeFry pseudorandom number generator based on Salmon et al., 2011, "Parallel random numbers: as easy as 1, 2, 3".

Changed

• Python 2.7 is no longer officially supported.

Fixed

• Windows HIP SDK support

rocRAND code for ROCm 5.4.4 did not change. The library was rebuilt for the updated ROCm 5.4.4 stack.

rocRAND code for ROCm 5.4.3 did not change. The library was rebuilt for the updated ROCm 5.4.3 stack.

rocRAND code for ROCm 5.4.2 did not change. The library was rebuilt for the updated ROCm 5.4.2 stack.

rocRAND code for ROCm 5.3.1 did not change. The library was rebuilt for the updated ROCm 5.3.1 stack.

Changed

• Increased number of warmup iterations for rocrand_benchmark_generate from 5 to 15 to eliminate corner cases that would generate artificially high benchmark scores.

rocRAND code for ROCm 5.2.3 did not change. The library was rebuilt for the updated ROCm 5.2.3 stack.

rocRAND code for ROCm 5.2.1 did not change. The library was rebuilt for the updated ROCm 5.2.1 stack.

rocRAND code for ROCm 5.1.3 did not change. The library was rebuilt for the updated ROCm 5.1.3 stack.

rocRAND code for ROCm 5.1.1 did not change. The library was rebuilt for the updated ROCm 5.1.1 stack.

Added

• Generating a random sequence different sizes now produces the same sequence without gaps
  indepent of how many values are generated per call.
  • Only in the case of XORWOW, MRG32K3A, PHILOX4X32_10, SOBOL32 and SOBOL64
  • This only holds true if the size in each call is a divisor of the distributions
    output_width due to performance
  • Similarly the output pointer has to be aligned to output_width * sizeof(output_type)

Changed

• hipRAND split into a separate package
• Header file installation location changed to match other libraries.
  • Using the rocrand.h header file should now use #include <rocrand/rocrand.h>, rather than #include <rocrand/rocrand.h>
• rocRAND still includes hipRAND using a submodule
  • The rocRAND package also sets the provides field with hipRAND, so projects which require hipRAND can begin to specify it.

Fixed

• Fix offset behaviour for XORWOW, MRG32K3A and PHILOX4X32_10 generator, setting offset now
  correctly generates the same sequence starting from the offset.
  • Only uniform int and float will work as these can be generated with a single call to the generator

Known issues

• kernel_xorwow unit test is failing for certain GPU architectures.