Skip to main content

software catalog

AI on Intel® D-Series GPU

Developer tools for Intel® GPU

Write the kernel. Find the bottleneck. Install the stack in one command.

Explore

GoalIdentify performance bottlenecks at the model and operator levelRecommended toolPyTorch Profiler
GoalDeep performance analysis with visibility into compute utilization, memory bandwidth, occupancy, and hardware stallsRecommended toolIntel® VTune™ ProfilerDetails
GoalFirst pass diagnosis of GPU dispatch, communication, and idle time issuesRecommended toolIntel® VTune™ LiteDetails
GoalInstrument Intel GPU softwareRecommended toolPTI for GPUDetails
GoalDebug GPU kernels and offload executionRecommended toolIntel® Distribution for GDBDetails
GoalWrite portable custom GPU kernels in the Triton kernel programming languageRecommended toolIntel XPU Backend for TritonDetails
GoalWrite custom Intel GPU kernels in C++ with SYCLRecommended toolSYCLDetails
GoalBuild optimized GEMM and attention kernels with SYCL*TLA, a CUTLASS-comparable C++ template libraryRecommended toolSYCL*TLADetails

Trademark notice

Intel, the Intel logo, Xeon, Arc, Xe, VTune and oneAPI are trademarks of Intel Corporation or its subsidiaries. SYCL, OpenCL and SPIR-V are trademarks of the Khronos Group. CUDA, CUTLASS, CuTe, Nsight, NCCL, cuDNN, cuBLAS, DCGM and Dynamo are trademarks or product names of NVIDIA Corporation. PyTorch, Triton and vLLM are projects of the Linux Foundation or their respective maintainers. Linux is a registered trademark of Linus Torvalds. Kubernetes is a registered trademark of the Linux Foundation. OpenShift is a trademark of Red Hat, Inc. Other names and brands may be claimed as the property of others.