PACKAGES.TXT; Fri Apr 18 15:15:17 UTC 2025 PACKAGE NAME: AMDMIGraphX-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 46556 K PACKAGE SIZE (uncompressed): 546140 K PACKAGE DESCRIPTION: AMDMIGraphX: AMDMIGraphX (AMD MIGraphX) AMDMIGraphX: AMDMIGraphX: AMD MIGraphX is AMDs graph inference engine, which accelerates AMDMIGraphX: machine learning model inference. To use MIGraphX, you can install AMDMIGraphX: the binaries or build from source code. Refer to the following AMDMIGraphX: sections for Ubuntu installation instructions (well provide AMDMIGraphX: instructions for other Linux distributions in the future). AMDMIGraphX: AMDMIGraphX: AMDMIGraphX: AMDMIGraphX: PACKAGE NAME: MIOpen-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 184216 K PACKAGE SIZE (uncompressed): 1562650 K PACKAGE DESCRIPTION: MIOpen: MIOpen (AMDs Machine Intelligence Library (HIP backend)) MIOpen: MIOpen: MIOpen is AMDs library for high-performance machine learning MIOpen: primitives. MIOpen: MIOpen: MIOpen: MIOpen: MIOpen: MIOpen: MIOpen: PACKAGE NAME: MIVisionX-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 54328 K PACKAGE SIZE (uncompressed): 174640 K PACKAGE DESCRIPTION: MIVisionX: MIVisionX (MIVisionX) MIVisionX: MIVisionX: MIVisionX toolkit is a set of comprehensive computer vision and MIVisionX: machine intelligence libraries, utilities, and applications bundled MIVisionX: into a single toolkit. AMD MIVisionX delivers highly optimized MIVisionX: conformant open-source implementation of the Khronos OpenVX™ and MIVisionX: OpenVX™ Extensions along with Convolution Neural Net Model Compiler MIVisionX: & Optimizer supporting ONNX, and Khronos NNEF™ exchange formats. MIVisionX: MIVisionX: MIVisionX: PACKAGE NAME: ROCdbgapi-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 372 K PACKAGE SIZE (uncompressed): 1670 K PACKAGE DESCRIPTION: rocm-dbgapi: ROCdbgapi (AMD Debugger API (ROCdbgapi)) rocm-dbgapi: rocm-dbgapi: The AMD Debugger API is a library that provides all the support rocm-dbgapi: necessary for a debugger and other tools to perform low level control rocm-dbgapi: of the execution and inspection of execution state of AMDs rocm-dbgapi: commercially available GPU architectures. rocm-dbgapi: rocm-dbgapi: rocm-dbgapi: rocm-dbgapi: rocm-dbgapi: PACKAGE NAME: ROCgdb-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 53280 K PACKAGE SIZE (uncompressed): 226470 K PACKAGE DESCRIPTION: ROCgdb: ROCgdb (ROCm source-level debugger for Linux, based on GDB) ROCgdb: ROCgdb: ROCgdb: ROCgdb: ROCgdb: ROCgdb: ROCgdb: ROCgdb: ROCgdb: ROCgdb: PACKAGE NAME: ROCmValidationSuite-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 800 K PACKAGE SIZE (uncompressed): 6210 K PACKAGE DESCRIPTION: rocmvalidationsuite: ROCmValidationSuite rocmvalidationsuite: rocmvalidationsuite: The ROCm Validation Suite (RVS) is a system validation and diagnostics rocmvalidationsuite: tool for monitoring, stress testing, detecting and troubleshooting rocmvalidationsuite: issues that affects the functionality and performance of AMD GPU(s) rocmvalidationsuite: operating in a high-performance/AI/ML computing environment. RVS is rocmvalidationsuite: enabled using the ROCm software stack on a compatible software and rocmvalidationsuite: hardware platform. rocmvalidationsuite: rocmvalidationsuite: rocmvalidationsuite: PACKAGE NAME: TransferBench-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 160 K PACKAGE SIZE (uncompressed): 3210 K PACKAGE DESCRIPTION: TransferBench: TransferBench (TransferBench) TransferBench: TransferBench: TransferBench is a utility for benchmarking simultaneous copies TransferBench: between user-specified CPU and GPU devices. TransferBench: TransferBench: TransferBench: TransferBench: TransferBench: TransferBench: TransferBench: PACKAGE NAME: amdgpu-pro-25.10-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 42908 K PACKAGE SIZE (uncompressed): 220830 K PACKAGE DESCRIPTION: amdgpu-pro: amdgpu-pro (AMDGPU Pro Advanced Multimedia