preview_0.92.16395

• Bug fixes in FindHIP cmake module.
• New APIs: hipRuntimeGetVersion.
• Removed following deprecated APIs: hipMallocHost, hipHostAlloc, hipFreeHost.
• Major changes to HIP signal & memory management implementation.
• Added several new samples.
• New test infrastructure.
• Documentation updates.

Notes:

• The code has been tested using HCC tagged version develop_0.10.16392.
• For convenience, a script that pulls the correct HCC and HIP code from github and builds it as well has been added to the release. To use it, simply download the script build_hcc_and_hip.sh to an empty folder on your development machine and run ./build_hcc_and_hip.sh

preview_0.92.16375

• Added support for async memcpy driver API (for example hipMemcpyHtoDAsync).
• clang-hipify support for CUDA driver memory functions.
• Initial support for HIP_ADD_LIBRARY in FindHIP.
• Documentation clean up and several updates.

Notes:

• The code has been tested using HCC develop branch commit 6e43ee8.
• For convenience, a script that pulls the correct HCC and HIP code from github and builds it as well has been added to the release. To use it, simply download the script build_hcc_and_hip.sh to an empty folder on your development machine and run ./build_hcc_and_hip.sh

preview_0.92.16365

• clang-hipify support for CUDA driver APIs.
• Improvements to module code generation.
• Hip library now installs as a static library by default.
• Some more signal management fixes.

Note: Code has been tested using HCC develop branch commit 6e43ee8.

preview_0.92.16360

• Several signal handling fixes.
• Initial support for HIP context and HIP module APIs.
• Support for complex data type and math functions.
• Updated documentation.
• Clang-hipify updates.
• Initial implementation for FindHIP.cmake

Note: Tested using HCC develop branch commit 8f82aa4.

release_0.92.00

Release:0.92.00
Date: 2016.08.14

• hipLaunchKernel supports one-dimensional grid and/or block dims, without explicit cast to dim3 type (actually in 0.90.00)
• fp16 software support
• Support for Hawaii dGPUs using environment variable ROCM_TARGET=hawaii
• Support hipArray
• Improved profiler support
• Documentation updates
• Improvements to clang-hipify

release_0.90.00

Release:0.90.00
Date: 2016.06.29

• Support dynamic shared memory allocations
• Min HCC compiler version is > 16186.
• Expanded math functions (device and host). Document unsupported functions.
• hipFree with null pointer initializes runtime and returns success.
• Improve error code reporting on nvcc.
• Add hipPeekAtError for nvcc.

release_0.86.00

Release:0.86.00
Date: 2016.06.06

• Add clang-hipify : clang-based hipify tool. Improved parsing of source code, and automates
  creation of hipLaunchParm variable.
• Implement memory register / unregister commands (hipHostRegister, hipHostUnregister)
• Add cross-linking support between G++ and HCC, in particular for interfaces that use
  standard C++ libraries (ie std::vectors, std::strings). HIPCC now uses libstdc++ by default on the HCC
  compilation path.
• More samples including gpu-burn, SHOC, nbody, rtm. See HIP-Examples

release_0.84.01

Release:0.84.01
Date: 2016.04.25

• Refactor HIP make and install system:
  • Move to CMake. Refer to the installation section in README.md for details.
  • Split source into multiple modular .cpp and .h files.
  • Create static library and link.
  • Set HIP_PATH to install.
• Make hipDevice and hipStream thread-safe.
  • Prefered hipStream usage is still to create new streams for each new thread, but it works even if you don;t.
• Improve automated platform detection: If AMD GPU is installed and detected by driver, default HIP_PLATFORM to hcc.
• HIP_TRACE_API now prints arguments to the HIP function (in addition to name of function).
• Deprecate hipDeviceGetProp (Replace with hipGetDeviceProp)
• Deprecate hipMallocHost (Replace with hipHostMalloc)
• Deprecate hipFreeHost (Replace with hipHostFree)
• The mixbench benchmark tool for measuring operational intensity now has a HIP target, in addition to CUDA and OpenCL. Let the comparisons begin. :)
  See here for more : https://github.com/ekondis/mixbench.

release_0.82.01

Release:0.82.01
Date: 2016.03.08

• Bump minimum required HCC workweek to 16074.
• Bump minimum required ROCK-Kernel-Driver and ROCR-Runtime to Developer Preview 2.
• Enable multi-GPU support.
  • Use hipSetDevice to select a device for subsequent kernel calls and memory allocations.
  • CUDA_VISIBLE_DEVICES / HIP_VISIBLE_DEVICE environment variable selects devices visible to the runtime.
• Support hipStreams – send sequences of copy and kernel commands to a device.
  • Asynchronous copies supported.
• Optimize memory copy operations.
• Support hipPointerGetAttribute – can determine if a pointer is host or device.
• Enable atomics to local memory.
• Support for LC Direct-To-ISA path.
• Improved free memory reporting.
  • hipMemGetInfo (report full memory used in current process).
  • hipDeviceReset (deletes all memory allocated by current process).