Framework) amdgpu-pro: amdgpu-pro: amdgpu contain AMDGPU Pro libraries amdgpu-pro: amdgpu-pro: Do not replace the system libraries, the X works but Wayland does not. amdgpu-pro: amdgpu-pro: amdgpu-pro: amdgpu-pro: amdgpu-pro: This is the BINARY VERSION amdgpu-pro: PACKAGE NAME: amdsmi-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 696 K PACKAGE SIZE (uncompressed): 5760 K PACKAGE DESCRIPTION: amdsmi: amdsmi (AMD System Management Interface library) amdsmi: amdsmi: The AMD System Management Interface (AMD SMI) library offers a unified amdsmi: tool for managing and monitoring GPUs, particularly in amdsmi: high-performance computing environments. It provides a user-space amdsmi: interface that allows applications to control GPU operations, amdsmi: monitor performance, and retrieve information about the systems amdsmi: drivers and GPUs. amdsmi: amdsmi: amdsmi: PACKAGE NAME: composable_kernel-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 891440 K PACKAGE SIZE (uncompressed): 3748570 K PACKAGE DESCRIPTION: composable_kernel: composable_kernel (High Performance Composable Kernel for AMD GPUs) composable_kernel: composable_kernel: The Composable Kernel (CK) library provides a programming model for composable_kernel: writing performance-critical kernels for machine learning workloads composable_kernel: across multiple architectures (GPUs, CPUs, etc.). The CK library composable_kernel: uses general purpose kernel languages, such as HIP C++. composable_kernel: composable_kernel: composable_kernel: composable_kernel: composable_kernel: PACKAGE NAME: half-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 20 K PACKAGE SIZE (uncompressed): 160 K PACKAGE DESCRIPTION: half: half (HALF-PRECISION FLOATING POINT LIBRARY) half: half: This is a C++ header-only library to provide an IEEE 754 conformant half: 16-bit half-precision floating point type along with corresponding half: arithmetic operators, type conversions and common mathematical half: functions. It aims for both efficiency and ease of use, trying to half: accurately mimic the behaviour of the builtin floating point types at half: the best performance possible. half: half: half: PACKAGE NAME: hip-runtime-amd-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 6216 K PACKAGE SIZE (uncompressed): 30300 K PACKAGE DESCRIPTION: hip-runtime-amd: Heterogeneous Interface for Portability ROCm (hip-runtime-amd) hip-runtime-amd: hip-runtime-amd: HIP is a C++ Runtime API and Kernel Language that allows developers hip-runtime-amd: to create portable applications for AMD and NVIDIA GPUs from single hip-runtime-amd: source code. hip-runtime-amd: hip-runtime-amd: hip-runtime-amd: hip-runtime-amd: hip-runtime-amd: hip-runtime-amd: PACKAGE NAME: hipBLAS-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 224 K PACKAGE SIZE (uncompressed): 4230 K PACKAGE DESCRIPTION: hipBLAS: hipBLAS (Basic Linear Algebra Subprograms) hipBLAS: hipBLAS: hipBLAS is a Basic Linear Algebra Subprograms (BLAS) marshalling hipBLAS: library with multiple supported backends. It sits between your hipBLAS: application and a worker BLAS library, where it marshals inputs to hipBLAS: the backend library and marshals results to your application. hipBLAS hipBLAS: exports an interface that doesnt require the client to change, hipBLAS: regardless of the chosen backend. Currently, hipBLAS supports rocBLAS hipBLAS: and cuBLAS backends. hipBLAS: PACKAGE NAME: hipBLAS-common-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 8 K PACKAGE SIZE (uncompressed): 30 K PACKAGE DESCRIPTION: hipBLAS-common: hipBLAS-common hipBLAS-common: hipBLAS-common: Common files shared by hipBLAS and hipBLASLt hipBLAS-common: hipBLAS-common: hipBLAS-common: hipBLAS-common: hipBLAS-common: hipBLAS-common: hipBLAS-common: hipBLAS-common: PACKAGE NAME: hipBLASLt-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 984 K PACKAGE SIZE (uncompressed): 9510 K PACKAGE DESCRIPTION: hipBLASLt: hipBLASLt (hipBLASLt) hipBLASLt: hipBLASLt: General matrix-matrix operations beyond a traditional BLAS library hipBLASLt: hipBLASLt is exposed APIs in HIP programming language with an hipBLASLt: an underlying optimized generator as a backend kernel provider. hipBLASLt: hipBLASLt: This library adds flexibility in matrix data layouts, input types, hipBLASLt: compute types, and also in choosing the algorithmic implementations hipBLASLt: and heuristics through parameter programmability. hipBLASLt: hipBLASLt: PACKAGE NAME: hipBLASLt-old-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 24 K PACKAGE SIZE (uncompressed): 210 K PACKAGE DESCRIPTION: hipBLASLt: hipBLASLt (hipBLASLt) hipBLASLt: hipBLASLt: General matrix-matrix operations beyond a traditional BLAS library hipBLASLt: hipBLASLt is exposed APIs in HIP programming language with an hipBLASLt: an underlying optimized generator as a backend kernel provider. hipBLASLt: hipBLASLt: This library adds flexibility in matrix data layouts, input types, hipBLASLt: compute types, and also in choosing the algorithmic implementations hipBLASLt: and heuristics through parameter programmability. hipBLASLt: hipBLASLt: PACKAGE NAME: hipCUB-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 76 K PACKAGE SIZE (uncompressed): 1400 K PACKAGE DESCRIPTION: hipCUB: hipCUB (Header-only library on top of rocPRIM or CUB) hipCUB: hipCUB: hipCUB is a thin wrapper library on top of rocPRIM or CUB. You can hipCUB: use it to port a CUB project into HIP so you can use AMD hardware hipCUB: (and ROCm software). hipCUB: hipCUB: In the ROCm environment, hipCUB uses the rocPRIM library as the hipCUB: backend. On CUDA platforms, it uses CUB as the backend. hipCUB: hipCUB: PACKAGE NAME: hipFFT-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 36 K PACKAGE SIZE (uncompressed): 160 K PACKAGE DESCRIPTION: hipFFT: hipFFT (rocFFT marshalling library) hipFFT: hipFFT: hipFFT is an FFT marshalling library that supports rocFFT and cuFFT hipFFT: backends. hipFFT: hipFFT: hipFFT exports an interface that doesnt require the client to change, hipFFT: regardless of the chosen backend. It sits between your application and hipFFT: the backend FFT library, where it marshals inputs to the backend and hipFFT: marshals results back to your application. hipFFT: hipFFT: PACKAGE NAME: hipRAND-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 28 K PACKAGE SIZE (uncompressed): 240 K PACKAGE DESCRIPTION: hipRAND: hipRAND (rocRAND marshalling library) hipRAND: hipRAND: hipRAND is a RAND marshalling library with multiple supported hipRAND: backends. It sits between your application and the backend RAND hipRAND: library, where it marshals inputs to the backend and results to the hipRAND: application. hipRAND exports an interface that doesnt require the hipRAND: client to change, regardless of the chosen backend. hipRAND: hipRAND: hipRAND supports rocRAND and cuRAND. hipRAND: hipRAND: PACKAGE NAME: hipSOLVER-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 72 K PACKAGE SIZE (uncompressed): 730 K PACKAGE DESCRIPTION: hipSOLVER: hipSOLVER (rocSOLVER marshalling library.) hipSOLVER: hipSOLVER: hipSOLVER is a LAPACK marshalling library, with multiple supported hipSOLVER: backends. It sits between the application and a worker LAPACK hipSOLVER: library, marshalling inputs into the backend library and marshalling hipSOLVER: results back to the application. hipSOLVER exports an interface that hipSOLVER: does not require the client to change, regardless of the chosen hipSOLVER: backend. Currently, hipSOLVER supports rocSOLVER and cuSOLVER as hipSOLVER: backends. hipSOLVER: PACKAGE NAME: hipSPARSE-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 1204 K PACKAGE SIZE (uncompressed): 6160 K PACKAGE DESCRIPTION: hipSPARSE: hipSPARSE (rocSPARSE marshalling library.) hipSPARSE: hipSPARSE: hipSPARSE is a SPARSE marshalling library with multiple supported hipSPARSE: backends. It sits between your application and a worker SPARSE hipSPARSE: library, where it marshals inputs to the backend library and marshals hipSPARSE: results to your application. hipSPARSE exports an interface that hipSPARSE: does not require the client to change, regardless of the chosen hipSPARSE: backend. Currently, hipSPARSE supports rocSPARSE and cuSPARSE hipSPARSE: backends. hipSPARSE: hipSPARSE: PACKAGE NAME: hipTensor-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 64272 K PACKAGE SIZE (uncompressed): 257870 K PACKAGE DESCRIPTION: hipTensor: hipTensor (hipTensor) hipTensor: hipTensor: hiptensor is AMDs C++ library for accelerating tensor primitives hipTensor: using GPU matrix cores on AMDs latest discrete GPUs. hipTensor: hipTensor: hipTensor: hipTensor: hipTensor: hipTensor: hipTensor: PACKAGE NAME: hipfort-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 10844 K PACKAGE SIZE (uncompressed): 28240 K PACKAGE DESCRIPTION: hipfort: hipfort (Fortran Interface For GPU Kernel Libraries) hipfort: hipfort: This is a FORTRAN interface library for accessing GPU Kernels. hipfort: hipfort: hipfort: hipfort: hipfort: hipfort: hipfort: hipfort: PACKAGE NAME: hipify-clang-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 16000 K PACKAGE SIZE (uncompressed): 71040 K PACKAGE DESCRIPTION: hipify: hipify (Convert CUDA to Portable C++ Code) hipify: hipify: HIPIFY is a set of tools that you can use to automatically translate hipify: CUDA source code into portable HIP C++. hipify: hipify: hipify: hipify: hipify: hipify: hipify: PACKAGE NAME: hsa-amd-aqlprofile-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 292 K PACKAGE SIZE (uncompressed): 1400 K PACKAGE DESCRIPTION: hsa-amd-aqlprofile: hsa-amd-aqlprofile (AQLPROFILE library) hsa-amd-aqlprofile: hsa-amd-aqlprofile: AQLPROFILE library for AMD HSA runtime API extension support. hsa-amd-aqlprofile: hsa-amd-aqlprofile: hsa-amd-aqlprofile: hsa-amd-aqlprofile: hsa-amd-aqlprofile: hsa-amd-aqlprofile: hsa-amd-aqlprofile: closed source hsa-amd-aqlprofile: PACKAGE NAME: hsa-rocr-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 776 K PACKAGE SIZE (uncompressed): 4530 K PACKAGE DESCRIPTION: hsa-rocr: hsa-rocr (HSA Runtime API and runtime for ROCm) hsa-rocr: hsa-rocr: API interfaces and libraries necessary for host applications to hsa-rocr: launch compute kernels to available HSA ROCm kernel agents. Reference hsa-rocr: source code for the core runtime is also available. hsa-rocr: hsa-rocr: hsa-rocr: hsa-rocr: hsa-rocr: hsa-rocr: PACKAGE NAME: libva-amdgpu-dev-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 220 K PACKAGE SIZE (uncompressed): 1310 K PACKAGE DESCRIPTION: libva-amdgpu-dev: libva-amdgpu-dev (VA AMD GPU) libva-amdgpu-dev: libva-amdgpu-dev: Varios packages from AMD libva-amdgpu-dev: libva-amdgpu-dev: libva-amdgpu-dev: libva-amdgpu-dev: libva-amdgpu-dev: libva-amdgpu-dev: libva-amdgpu-dev: closed source libva-amdgpu-dev: PACKAGE NAME: rapidjson-git_20241222_24b5e7a8-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 1140 K PACKAGE SIZE (uncompressed): 18950 K PACKAGE DESCRIPTION: rapidjson: RapidJSON (RapidJSON) rapidjson: rapidjson: A fast JSON parser/generator for C++ with both SAX/DOM style API rapidjson: rapidjson: rapidjson: rapidjson: rapidjson: rapidjson: rapidjson: rapidjson: PACKAGE NAME: rccl-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 12048 K PACKAGE SIZE (uncompressed): 405750 K PACKAGE DESCRIPTION: rccl: rccl (ROCm Communication Collectives Library) rccl: rccl: RCCL (pronounced 'Rickle') is a stand-alone library of standard rccl: collective communication routines for GPUs, implementing all-reduce, rccl: all-gather, reduce, broadcast, reduce-scatter, gather, scatter, and rccl: all-to-all. There is also initial support for direct GPU-to-GPU send rccl: and receive operations. rccl: rccl: rccl: rccl: PACKAGE NAME: rdc-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 9568 K PACKAGE SIZE (uncompressed): 51080 K PACKAGE DESCRIPTION: rdc: rdc (ROCmTM Data Center Tool) rdc: rdc: The ROCm™ Data Center Tool simplifies the administration and addresses rdc: key infrastructure challenges in AMD GPUs in cluster and datacenter rdc: environments. The main features are: rdc: rdc: GPU telemetry rdc: GPU statistics for jobs rdc: Integration with third-party tools rdc: Open source rdc: PACKAGE NAME: rocAL-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 31992 K PACKAGE SIZE (uncompressed): 39910 K PACKAGE DESCRIPTION: rocAL: rocAL (The AMD ROCm Augmentation Library) rocAL: rocAL: The AMD ROCm Augmentation Library (rocAL) is designed to efficiently rocAL: decode and process images and videos from a variety of storage formats rocAL: and modify them through a processing graph programmable by the user. rocAL: rocAL currently provides C API. rocAL: rocAL: rocAL: rocAL: rocAL: PACKAGE NAME: rocALUTION-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 5108 K PACKAGE SIZE (uncompressed): 107910 K PACKAGE DESCRIPTION: rocALUTION: rocALUTION (Next generation library for iterative sparse solvers) rocALUTION: rocALUTION: rocALUTION is a sparse linear algebra library that can be used to rocALUTION: explore fine-grained parallelism on top of the ROCm platform runtime rocALUTION: and toolchains. Based on C++ and HIP, rocALUTION provides a portable, rocALUTION: generic, and flexible design that allows seamless integration with rocALUTION: other scientific software packages. rocALUTION: rocALUTION: rocALUTION: PACKAGE NAME: rocBLAS-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 110468 K PACKAGE SIZE (uncompressed): 4007170 K PACKAGE DESCRIPTION: rocBLAS: rocBLAS (Next generation BLAS implementation for ROCm platform) rocBLAS: rocBLAS: rocBLAS is the ROCm Basic Linear Algebra Subprograms (BLAS) library. rocBLAS: rocBLAS is implemented in the HIP programming language and optimized rocBLAS: for AMD GPUs. rocBLAS: rocBLAS: rocBLAS: rocBLAS: rocBLAS: rocBLAS: PACKAGE NAME: rocDecode-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 48952 K PACKAGE SIZE (uncompressed): 91600 K PACKAGE DESCRIPTION: rocDecode: rocDecode (AMD ROCm rocDecode) rocDecode: rocDecode: rocDecode is a high-performance video decode SDK for AMD GPUs. Using rocDecode: the video decoding features available on your GPU. rocDecode: rocDecode: rocDecode: rocDecode: rocDecode: rocDecode: rocDecode: PACKAGE NAME: rocFFT-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 78760 K PACKAGE SIZE (uncompressed): 1241860 K PACKAGE DESCRIPTION: rocFFT: rocFFT (Next generation FFT implementation for ROCm) rocFFT: rocFFT: rocFFT is a software library for computing fast Fourier transforms rocFFT: (FFTs) written in the HIP programming language. It's part of AMD's rocFFT: software ecosystem based on ROCm. The rocFFT library can be used with rocFFT: AMD and NVIDIA GPUs. rocFFT: rocFFT: rocFFT: rocFFT: rocFFT: PACKAGE NAME: rocJPEG-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 4248 K PACKAGE SIZE (uncompressed): 5420 K PACKAGE DESCRIPTION: rocJPEG: rocJPEG (AMD ROCm rocJPEG) rocJPEG: rocJPEG: rocJPEG is a high performance JPEG decode SDK for AMD GPUs. Using the rocJPEG: rocJPEG API, you can access the JPEG decoding features available on rocJPEG: your GPU. rocJPEG: rocJPEG: rocJPEG: rocJPEG: rocJPEG: rocJPEG: PACKAGE NAME: rocMLIR-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 48284 K PACKAGE SIZE (uncompressed): 578500 K PACKAGE DESCRIPTION: rocMLIR: rocMLIR (MLIR-based convolution and GEMM kernel generator for ROCm) rocMLIR: rocMLIR: MLIR-based convolution and GEMM kernel generator targetting AMD rocMLIR: hardware. This generator is mainly used from MIGraphX, but it can be rocMLIR: used on a standalone basis. rocMLIR: rocMLIR: rocMLIR: rocMLIR: rocMLIR: rocMLIR: PACKAGE NAME: rocPRIM-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 268 K PACKAGE SIZE (uncompressed): 6040 K PACKAGE DESCRIPTION: rocPRIM: rocPRIM (Header-only library providing HIP parallel primitives) rocPRIM: rocPRIM: rocPRIM is a header-only library that provides HIP parallel rocPRIM: primitives. You can use this library to develop performant rocPRIM: GPU-accelerated code on AMD ROCm platforms. rocPRIM: rocPRIM: rocPRIM: rocPRIM: rocPRIM: rocPRIM: PACKAGE NAME: rocRAND-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 14612 K PACKAGE SIZE (uncompressed): 140780 K PACKAGE DESCRIPTION: rocRAND: rocRAND (Pseudo-random and quasi-random number generator on ROCm) rocRAND: rocRAND: The rocRAND project provides functions that generate pseudorandom and rocRAND: quasirandom numbers. The rocRAND library is implemented in the HIP rocRAND: programming language and optimized for AMDs latest discrete GPUs. rocRAND: It is designed to run on top of AMDs ROCm runtime, but it also works rocRAND: on CUDA-enabled GPUs. rocRAND: rocRAND: rocRAND: rocRAND: PACKAGE NAME: rocSOLVER-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 107760 K PACKAGE SIZE (uncompressed): 131760 K PACKAGE DESCRIPTION: rocSOLVER: rocSOLVER (Subset of LAPACK functionality on the ROCm platform) rocSOLVER: rocSOLVER: rocSOLVER is a work-in-progress implementation of a subset of LAPACK rocSOLVER: functionality on the ROCm platform. rocSOLVER: rocSOLVER: rocSOLVER: rocSOLVER: rocSOLVER: rocSOLVER: PACKAGE NAME: rocSPARSE-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 13904 K PACKAGE SIZE (uncompressed): 63660 K PACKAGE DESCRIPTION: rocSPARSE: rocSPARSE (BLAS for sparse computation on top of ROCm) rocSPARSE: rocSPARSE: rocSPARSE exposes a common interface that provides Basic Linear rocSPARSE: Algebra Subroutines (BLAS) for sparse computation. Its implemented rocSPARSE: on top of AMD ROCm runtime and toolchains. rocSPARSE is created rocSPARSE: using the HIP programming language and optimized for AMDs latest rocSPARSE: discrete GPUs. rocSPARSE: rocSPARSE: rocSPARSE: rocSPARSE: PACKAGE NAME: rocThrust-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 392 K PACKAGE SIZE (uncompressed): 6160 K PACKAGE DESCRIPTION: rocThrust: rocThrust (Port of Thrust parallel algorithm library atop HIP/ROCm) rocThrust: rocThrust: Thrust is a parallel algorithm library. It has been ported to HIP and rocThrust: ROCm, which use the rocPRIM library. The HIP-ported library works on rocThrust: HIP and ROCm software. Currently there is no CUDA backend in place. rocThrust: rocThrust: rocThrust: rocThrust: rocThrust: PACKAGE NAME: rocWMMA-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 80 K PACKAGE SIZE (uncompressed): 980 K PACKAGE DESCRIPTION: rocWMMA: rocWMMA (rocWMMA) rocWMMA: rocWMMA: rocWMMA is C++ library for accelerating mixed-precision matrix rocWMMA: multiply-accumulate (MMA) operations leveraging AMD GPU hardware. rocWMMA: rocWMMA makes it easier to break down MMA problems into fragments and rocWMMA: distribute block-wise MMA operations in parallel across GPU rocWMMA: wavefronts. The API consists of a header library, that can be used to rocWMMA: compile MMA acceleration directly into GPU kernel device code. This rocWMMA: can benefit from compiler optimization in the generation of kernel rocWMMA: assembly, and does not incur additional overhead costs of linking to rocWMMA: external runtime libraries or having to launch separate kernels. PACKAGE NAME: rocm-OpenMP-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 548 K PACKAGE SIZE (uncompressed): 1990 K PACKAGE DESCRIPTION: OpenMP: OpenMP (Open Multi-Processing) OpenMP: OpenMP: OpenMP (Open Multi-Processing) is an application programming interface OpenMP: (API) that supports multi-platform shared-memory multiprocessing OpenMP: programming in C, C++, and Fortran on many platforms, instruction-set OpenMP: architectures and operating systems OpenMP: It consists of a set of compiler directives, library routines, and OpenMP: environment variables that influence run-time behavior. OpenMP: OpenMP: OpenMP: PACKAGE NAME: rocm-cmake-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 24 K PACKAGE SIZE (uncompressed): 150 K PACKAGE DESCRIPTION: rocm-cmake: rocm-cmake (ROCm cmake) rocm-cmake: rocm-cmake: rocm-cmake is a collection of CMake modules for common build and rocm-cmake: development tasks within the ROCm project. It is therefore a build rocm-cmake: dependency for many of the libraries that comprise the ROCm platform. rocm-cmake: rocm-cmake: rocm-cmake is not required for building libraries or programs that rocm-cmake: use ROCm; it is required for building some of the libraries that are rocm-cmake: a part of ROCm. rocm-cmake: rocm-cmake: PACKAGE NAME: rocm-comgr-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 38220 K PACKAGE SIZE (uncompressed): 157630 K PACKAGE DESCRIPTION: comgr: Code Object Manager (comgr) comgr: comgr: The Comgr library provides APIs for compiling and inspecting AMDGPU comgr: code objects. comgr: comgr: comgr: comgr: comgr: comgr: comgr: PACKAGE NAME: rocm-core-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 12 K PACKAGE SIZE (uncompressed): 70 K PACKAGE DESCRIPTION: rocm-core: rocm-core (ROCm Core) rocm-core: rocm-core: rocm-core is a utility which can be used to get ROCm release version. rocm-core: rocm-core: rocm-core: rocm-core: rocm-core: rocm-core: rocm-core: rocm-core: PACKAGE NAME: rocm-device-libs-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 460 K PACKAGE SIZE (uncompressed): 3340 K PACKAGE DESCRIPTION: rocm-device-libs: ROCm Device Libraries rocm-device-libs: rocm-device-libs: rocm-device-libs is a collection of CMake modules for common build and rocm-device-libs: development tasks within the ROCm project. It is therefore a build rocm-device-libs: dependency for many of the libraries that comprise the ROCm platform. rocm-device-libs: rocm-device-libs: rocm-device-libs is not required for building libraries or programs that rocm-device-libs: use ROCm; it is required for building some of the libraries that are rocm-device-libs: a part of ROCm. rocm-device-libs: rocm-device-libs: PACKAGE NAME: rocm-hipcc-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 96 K PACKAGE SIZE (uncompressed): 530 K PACKAGE DESCRIPTION: hipcc: HIP compiler driver (hipcc) hipcc: hipcc: hipcc is a compiler driver utility that will call clang or nvcc, depending on hipcc: target, and pass the appropriate include and library options for the target hipcc: compiler and HIP infrastructure. hipcc: hipcc: hipcc will pass-through options to the target compiler. The tools calling hipcc hipcc: must ensure the compiler options are appropriate for the target compiler. hipcc: hipcc: hipcc: PACKAGE NAME: rocm-llvm-project-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 906860 K PACKAGE SIZE (uncompressed): 5356170 K PACKAGE DESCRIPTION: rocm-llvm: rocm-llvm (Radeon Open Compute - LLVM toolchain (llvm, clang, lld)) rocm-llvm: rocm-llvm: AMD Fork of The LLVM Compiler Infrastructure rocm-llvm: rocm-llvm: The AMD fork aims to contain all of upstream LLVM, and also includes rocm-llvm: several AMD-specific additions in the llvm-project/amd directory: rocm-llvm: rocm-llvm: amd/comgr rocm-llvm: amd/device-libs rocm-llvm: amd/hip rocm-llvm: PACKAGE NAME: rocm-opencl-runtime-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 564 K PACKAGE SIZE (uncompressed): 2360 K PACKAGE DESCRIPTION: rocm-opencl-runtime: rocm-opencl-runtime (OpenCL implementation for AMD) rocm-opencl-runtime: rocm-opencl-runtime: AMD Common Language Runtime contains source codes for AMDs compute rocm-opencl-runtime: languages runtimes: HIP and OpenCL-tm. rocm-opencl-runtime: rocm-opencl-runtime: rocm-opencl-runtime: rocm-opencl-runtime: rocm-opencl-runtime: rocm-opencl-runtime: rocm-opencl-runtime: PACKAGE NAME: rocm_bandwidth_test-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 44 K PACKAGE SIZE (uncompressed): 140 K PACKAGE DESCRIPTION: rocm_bandwidth_test: ROCm Bandwidth Test rocm_bandwidth_test: rocm_bandwidth_test: ROCm Bandwidth Test is designed to capture the performance rocm_bandwidth_test: characteristics of buffer copying and kernel read and write rocm_bandwidth_test: operations. The benchmark help screen shows various options for rocm_bandwidth_test: initiating copy, read, and write operations. In addition to this, you rocm_bandwidth_test: can also query the system topology in terms of memory pools and their rocm_bandwidth_test: agents. rocm_bandwidth_test: rocm_bandwidth_test: rocm_bandwidth_test: PACKAGE NAME: rocm_smi_lib-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 616 K PACKAGE SIZE (uncompressed): 3410 K PACKAGE DESCRIPTION: rocm-smi-lib: rocm-smi-lib (ROCm System Management Interface Library) rocm-smi-lib: rocm-smi-lib: The ROCm System Management Interface Library, or ROCm SMI library, is rocm-smi-lib: part of the Radeon Open Compute ROCm software stack . It is a C rocm-smi-lib: library for Linux that provides a user space interface for rocm-smi-lib: applications to monitor and control GPU applications. rocm-smi-lib: rocm-smi-lib: rocm-smi-lib: rocm-smi-lib: rocm-smi-lib: PACKAGE NAME: rocminfo-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 24 K PACKAGE SIZE (uncompressed): 90 K PACKAGE DESCRIPTION: rocminfo: rocminfo (ROCm Application for Reporting System Info) rocminfo: rocminfo: ROCm Application for Reporting System Info rocminfo: rocminfo: rocminfo: rocminfo: rocminfo: rocminfo: rocminfo: rocminfo: PACKAGE NAME: rocprofiler-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 1284 K PACKAGE SIZE (uncompressed): 8790 K PACKAGE DESCRIPTION: rocprofiler: rocprofiler (Profiling with perf-counters and derived metrics.) rocprofiler: rocprofiler: ROCProfiler is AMD’s tooling infrastructure that provides a hardware rocprofiler: specific low level performance analysis interface for the profiling rocprofiler: and the tracing of GPU compute applications. rocprofiler: rocprofiler: rocprofiler: rocprofiler: rocprofiler: rocprofiler: PACKAGE NAME: rocprofiler-register-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 80 K PACKAGE SIZE (uncompressed): 390 K PACKAGE DESCRIPTION: rocprofiler-register: rocprofiler-register rocprofiler-register: rocprofiler-register: The rocprofiler-register library is a helper library that coordinates rocprofiler-register: the modification of the intercept API table(s) of the HSA/HIP/ROCTx rocprofiler-register: runtime libraries by the ROCprofiler (v2) library. The purpose of rocprofiler-register: this library is to provide a consistent and automated mechanism of rocprofiler-register: enabling performance analysis in the ROCm runtimes which does not rocprofiler-register: rely on environment variables or unique methods for each runtime rocprofiler-register: library. rocprofiler-register: rocprofiler-register: PACKAGE NAME: roctracer-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 476 K PACKAGE SIZE (uncompressed): 4070 K PACKAGE DESCRIPTION: roctracer: roctracer (ROCm tracer library for performance tracing) roctracer: roctracer: ROC-tracer library: Runtimes Generic Callback/Activity APIs roctracer: The goal of the implementation is to provide a generic independent roctracer: from specific runtime profiler to trace API and asynchronous activity. roctracer: roctracer: ROC-TX library: Code Annotation Events API roctracer: Includes API for: roctracer: - roctxMark roctracer: - roctxRangePush roctracer: - roctxRangePop PACKAGE NAME: rpp-6.4.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 42164 K PACKAGE SIZE (uncompressed): 279700 K PACKAGE DESCRIPTION: rpp: rpp (AMD ROCm Performance Primitives) rpp: rpp: AMD ROCm Performance Primitives (RPP) library is a comprehensive, rpp: high-performance computer vision library for AMD processors that have rpp: HIP, OpenCL, or CPU backends. rpp: rpp: rpp: rpp: rpp: rpp: PACKAGE NAME: yaml-cpp-0.8.0-x86_64-1condor.txz PACKAGE LOCATION: . PACKAGE SIZE (compressed): 136 K PACKAGE SIZE (uncompressed): 550 K PACKAGE DESCRIPTION: yaml-cpp: yaml-cpp (yaml parser and emitter in c++) yaml-cpp: yaml-cpp: yaml-cpp is a YAML parser and emitter in C++ yaml-cpp: matching the YAML 1.2 spec. yaml-cpp: yaml-cpp: yaml-cpp: yaml-cpp: yaml-cpp: yaml-cpp: yaml-cpp home: https://github.com/jbeder/yaml-cpp yaml-cpp: