# OpenCL

OpenCL is an open, royalty-free standard and programming interface for portable parallel computing across heterogeneous processors such as CPUs and GPUs.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Tackling Parallelization Challenges of Randomized Preconditioners With Dependency Tracking

DevFeed: [Tackling Parallelization Challenges of Randomized Preconditioners With Dependency Tracking](<https://devfeed.tech/articles/tackling-parallelization-challenges-of-randomized-preconditioners-with-dependency-tracking-142957.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2505.02977>)

Author: Tianyu Liang, Chao Chen, Yotam Yaniv, Hengrui Luo, David Tench, Xiaoye S. Li, Aydin Buluc, James Demmel, Jie Chen

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [Supercomputing](<https://devfeed.tech/topics/supercomputing.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [bottleneck](<https://devfeed.tech/tags/bottleneck.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-ds](<https://devfeed.tech/tags/cs-ds.md>), [cs-na](<https://devfeed.tech/tags/cs-na.md>), [dependency](<https://devfeed.tech/tags/dependency.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [graph](<https://devfeed.tech/tags/graph.md>), [irregular](<https://devfeed.tech/tags/irregular.md>), [math-na](<https://devfeed.tech/tags/math-na.md>), [memory](<https://devfeed.tech/tags/memory.md>), [memory-management](<https://devfeed.tech/tags/memory-management.md>), [numerics](<https://devfeed.tech/tags/numerics.md>), [pattern](<https://devfeed.tech/tags/pattern.md>), [sdd](<https://devfeed.tech/tags/sdd.md>), [setup](<https://devfeed.tech/tags/setup.md>), [tracking](<https://devfeed.tech/tags/tracking.md>)

### AI overview

ParAC addresses the setup bottleneck in Approximate Cholesky preconditioning by parallelizing the sequential rchol algorithm on CPUs and GPUs with dynamic dependency tracking and architecture-aware memory management, while preserving its numerics. The abstract reports total time-to-solution speedups over deterministic Incomplete Cholesky of up to 57.3x on CPU and 52.2x on GPU. Algebraic multigrid remains preferable for structured PDE discretizations; on irregular graph Laplacians where AMG struggles, ParAC reaches up to 7.2x and 6.0x speedups. On 200 adversarial SDD systems, ParAC converged on all instances, while the AMG solvers failed on 15 CPU and 19 GPU cases.

### Source excerpt

arXiv:2505.02977v4 Announce Type: replace Abstract: Incomplete Cholesky (IC) preconditioners are the standard black-box, memory-efficient first resort for large graph Laplacian systems, but classical IC can break down on irregular graphs. Approximate Cholesky (AC) addresses this with randomized dropping that is provably breakdown-free. Its stochastic fill-in pattern, however, resists static parallelization, creating a "setup bottleneck." We present ParAC, which parallelizes the sequential rchol algorithm on CPUs and GPUs using dynamic dependency tracking and architecture-aware memory management, without altering its numerics. Total time-to-solution speedups over deterministic IC reach $57.3\times$ on CPU and $52.2\times$ on GPU. Algebraic multigrid (AMG) remains preferable on structured PDE discretizations; on irregular graph Laplacians where AMG struggles, ParAC attains up to $7.2\times$ and $6.0\times$. On 200 adversarial SDD systems, ParAC converges on every instance, whereas the AMG solvers fail on 15 and 19, on CPU and GPU, respectively.

## ModelBlaster: Closing the Performance Gap through Learning-Augmented Agents Across Models, Kernels and Hardware Backends

DevFeed: [ModelBlaster: Closing the Performance Gap through Learning-Augmented Agents Across Models, Kernels and Hardware Backends](<https://devfeed.tech/articles/modelblaster-closing-the-performance-gap-through-learning-augmented-agents-across-models-kernels-and-hardware-backends-116898.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.04104>)

Author: Shengjun Kris Dong, Dima Nikiforov, Sahil Modi, Sana Damani, Edward C Lin, Siva Kumar Sastry Hari, Christos Kozyrakis

Published: 2026-11-04T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [GPU optimization](<https://devfeed.tech/topics/gpu-optimization.md>), [High-Performance Computing](<https://devfeed.tech/topics/high-performance-computing.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [accelerators](<https://devfeed.tech/tags/accelerators.md>), [actions](<https://devfeed.tech/tags/actions.md>), [actor](<https://devfeed.tech/tags/actor.md>), [adreno](<https://devfeed.tech/tags/adreno.md>), [agents](<https://devfeed.tech/tags/agents.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [apache](<https://devfeed.tech/tags/apache.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [backends](<https://devfeed.tech/tags/backends.md>), [base](<https://devfeed.tech/tags/base.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [gap](<https://devfeed.tech/tags/gap.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [kernels](<https://devfeed.tech/tags/kernels.md>), [learning](<https://devfeed.tech/tags/learning.md>), [models](<https://devfeed.tech/tags/models.md>), [performance](<https://devfeed.tech/tags/performance.md>)

### AI overview

ModelBlaster reuses optimization experience across kernels, whole models, and heterogeneous accelerators. Its persistent knowledge base maps performance states to actions, outcomes, and constraints, and is updated at inference time using Actor-Critic Textual Gradient Descent; a model-level optimizer draws on kernel-level knowledge. One optimization loop and knowledge schema support CUDA on NVIDIA GPUs, OpenCL on Qualcomm GPUs, and RVV intrinsics on RISC-V vector cores, while lowering and measurement remain target-specific. The abstract reports B200 geometric-mean speedups over PyTorch of 1.85x, 5.58x, and 5.18x on KernelBench Levels 1-3, and 1.69x on SOL-ExecBench Levels 1-2. It also reports 5.8x over the Qualcomm vendor SDK and 1.7x over Apache TVM on Adreno GPUs, plus 2.7x over ExecuTorch with XNNPACK across 70 KernelBench problems on RISC-V vector cores.

### Source excerpt

arXiv:2611.04104v1 Announce Type: new Abstract: Optimizing accelerator code across hardware architectures is difficult. ML compilers search predefined spaces of schedules and micro-kernels, while LLM-guided optimization can explore alternative algorithms, operator decompositions, and hardware-specific techniques. However, existing LLM agents typically target a single programming interface, toolchain, or accelerator family, focus on kernel-level optimization without model-level transforms, and offer limited reuse of experience across hardware targets. We present ModelBlaster, a Memory-Augmented In-Context Reinforcement Learning (MAIC-RL) framework for optimizing data-parallel kernels and whole models across heterogeneous SIMD and SIMT accelerators. Its mutable policy is a persistent knowledge base updated at inference time by Actor-Critic Textual Gradient Descent (AC-TGD). The knowledge base maps performance states to actions, outcomes, and constraints, enabling experience reuse across kernels, models, and hardware targets. A model-level optimizer uses kernel-level knowledge to inform whole-model decisions. The same optimization loop and knowledge schema support CUDA on NVIDIA GPUs, OpenCL on Qualcomm GPUs, and RVV intrinsics on RISC-V vector cores, with only lowering and measurement layers specific to each target. Compared with PyTorch, ModelBlaster achieves geometric-mean speedups of 1.85x, 5.58x, and 5.18x on KernelBench Levels 1, 2, and 3, and 1.69x on SOL-ExecBench Levels 1 and 2 on a B200 GPU. On Qualcomm Adreno GPUs, it achieves 5.8x over the vendor SDK and 1.7x over Apache TVM; on RISC-V vector cores, it achieves 2.7x over ExecuTorch with XNNPACK across 70 KernelBench problems.

## Intel Compute Runtime Continues Prepping For GPU D Series, OpenCL LEO for Nova Lake P

DevFeed: [Intel Compute Runtime Continues Prepping For GPU D Series, OpenCL LEO for Nova Lake P](<https://devfeed.tech/articles/intel-compute-runtime-continues-prepping-for-gpu-d-series-opencl-leo-for-nova-lake-p-114147.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/Intel-Compute-26.40.40196.8>)

Author: Michael Larabel

Published: 2026-11-03T10:52:14Z

Content type: news

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [OpenCL](<https://devfeed.tech/topics/opencl.md>), [intel](<https://devfeed.tech/topics/intel.md>), [Intel Iris Xe](<https://devfeed.tech/topics/intel-iris-xe.md>)

Tags: [ai-accelerator](<https://devfeed.tech/tags/ai-accelerator.md>), [apis](<https://devfeed.tech/tags/apis.md>), [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [compute](<https://devfeed.tech/tags/compute.md>), [crescent-island](<https://devfeed.tech/tags/crescent-island.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [driver](<https://devfeed.tech/tags/driver.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [extension](<https://devfeed.tech/tags/extension.md>), [features](<https://devfeed.tech/tags/features.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gpu-compute](<https://devfeed.tech/tags/gpu-compute.md>), [gpu-d-series](<https://devfeed.tech/tags/gpu-d-series.md>), [intel](<https://devfeed.tech/tags/intel.md>), [leo](<https://devfeed.tech/tags/leo.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [nova](<https://devfeed.tech/tags/nova.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [source](<https://devfeed.tech/tags/source.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>)

### AI overview

Intel Compute Runtime 26.40.40196.8 enables unified shared memory and deferred backing for the Crescent Island accelerator, now called Intel GPU D Series. Shared memory lets GPU kernels access ordinary CPU memory through C/C++ pointers. Standby mode is enabled with the Xe kernel driver for Battlemage and Crescent Island. The update also improves multi-queue use and local memory ring buffer capacity. For Nova Lake P, Intel enables OpenCL LEO by default; LEO implements OpenCL on Level Zero rather than using a separate OpenCL-to-hardware driver. Other additions include front-end copy capability, an experimental event flags extension, and refactoring intended to optimize Level Zero compilation.

### Source excerpt

Released today was the Intel Compute Runtime 26.40.40196.8 as the newest version of their open-source GPU compute stack for both Windows and Linux systems...

## Google ML Drift Accelerates On-Device AI Inference Across Diverse GPUs

DevFeed: [Google ML Drift Accelerates On-Device AI Inference Across Diverse GPUs](<https://devfeed.tech/articles/google-ml-drift-accelerates-on-device-ai-inference-across-diverse-gpus-99272.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/10/google-ml-drift/>)

Author: Sergio De Simone

Published: 2026-10-25T17:00:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [On-device AI](<https://devfeed.tech/topics/on-device-ai.md>), [LiteRT](<https://devfeed.tech/topics/litert.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [gemma](<https://devfeed.tech/topics/gemma.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-and-machine-learning](<https://devfeed.tech/tags/ai-and-machine-learning.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [ai-ml-data-engineering](<https://devfeed.tech/tags/ai-ml-data-engineering.md>), [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [apis](<https://devfeed.tech/tags/apis.md>), [compute](<https://devfeed.tech/tags/compute.md>), [cross-platform](<https://devfeed.tech/tags/cross-platform.md>), [development](<https://devfeed.tech/tags/development.md>), [device](<https://devfeed.tech/tags/device.md>), [edge](<https://devfeed.tech/tags/edge.md>), [engine](<https://devfeed.tech/tags/engine.md>), [google](<https://devfeed.tech/tags/google.md>), [google-ml-drift](<https://devfeed.tech/tags/google-ml-drift.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gpu-compute](<https://devfeed.tech/tags/gpu-compute.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [inference](<https://devfeed.tech/tags/inference.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [local-inference](<https://devfeed.tech/tags/local-inference.md>), [low-level](<https://devfeed.tech/tags/low-level.md>), [ml](<https://devfeed.tech/tags/ml.md>), [ml-data-engineering](<https://devfeed.tech/tags/ml-data-engineering.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [news](<https://devfeed.tech/tags/news.md>), [on-device](<https://devfeed.tech/tags/on-device.md>), [on-device-ai](<https://devfeed.tech/tags/on-device-ai.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [tensorflow](<https://devfeed.tech/tags/tensorflow.md>)

### AI overview

Google's open-source ML Drift is a cross-platform GPU engine for on-device inference and the acceleration core of LiteRT. It abstracts GPU hardware and APIs, supporting OpenGL ES, OpenCL, Metal, and WebGPU; desktop inference uses Chromium's Dawn on Windows and Linux, while macOS retains native Metal support. Compared with the legacy TensorFlow Lite GPU delegate, ML Drift adds unified shaders through tensor virtualization, custom operations, five-dimensional tensors, and optimizations for Arm, Intel, and Qualcomm GPUs. Google reports 12% lower memory overhead than llama.cpp and MLX LM in workstation Gemma benchmarks, plus app-specific latency or performance gains; these are company-reported results, and the source says Google provided no comparison with Core ML on recent iPhones. Google will stop updating the legacy delegate and recommends migrating existing models to the LiteRT ML Drift GPU accelerator. Developers can use that accelerator or the lower-level C++ API to build custom compute graphs and shaders.

### Source excerpt

Google has released ML Drift, an open-source, cross-platform GPU compute engine designed for on-device AI and machine learning inference. Licensed under Apache 2.0, it abstracts the complexities of different GPU hardware and low-level APIs, supporting OpenGL ES, OpenCL, Metal, and WebGPU. By Sergio De Simone

## Mesa RADV Change Satisfies More Steam Play Games On Aging AMD GFX8 GPUs

DevFeed: [Mesa RADV Change Satisfies More Steam Play Games On Aging AMD GFX8 GPUs](<https://devfeed.tech/articles/mesa-radv-change-satisfies-more-steam-play-games-on-aging-amd-gfx8-gpus-95294.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/Mesa-RADV-GFX8-FP16-Gaming>)

Author: Michael Larabel

Published: 2026-10-22T10:30:00Z

Content type: news

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [GPU optimization](<https://devfeed.tech/topics/gpu-optimization.md>), [real-time rendering](<https://devfeed.tech/topics/real-time-rendering.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>)

Tags: [aging](<https://devfeed.tech/tags/aging.md>), [amd](<https://devfeed.tech/tags/amd.md>), [change](<https://devfeed.tech/tags/change.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [driver](<https://devfeed.tech/tags/driver.md>), [games](<https://devfeed.tech/tags/games.md>), [gaming](<https://devfeed.tech/tags/gaming.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [graphics](<https://devfeed.tech/tags/graphics.md>), [graphics-cards](<https://devfeed.tech/tags/graphics-cards.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [patch](<https://devfeed.tech/tags/patch.md>), [performance](<https://devfeed.tech/tags/performance.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [proton](<https://devfeed.tech/tags/proton.md>), [radeon](<https://devfeed.tech/tags/radeon.md>), [steam](<https://devfeed.tech/tags/steam.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>), [update](<https://devfeed.tech/tags/update.md>), [valve](<https://devfeed.tech/tags/valve.md>), [vulkan](<https://devfeed.tech/tags/vulkan.md>), [windows](<https://devfeed.tech/tags/windows.md>), [witcher-3](<https://devfeed.tech/tags/witcher-3.md>)

### AI overview

Mesa RADV now exposes Vulkan FP16 support by default on AMD GFX8 GPUs when VKD3D-Proton is running, helping newer Windows games that require FP16. The excerpt gives Witcher 3's SSAO after a recent game update as a specific fix. FP16 remains disabled by default for other applications because it typically offers no performance gain on these GPUs and can be slower than FP32. The change is merged to Mesa; the source summary says it is slated for backport to current stable Mesa series.

### Source excerpt

Valve landed a patch in Mesa 27.0 and to be back-ported to current Mesa stable series to satisfy more games running under Steam Play with VKD3D-Proton for working on AMD GFX8 GPUs like Polaris...

## TornadoVM 7 Enables GPU-Native Workloads From Java Applications

DevFeed: [TornadoVM 7 Enables GPU-Native Workloads From Java Applications](<https://devfeed.tech/articles/tornadovm-7-enables-gpu-native-workloads-from-java-applications-91286.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/10/tornadovm-7-gpu/>)

Author: Ben Evans

Published: 2026-10-21T03:00:00Z

Content type: release

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [TornadoVM](<https://devfeed.tech/topics/tornadovm.md>), [CUDA](<https://devfeed.tech/topics/cuda.md>), [CUDA Tile](<https://devfeed.tech/topics/cuda-tile.md>), [Multi-GPU](<https://devfeed.tech/topics/multi-gpu.md>), [Java](<https://devfeed.tech/topics/java.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>), [openjdk](<https://devfeed.tech/topics/openjdk.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [ai-ml-data-engineering](<https://devfeed.tech/tags/ai-ml-data-engineering.md>), [apache-flink](<https://devfeed.tech/tags/apache-flink.md>), [apple](<https://devfeed.tech/tags/apple.md>), [architecture-design](<https://devfeed.tech/tags/architecture-design.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [cutile](<https://devfeed.tech/tags/cutile.md>), [development](<https://devfeed.tech/tags/development.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [java](<https://devfeed.tech/tags/java.md>), [llama3](<https://devfeed.tech/tags/llama3.md>), [ml-data-engineering](<https://devfeed.tech/tags/ml-data-engineering.md>), [news](<https://devfeed.tech/tags/news.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [tornadovm](<https://devfeed.tech/tags/tornadovm.md>), [tornadovm-7-gpu](<https://devfeed.tech/tags/tornadovm-7-gpu.md>)

### AI overview

TornadoVM 7.3 lets Java applications offload suitable data-parallel work to CPUs and GPUs while using mainstream JDKs. It manages accelerator memory and executes kernels, and supports local development with OpenCL or Apple Metal before deployment to Nvidia hardware. Version 7 replaces JNI with the Foreign Function & Memory API and removes the experimental JVMCI dependency; compiler metadata now follows one reflection, ASM, and Unsafe path across supported JDKs 21, 25, 26, and 27. Its optimized CUDA backend adds cuTile through TileContext, direct cuBLAS and CUTLASS calls in TaskGraphs, and multi-GPU execution. Developers can combine library calls with generated kernels to balance performance and portability. Similar hybrid support is described for Apple's MXL library. The excerpt cautions that offloading does not suit every computation; independent loop iterations are among the best candidates. It also describes a Flink integration that checks GPU availability and analyzes query IR for suitability before acceleration.

### Source excerpt

TornadoVM, an open-source heterogeneous programming framework for Java has reached version 7.0. It automatically accelerates Java programs on multi-core CPUs and GPUs and provides a rich GPU programming ecosystem in Java that can be used with any mainstream JDK distribution e.g. Temurin, Red Hat OpenJDK, Coretto, Oracle, GraalVM or Zulu. By Ben Evans

## Reflect, Transform, Accelerate: Bringing GPU Computing to Java

DevFeed: [Reflect, Transform, Accelerate: Bringing GPU Computing to Java](<https://devfeed.tech/articles/reflect-transform-accelerate-bringing-gpu-computing-to-java-91171.md>)

Original publisher: [Read original article](<https://inside.java/2026/10/20/devoxxbelgium-bringing-gpu-computing-to-java/>)

Author: Juan Fumero

Published: 2026-10-20T00:00:00Z

Content type: article

Language: en

Sources: [Inside Java](<https://devfeed.tech/sources/inside-java.md>)

Topics: [GPU](<https://devfeed.tech/topics/gpu.md>), [Java](<https://devfeed.tech/topics/java.md>), [CUDA](<https://devfeed.tech/topics/cuda.md>), [Tensor Cores](<https://devfeed.tech/topics/tensor-cores.md>), [GPU optimization](<https://devfeed.tech/topics/gpu-optimization.md>), [openjdk](<https://devfeed.tech/topics/openjdk.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>), [High-Performance Computing](<https://devfeed.tech/topics/high-performance-computing.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [backend](<https://devfeed.tech/tags/backend.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [java](<https://devfeed.tech/tags/java.md>), [kernels](<https://devfeed.tech/tags/kernels.md>), [matrix](<https://devfeed.tech/tags/matrix.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [openjdk](<https://devfeed.tech/tags/openjdk.md>), [optimisation](<https://devfeed.tech/tags/optimisation.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [performance](<https://devfeed.tech/tags/performance.md>), [performance-analysis](<https://devfeed.tech/tags/performance-analysis.md>), [profiling](<https://devfeed.tech/tags/profiling.md>), [programming](<https://devfeed.tech/tags/programming.md>), [project-babylon](<https://devfeed.tech/tags/project-babylon.md>), [reflection](<https://devfeed.tech/tags/reflection.md>)

### AI overview

HAT uses Java code reflection to turn compute code into an analysable model, transform it into a GPU-friendly representation, and offload selected computations to OpenCL or CUDA. The excerpt demonstrates the framework with tensor-core programming and matrix multiplication, and describes tuning its CUDA backend using NVIDIA Nsight Compute and Nsight Systems to profile generated kernels and find optimisation opportunities. It introduces code reflection basics for developers new to the API; the excerpt does not provide benchmark results or quantify performance gains.

### Source excerpt

Java's code reflection API, developed in OpenJDK Project Babylon, opens a new path to targeting foreign programming models directly from Java--including GPUs. This talk introduces the Heterogeneous Accelerator Toolkit (HAT), a Java parallel programming framework that accelerates modern workloads on specialised hardware through three core stages: reflect, transform, and accelerate. Through examples of tensor-core programming and matrix multiplication--fundamental building blocks for AI and natural-language processing--we demonstrate HAT in action. We also explore performance analysis and tuning of the CUDA backend with NVIDIA Nsight Compute and Nsight Systems, from profiling generated kernels to identifying optimisation opportunities.

## RADV Promotes VK\_EXT\_host\_image\_copy To Enabled By Default For RDNA1 GPUs

DevFeed: [RADV Promotes VK\_EXT\_host\_image\_copy To Enabled By Default For RDNA1 GPUs](<https://devfeed.tech/articles/radv-promotes-vk-ext-host-image-copy-to-enabled-by-default-for-rdna1-gpus-89897.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/RADV-GFX10-Host-Image-Copy>)

Author: Michael Larabel

Published: 2026-10-19T09:48:43Z

Content type: news

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [real-time rendering](<https://devfeed.tech/topics/real-time-rendering.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>)

Tags: [amd](<https://devfeed.tech/tags/amd.md>), [data](<https://devfeed.tech/tags/data.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [radeon](<https://devfeed.tech/tags/radeon.md>), [rdna](<https://devfeed.tech/tags/rdna.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>), [vulkan](<https://devfeed.tech/tags/vulkan.md>)

### AI overview

The RADV Vulkan driver enables VK_EXT_host_image_copy by default for RDNA1 (GFX10) GPUs and adds experimental support for earlier GFX9 GPUs. The extension copies data between host memory and Vulkan images, which can reduce overhead, particularly on integrated GPUs. The change is planned for Mesa 27.0.

### Source excerpt

Going back to July 2025 the open-source Radeon RADV Vulkan driver has offered experimental host image copy support with the API's VK_EXT_host_image_copy extension. This has been for RDNA1 and newer GPUs while now GFX10 RDNA 1 GPUs have this extension enabled by default while also enabling experimental support for prior GFX9 era GPUs too...

## ROCm 10 OpenCL vs. Mesa 26.3-dev Rusticl Performance On AMD Strix Halo

DevFeed: [ROCm 10 OpenCL vs. Mesa 26.3-dev Rusticl Performance On AMD Strix Halo](<https://devfeed.tech/articles/rocm-10-opencl-vs-mesa-26-3-dev-rusticl-performance-on-amd-strix-halo-85454.md>)

Original publisher: [Read original article](<https://www.phoronix.com/review/rocm-10-opencl-rusticl>)

Author: Michael Larabel

Published: 2026-10-12T16:32:24Z

Content type: comparison

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [OpenCL](<https://devfeed.tech/topics/opencl.md>), [rocm](<https://devfeed.tech/topics/rocm.md>)

Tags: [amd](<https://devfeed.tech/tags/amd.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [rocm](<https://devfeed.tech/tags/rocm.md>), [strix-halo](<https://devfeed.tech/tags/strix-halo.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>)

### AI overview

The article compares Mesa 26.3-dev's Rusticl OpenCL driver with AMD's official OpenCL driver in ROCm 10. The benchmarks use AMD Ryzen AI Max+ 395 Strix Halo hardware and report that Rusticl supports OpenCL 3.1, while AMD's driver provides OpenCL 2.1 compliance.

### Source excerpt

With all the recent progress on Mesa's Rusticl driver as a Rust-based OpenCL driver working across the different Mesa Gallium3D hardware drivers, a Phoronix Premium supporter inquired about seeing some fresh benchmarks of this open-source OpenCL solution. Here is a look at how the Mesa 26.3 Rusticl driver is looking against AMD's official OpenCL driver within ROCm 10.

## Rusticl Had A Great Year For Rust OpenCL In Mesa With 3.1 Support, More Drivers

DevFeed: [Rusticl Had A Great Year For Rust OpenCL In Mesa With 3.1 Support, More Drivers](<https://devfeed.tech/articles/rusticl-had-a-great-year-for-rust-opencl-in-mesa-with-3-1-support-more-drivers-62704.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/Rusticl-2026>)

Author: Michael Larabel

Published: 2026-09-30T13:03:20Z

Content type: news

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [OpenCL](<https://devfeed.tech/topics/opencl.md>), [Rust](<https://devfeed.tech/topics/rust.md>)

Tags: [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [performance](<https://devfeed.tech/tags/performance.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [rust](<https://devfeed.tech/tags/rust.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>)

### AI overview

Rusticl, Mesa's Rust-based OpenCL driver, added OpenCL 3.1 support, expanded hardware driver support, and improved GPU performance during the year. The article also notes work on NVIDIA driver support and a Qualcomm QAIC accelerator driver.

### Source excerpt

Rusticl lead developer Karol herbst provided a status update on this Mesa Rust-based OpenCL driver during the XDC 2026 conference happening in Toronto...

## NOCL Making Progress As Mesa Gallium/OpenCL Atop NVIDIA CUDA

DevFeed: [NOCL Making Progress As Mesa Gallium/OpenCL Atop NVIDIA CUDA](<https://devfeed.tech/articles/nocl-making-progress-as-mesa-gallium-opencl-atop-nvidia-cuda-61946.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/NOCL-OpenCL-CUDA>)

Author: Michael Larabel

Published: 2026-09-29T13:53:05Z

Content type: news

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [OpenCL](<https://devfeed.tech/topics/opencl.md>), [Jetson Orin](<https://devfeed.tech/topics/jetson-orin.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [NVLink](<https://devfeed.tech/topics/nvlink.md>)

Tags: [compute](<https://devfeed.tech/tags/compute.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [gallium](<https://devfeed.tech/tags/gallium.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [performance](<https://devfeed.tech/tags/performance.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [ptx](<https://devfeed.tech/tags/ptx.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>)

### AI overview

NOCL is a developing Mesa Gallium driver that uses NVIDIA's proprietary CUDA driver and PTX representation to provide an open-source OpenCL option on Linux. Its merge request is pending; it supports more OpenCL extensions than NVIDIA's proprietary OpenCL driver and may aid performance comparisons and PTX development. PTX-to-NIR support could also matter for DLSS with the NVK Mesa driver.

### Source excerpt

In development the past year has been the Mesa Gallium3D API implemented atop NVIDIA's CUDA driver API. Initially named "CLUDA" and now going by "NOCL", this Mesa code paired with Rusticl is working well for OpenCL atop the NVIDIA proprietary driver as a new compute option...

## OpenCL 3.1.2 Released With cl\_khr\_command\_buffer Promoted

DevFeed: [OpenCL 3.1.2 Released With cl\_khr\_command\_buffer Promoted](<https://devfeed.tech/articles/opencl-3-1-2-released-with-cl-khr-command-buffer-promoted-42695.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/OpenCL-3.1.2-Released>)

Author: Michael Larabel

Published: 2026-09-18T00:33:22Z

Content type: release

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [OpenCL](<https://devfeed.tech/topics/opencl.md>), [Extension](<https://devfeed.tech/topics/extension.md>), [Documentation](<https://devfeed.tech/topics/documentation.md>)

Tags: [code-documentation](<https://devfeed.tech/tags/code-documentation.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [extension](<https://devfeed.tech/tags/extension.md>), [github](<https://devfeed.tech/tags/github.md>), [google](<https://devfeed.tech/tags/google.md>), [intel](<https://devfeed.tech/tags/intel.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [qualcomm](<https://devfeed.tech/tags/qualcomm.md>), [record-and-replay](<https://devfeed.tech/tags/record-and-replay.md>), [release](<https://devfeed.tech/tags/release.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>)

### AI overview

OpenCL 3.1.2 finalizes the cl_khr_command_buffer extension, promoting it beyond experimental status. The extension enables recording and replaying OpenCL command buffers to reduce the overhead of repeatedly enqueuing the same workload. The update also clarifies memory object API error-code documentation.

### Source excerpt

The Khronos Group today released the newest revision of the OpenCL specification with a handful of changes...

## Intel Compute Stack Enables LEO For Nova Lake, Introduces Intel Portable ISA "PISA"

DevFeed: [Intel Compute Stack Enables LEO For Nova Lake, Introduces Intel Portable ISA "PISA"](<https://devfeed.tech/articles/intel-compute-stack-enables-leo-for-nova-lake-introduces-intel-portable-isa-pisa-41401.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/Intel-Compute-Runtime-26.35.397>)

Author: Michael Larabel

Published: 2026-09-17T13:05:07Z

Content type: release

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [intel](<https://devfeed.tech/topics/intel.md>), [Nova](<https://devfeed.tech/topics/nova.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [LLVM](<https://devfeed.tech/topics/llvm.md>), [Compiler](<https://devfeed.tech/topics/compiler.md>), [Parallelism](<https://devfeed.tech/topics/parallelism.md>)

Tags: [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [intel](<https://devfeed.tech/tags/intel.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [llvm](<https://devfeed.tech/tags/llvm.md>), [nova](<https://devfeed.tech/tags/nova.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [release](<https://devfeed.tech/tags/release.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>), [update](<https://devfeed.tech/tags/update.md>)

### AI overview

Intel Compute Runtime 26.35.39758.10 adds several GPU compute features and enables the OpenCL LEO driver by default for upcoming Nova Lake S processors on Linux. The release also introduces initial support for Intel's Portable ISA (PISA) format.

### Source excerpt

Released today was the Intel Compute Runtime 26.35.39758.10 update for Windows and Linux systems. With this updated OpenCL and Level Zero GPU compute driver stack comes some exciting updates for this monthly feature update...

## Plan for Clojure AI, ML, and high-performance Uncomplicate ecosystem in 2026

DevFeed: [Plan for Clojure AI, ML, and high-performance Uncomplicate ecosystem in 2026](<https://devfeed.tech/articles/plan-for-clojure-ai-ml-and-high-performance-uncomplicate-ecosystem-in-2026-20726.md>)

Original publisher: [Read original article](<http://dragan.rocks/articles/25/Clojure-AI-ML-high-performance-Uncomplicate>)

Published: 2025-11-29T00:41:00Z

Content type: opinion

Language: en

Sources: [Dragan Djuric](<https://devfeed.tech/sources/dragan-djuric.md>)

Topics: [Clojure](<https://devfeed.tech/topics/clojure.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [CUDA](<https://devfeed.tech/topics/cuda.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [NumPy](<https://devfeed.tech/topics/numpy.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-ml](<https://devfeed.tech/tags/ai-ml.md>), [algebra](<https://devfeed.tech/tags/algebra.md>), [apple](<https://devfeed.tech/tags/apple.md>), [clojure](<https://devfeed.tech/tags/clojure.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [linear](<https://devfeed.tech/tags/linear.md>), [matrices](<https://devfeed.tech/tags/matrices.md>), [neanderthal](<https://devfeed.tech/tags/neanderthal.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [programming](<https://devfeed.tech/tags/programming.md>), [vectors](<https://devfeed.tech/tags/vectors.md>)

### AI overview

The article outlines a 2026 development and funding plan for the Uncomplicate ecosystem of Clojure libraries for AI, machine learning, and high-performance computing. It describes support for Nvidia GPUs, Apple Silicon, CPUs, CUDA, OpenCL, and several planned library improvements.

### Source excerpt

I've applied for Clojurists Together yearly funding in 2026. Here's my application. If you are a Clojurists Together member, and would like to see continued development in this area, your vote can help me keep working on this :) My goal with this funding in 2026 is to continuously develop Clojure AI, ML, and high-performance ecosystem of Uncomplicate libraries (Neanderhal and many more), on Nvidia GPUs, Apple Silicon, and traditional PC. In this year, I will also focus on writing tutorals on my blog and creating websites for the projects involved, which is something that I wanted for years, but didn't have time to do because I spent all time on programming. How that work will benefit the Clojure community This will highly benefit the Clojure community as this is THE AI ecosystem for Clojure, and supporting AI is arguably the main focus on probably all software platforms. Clojure has something to offer on that front, beyond just calling OpenAI API as a web service! Uncomplicate grew to quite a few libraries (of which some are quite big; just Neanderthal is 28,000 lines of highly-condensed, aggresively macroized, and reusable code): Diamond ONNX Runtime, Neanderthal, Deep Diamond, ClojureCUDA, ClojureCPP, Apple Presets, ClojureCL, Fluokitten, Bayadera, Clojure Sound, and Commons. Here's a word or two of how I hope to improve each of these libraries with Clojurists Together funding in 2026. Neanderthal (Clojure's alternative to NumPy, on steroids) In 2025, Neanderthal celebrated its 10th birthday. It started as a humble but fast matrix and vector library for Clojure, but after 10 years of relentless improvements, now it boasts a general matrix/vector/linear algebra API implemented by no less than 5(!) engines for CPUs, GPU (Nvidia CUDA), GPU (OpenCL: AMD, Intel, Nvidia), Apple Silicon (Accelerate), and general CPU (OpenBLAS). And this is not a superficial support for the sake of ticking a check box; each of these engines support much more operations on exotic structure

## Get Ready for Clojure, GPU, and AI in 2026 with CUDA 13.0

DevFeed: [Get Ready for Clojure, GPU, and AI in 2026 with CUDA 13.0](<https://devfeed.tech/articles/get-ready-for-clojure-gpu-and-ai-in-2026-with-cuda-13-0-20730.md>)

Original publisher: [Read original article](<http://dragan.rocks/articles/25/Get-Ready-Clojure-GPU-AI-2026-CUDA-13>)

Published: 2025-10-30T16:37:00Z

Content type: tutorial

Language: en

Sources: [Dragan Djuric](<https://devfeed.tech/sources/dragan-djuric.md>)

Topics: [CUDA](<https://devfeed.tech/topics/cuda.md>), [Clojure](<https://devfeed.tech/topics/clojure.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [addition](<https://devfeed.tech/tags/addition.md>), [ai](<https://devfeed.tech/tags/ai.md>), [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [clojure](<https://devfeed.tech/tags/clojure.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [deep](<https://devfeed.tech/tags/deep.md>), [diamond](<https://devfeed.tech/tags/diamond.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [interactive](<https://devfeed.tech/tags/interactive.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [programming](<https://devfeed.tech/tags/programming.md>), [repl](<https://devfeed.tech/tags/repl.md>), [tensors](<https://devfeed.tech/tags/tensors.md>)

### AI overview

ClojureCUDA 0.25.0 adds support for CUDA 13.0.2 and lets developers manage GPU work interactively from the Clojure REPL while writing kernels in C++ CUDA. The example walks through initializing a CUDA context, loading and compiling a `.cu` kernel, allocating GPU memory through either the runtime or driver API, copying vectors to the GPU, launching an asynchronous addition kernel, synchronizing, reading back the result `(3.0 5.0 7.0)`, and releasing resources. The author argues that this low-level setup is manageable and says library helpers can simplify resource handling; higher-level vector, matrix, and tensor libraries mean custom kernels are only occasionally needed. The excerpt cautions that GPU transfers and setup can outweigh computation for small or simple workloads, so GPUs make sense when there is substantial, more demanding work.

### Source excerpt

A little anniversary Did you know that CUDA has been available in Clojure for the last 9 years through ClojureCUDA, and GPU programming through OpenCL for more than 10? I almost forgot about these anniversaries. Ten years ago most people liked it a lot, starred it on Github, patted me on the back, but then concluded that they don't have an Nvidia card available on their laptops, or, if they had GPUs, that they won't have time to learn to think in massive parallel algorithms, or if they have time and will, that there are no GPUs in the servers, so what would they do with their applications, even if they created them in Clojure, and so on, and so off :) But, ClojureCUDA and ClojureCL continued living on for these 10 years, I used them in creating Neanderthal, Deep Diamond, and Diamond ML, and they proved themselves as simple and reliable tools. I still had trouble convincing Clojure programmers that they can write GPU programs that run as fast as they'd wrote them in C++, but interactively in the Cloujre REPL, without C++ hell. But I'm not easy to shake off! If it's necessary, I'll continue for 10 more years, for I'm convinced there'd be a moment when Clojure programmers are going to say "hmmm, this is something that we can use and be good at!". CUDA 13 is here! I've recently released ClojureCUDA 0.25.0, with support for the latest CUDA 13.0.2! Why not celebrate that by opening the REPL, and coding your first Hello World application on the GPU? I promise, it won't be a usual GPU carpet of text; this is ClojureCUDA, it follows the Clojure philosophy by being simple and interactive! There's not much sense in wielding a GPU to print out "Hello World". Note that it is also not very useful to work with scalar numbers and call a GPU function to add or multiply two numbers. No. Unless you have many, many, numbers to crunch, stay by your trusty CPU. For our purposes, many, many, numbers would be two vectors of dimension 3 (hey, it's hello world; imagine it's 3 billion). Also,

## GSoC 2025: Profiling and Testing Math Functions on GPUs

DevFeed: [GSoC 2025: Profiling and Testing Math Functions on GPUs](<https://devfeed.tech/articles/gsoc-2025-profiling-and-testing-math-functions-on-gpus-43118.md>)

Original publisher: [Read original article](<https://blog.llvm.org/posts/2025-08-29-gsoc-profiling-and-testing-math-functions-on-gpus/>)

Author: Leandro Augusto Lacerda Campos

Published: 2025-09-01T00:00:00Z

Content type: article

Language: en

Sources: [LLVM Project](<https://devfeed.tech/sources/the-llvm-project-blog.md>)

Topics: [Computing](<https://devfeed.tech/topics/computing.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [Software Testing](<https://devfeed.tech/topics/software-testing.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [LLVM](<https://devfeed.tech/topics/llvm.md>), [C](<https://devfeed.tech/topics/c.md>), [C++](<https://devfeed.tech/topics/c-plus-plus.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>), [Hardware](<https://devfeed.tech/topics/hardware.md>)

Tags: [2025](<https://devfeed.tech/tags/2025.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [c](<https://devfeed.tech/tags/c.md>), [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [code](<https://devfeed.tech/tags/code.md>), [computing](<https://devfeed.tech/tags/computing.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [data](<https://devfeed.tech/tags/data.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gsoc](<https://devfeed.tech/tags/gsoc.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [libc](<https://devfeed.tech/tags/libc.md>), [libraries](<https://devfeed.tech/tags/libraries.md>), [library](<https://devfeed.tech/tags/library.md>), [llvm](<https://devfeed.tech/tags/llvm.md>), [math](<https://devfeed.tech/tags/math.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [profiling](<https://devfeed.tech/tags/profiling.md>), [testing](<https://devfeed.tech/tags/testing.md>)

### AI overview

This report describes a Google Summer of Code 2025 project that developed a C++ framework for conformance testing of GPU math functions in LLVM-libc and expanded benchmarking infrastructure. It covers standards compliance, accuracy measurement, performance comparisons with vendor libraries, and support for AMD and NVIDIA hardware.

### Source excerpt

With the increasing importance of GPU computing, having a robust and familiar C standard library becomes a valuable asset for developers. The LLVM project is actively working to provide this foundation, as a solid libc implementation enables more complex libraries to be developed for and used on GPUs. A key part of this effort is providing the C standard math library (LLVM-libm) on GPUs, often reusing the same target-agnostic implementations developed for CPU targets. This context creates a twofold challenge. First, there is a need to systematically verify the conformance of these implementations to standards like OpenCL. Second, it is crucial to benchmark their performance against the highly-optimized vendor libraries to understand the trade-offs involved. This Google Summer of Code 2025 project was designed to address both challenges by developing a framework for conformance testing as well as refining and expanding the existing benchmarking infrastructure. The work provides two benefits to the LLVM community: It empowers libc contributors with a robust tool to validate their GPU math function implementations. It builds trust with end-users by providing transparent accuracy and performance data. This report details the work completed on this project. Conformance Testing To address the goal of accuracy verification, I implemented a C++ framework for conformance testing within the offload/unittests/Conformance directory. This framework was designed to be extensible, easy to use, and capable of testing various implementation providers (llvm-libm, cuda-math, hip-math) across different hardware platforms (AMD, NVIDIA). Key Components The framework's power and simplicity come from a few key components that work together: DeviceContext: A lightweight wrapper around the new Offload API that abstracts away the low-level details of device discovery, resource management, and kernel launching. InputGenerator: An extensible interface for test input generation. The framework pr

## GSoC 2024: Compile GPU kernels using ClangIR

DevFeed: [GSoC 2024: Compile GPU kernels using ClangIR](<https://devfeed.tech/articles/gsoc-2024-compile-gpu-kernels-using-clangir-43103.md>)

Original publisher: [Read original article](<https://blog.llvm.org/posts/2024-08-29-gsoc-opencl-c-support-for-clangir/>)

Author: Zhi Ma (7mile)

Published: 2024-09-09T00:00:00Z

Content type: article

Language: en

Sources: [LLVM Project](<https://devfeed.tech/sources/the-llvm-project-blog.md>)

Topics: [Compiler](<https://devfeed.tech/topics/compiler.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>), [LLVM](<https://devfeed.tech/topics/llvm.md>), [mlir](<https://devfeed.tech/topics/mlir.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [Code](<https://devfeed.tech/topics/code.md>), [software-development](<https://devfeed.tech/topics/software-development.md>), [Kernel](<https://devfeed.tech/topics/kernel.md>), [kernels](<https://devfeed.tech/topics/kernels.md>)

Tags: [c](<https://devfeed.tech/tags/c.md>), [clang](<https://devfeed.tech/tags/clang.md>), [clangir](<https://devfeed.tech/tags/clangir.md>), [compilation](<https://devfeed.tech/tags/compilation.md>), [compiler](<https://devfeed.tech/tags/compiler.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [design](<https://devfeed.tech/tags/design.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gsoc](<https://devfeed.tech/tags/gsoc.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [kernels](<https://devfeed.tech/tags/kernels.md>), [llvm](<https://devfeed.tech/tags/llvm.md>), [llvm-ir](<https://devfeed.tech/tags/llvm-ir.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [programming](<https://devfeed.tech/tags/programming.md>)

### AI overview

A GSoC project report describes adding OpenCL C support to ClangIR, an MLIR-based intermediate representation for Clang. The work targets compilation of GPU kernels to LLVM IR for SPIR-V and covers address spaces, OpenCL and SPIR-V integration, vector types, metadata, qualified variables, and calling conventions.

### Source excerpt

Hello everyone! I'm 7mile. My GSoC project this summer is Compile GPU kernels using ClangIR. It's been an exciting journey in compiler development, and I'm thrilled to share the progress and insights gained along the way here. Background The ClangIR project aims to establish a new IR for Clang, built on top of MLIR. As part of the ongoing effort to support heterogeneous programming models, this project focuses on integrating OpenCL C language support into ClangIR. The ultimate goal is to enable the compilation of GPU kernels written in OpenCL C into LLVM IR targeting the SPIR-V architecture, laying the groundwork for future enhancements in SYCL and CUDA support. What We Did Our work involved several key areas: Address Space Support: One of the fundamental tasks was teaching ClangIR to handle address spaces, a vital feature for languages like OpenCL. Initially, we considered mimicking LLVM's approach, but this proved inadequate for ClangIR's goals. After thorough discussion and an RFC, we implemented a unified address space design that aligns with ClangIR's objectives, ensuring a clean and maintainable code structure. OpenCL Language and SPIR-V Target Integration: We extended ClangIR to support the OpenCL language and the SPIR-V target. This involved enhancing the pipeline to accommodate the latest OpenCL 3.0 specification and implementing hooks for language-specific and target-specific customizations. Vector Type Support: OpenCL vector types, a critical feature for GPU programming, were integrated into ClangIR. We leveraged ClangIR's existing cir.vector type to generate the necessary code, ensuring consistent compilation results. Kernel and Module Metadata Emission: We added support for emitting OpenCL kernel and module metadata in ClangIR, a necessary step for proper integration with the SPIR-V target. This included the creation of structured attributes to represent metadata, following MLIR's preferences for well-defined structures. Global and Static Variables with

## Announcing the program for the 2018 LLVM Developers' Meeting Bay Area

DevFeed: [Announcing the program for the 2018 LLVM Developers' Meeting Bay Area](<https://devfeed.tech/articles/announcing-the-program-for-the-2018-llvm-developers-meeting-bay-area-43056.md>)

Original publisher: [Read original article](<https://blog.llvm.org/2018/08/announcing-program-for-2018-llvm.html>)

Author: Tanya Lattner

Published: 2018-08-31T16:29:00Z

Content type: release

Language: en

Sources: [LLVM Project](<https://devfeed.tech/sources/the-llvm-project-blog.md>)

Topics: [LLVM](<https://devfeed.tech/topics/llvm.md>), [Compiler](<https://devfeed.tech/topics/compiler.md>), [toolchain](<https://devfeed.tech/topics/toolchain.md>), [C++](<https://devfeed.tech/topics/c-plus-plus.md>), [clang](<https://devfeed.tech/topics/clang.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>), [C](<https://devfeed.tech/topics/c.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [Memory Safety](<https://devfeed.tech/topics/memory-safety.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [MEAN](<https://devfeed.tech/topics/mean-stack.md>)

Tags: [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [clang](<https://devfeed.tech/tags/clang.md>), [compiler](<https://devfeed.tech/tags/compiler.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [developers](<https://devfeed.tech/tags/developers.md>), [devmtg](<https://devfeed.tech/tags/devmtg.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [llvm](<https://devfeed.tech/tags/llvm.md>), [memory-safety](<https://devfeed.tech/tags/memory-safety.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [performance](<https://devfeed.tech/tags/performance.md>), [swift](<https://devfeed.tech/tags/swift.md>)

### AI overview

The LLVM Foundation announces the program for the 2018 LLVM Developers' Meeting in San Jose. The schedule includes talks on compiler development, C++ modules, code layout, toolchains, OpenMP, GPU and OpenCL compilation, LLVM-based machine learning, TensorFlow, memory safety, vectorization, and static analysis.

### Source excerpt

The LLVM Foundation is excited to announce the program for the 2018 LLVM Developers' Meeting in San Jose, CA on October 17 & 18. As a reminder, ticket prices for the event will increase on September 17th. Purchase your tickets today! Technical Talks Lessons Learned Implementing Common Lisp with LLVM over Six Years - Christian Schafmeister Porting Function merging pass to thinlto - Aditya Kumar Build Impact of Explicit and C++ Standard Modules - David Blaikie Profile Guided Code Layout in LLVM and LLD - Michael Spencer Developer Toolchain for the Nintendo Switch - Bob Campbell, Jeff Sirois Methods for Maintaining OpenMP Semantics without Being Overly Conservative - Jin Lin, Ernesto Su, Xinmin Tian Understanding the performance of code using LLVM's Machine Code Analyzer (llvm-mca) - Andrea Di Biagio, Matt Davis Art Class for Dragons: Supporting GPU compilation without metadata hacks! - Neil Hickey Implementing an OpenCL compiler for CPU in LLVM - Evgeniy Tyurin Working with Standalone Builds of LLVM sub-projects - Tom Stellard Loop Transformations in LLVM: The Good, the Bad, and the Ugly - Michael Kruse, Hal Finkel Efficiently Implementing Runtime Metadata with LLVM - Joe Groff, Doug Gregor Coroutine Representations and ABIs in LLVM - John McCall Glow: LLVM-based machine learning compiler - Nadav Rotem, Jakob Olesen Graph Program Extraction and Device Partitioning in Swift for TensorFlow - Mingsheng Hong, Chris Lattner Memory Tagging, how it improves C++ memory safety, and what does it mean for compiler optimizations - Kostya Serebryany, Evgenii Stepanov, Vlad Tsyrklevich Improving code reuse in clang tools with clangmetatool - Daniel Ruoso Sound Devirtualization in LLVM - Piotr Padlewski, Krzysztof Pszeniczny Extending the SLP vectorizer to support variable vector widths - Vasileios Porpodas, Rodrigo C. O. Rocha, Luís F. W. Góes Revisiting Loop Fusion, and its place in the loop transformation framework. - Johannes Doerfert, Kit Barton, Hal Finkel, Michael Kruse Optim

## A Beginner's Guide to Mining Siacoin

DevFeed: [A Beginner's Guide to Mining Siacoin](<https://devfeed.tech/articles/a-beginner-s-guide-to-mining-siacoin-52971.md>)

Original publisher: [Read original article](<https://mtlynch.io/windows-sia-mining/>)

Author: Michael Lynch

Published: 2017-05-20T00:00:00Z

Content type: tutorial

Language: en

Sources: [Mtlynch](<https://devfeed.tech/sources/mtlynch-io.md>)

Topics: [Computing](<https://devfeed.tech/topics/computing.md>), [Cryptocurrency](<https://devfeed.tech/topics/cryptocurrency.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [P2P](<https://devfeed.tech/topics/p2p.md>), [CUDA](<https://devfeed.tech/topics/cuda.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>), [Transactions](<https://devfeed.tech/topics/transactions.md>), [Windows](<https://devfeed.tech/topics/windows.md>), [Hardware](<https://devfeed.tech/topics/hardware.md>), [Software](<https://devfeed.tech/topics/software.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [beginner](<https://devfeed.tech/tags/beginner.md>), [computing](<https://devfeed.tech/tags/computing.md>), [cryptocurrency](<https://devfeed.tech/tags/cryptocurrency.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [guide](<https://devfeed.tech/tags/guide.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [network](<https://devfeed.tech/tags/network.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [peer-to-peer](<https://devfeed.tech/tags/peer-to-peer.md>), [software](<https://devfeed.tech/tags/software.md>)

### AI overview

A beginner-oriented guide to mining Siacoin on a Windows PC using a desktop GPU. It explains the Sia network and mining, identifies compatible NVIDIA and AMD GPUs, and covers installing CUDA or OpenCL and related software. The article warns that it is outdated and that custom mining hardware has made GPU mining non-viable.

### Source excerpt

This guide is out of date. This post describes mining Sia with a desktop graphics card (GPU), but custom mining hardware is now available for Sia. The custom hardware has made Sia GPU mining non-viable. This guide will still work, but you may never reach payout, even with a high-end GPU. Overview Sia is a decentralized, peer-to-peer network for buying and selling computer storage space. Users pay for transactions within Sia using a cryptocurrency called Siacoin. Like Bitcoin, Sia relies on "miners" to supply computing power to the network. These miners are paid for their contributions in Siacoin.

## LLVM Weekly - #119, Apr 11th 2016

DevFeed: [LLVM Weekly - #119, Apr 11th 2016](<https://devfeed.tech/articles/llvm-weekly-119-apr-11th-2016-43027.md>)

Original publisher: [Read original article](<https://blog.llvm.org/2016/04/llvm-weekly-119-apr-11th-2016.html>)

Author: Alex Bradbury

Published: 2016-04-11T06:03:00Z

Content type: news

Language: en

Sources: [LLVM Project](<https://devfeed.tech/sources/the-llvm-project-blog.md>)

Topics: [LLVM](<https://devfeed.tech/topics/llvm.md>), [clang](<https://devfeed.tech/topics/clang.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>), [C++](<https://devfeed.tech/topics/c-plus-plus.md>), [Microsoft](<https://devfeed.tech/topics/microsoft.md>)

Tags: [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [clang](<https://devfeed.tech/tags/clang.md>), [llvm](<https://devfeed.tech/tags/llvm.md>), [llvmweekly](<https://devfeed.tech/tags/llvmweekly.md>), [news](<https://devfeed.tech/tags/news.md>), [newsletter](<https://devfeed.tech/tags/newsletter.md>), [opencl](<https://devfeed.tech/tags/opencl.md>)

### AI overview

This issue of LLVM Weekly covers LLVM and Clang developments, including EuroLLVM conference videos, integer overflow checking, a Pocl release with initial OpenCL 2.0 support, a Clang custom directive-handler guide, Clang/C2 feedback, compiler RFCs, LLDB on Linux for SystemZ, Swift calling-convention support, and GlobalISel work.

### Source excerpt

Welcome to the one hundred and nineteenth issue of LLVM Weekly, a weekly newsletter (published every Monday) covering developments in LLVM, Clang, and related projects. LLVM Weekly is brought to you by Alex Bradbury. Subscribe to future issues at http://llvmweekly.org and pass it on to anyone else you think may be interested. Please send any tips or feedback to asb@asbradbury.org, or @llvmweekly or @asbradbury on Twitter. The canonical home for this issue can be found here at llvmweekly.org. News and articles from around the web Last week the slides from the recent EuroLLVM 2016 Developers' Meeting made it online. This week this has been followed by videos of the talks from the conference. John Regehr has written about efficient integer overflow checking in LLVM, looking at cases where LLVM can and cannot remove unnecessary overflow checks, and how this might be improved. Version 0.13 of Pocl, the portable OpenCL implementation has been released. This release works with LLVM/Clang 3.8 and 3.7, and adds initial OpenCL 2.0 support and improved HSA support. Serge Guelton at QuarksLab has written up a really useful guide to implementing a custom directive handler in Clang. Microsoft's Visual C++ team are looking for feedback on Clang/C2 (Clang with Microsoft CodeGen). On the mailing lists James Molloy has posted an RFC on adding support for constant folding calls to math.h functions on long doubles. Currently these functions aren't constant-folded as the internal APFloat class doesn't implement them and long double operations aren't portable. Solutions include adding support to APFloat, linking against libMPFR to provide compile-time evaluation, or recognising when the long double format of the host and target are the same, so the host math library can be called. From the responses so far, there seems to be some push-back on adding the libMPFR dependency. Sanjoy Das has an RFC on adding a patchable-prologue attribute. This would be used to indicate that the function's p

## LLVM Weekly - #115, Mar 14th 2016

DevFeed: [LLVM Weekly - #115, Mar 14th 2016](<https://devfeed.tech/articles/llvm-weekly-115-mar-14th-2016-43022.md>)

Original publisher: [Read original article](<https://blog.llvm.org/2016/03/llvm-weekly-115-mar-14th-2016.html>)

Author: Alex Bradbury

Published: 2016-03-14T04:56:00Z

Content type: article

Language: en

Sources: [LLVM Project](<https://devfeed.tech/sources/the-llvm-project-blog.md>)

Topics: [LLVM](<https://devfeed.tech/topics/llvm.md>), [clang](<https://devfeed.tech/topics/clang.md>), [CUDA](<https://devfeed.tech/topics/cuda.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>), [releases](<https://devfeed.tech/topics/releases.md>), [Go Language](<https://devfeed.tech/topics/go-language.md>)

Tags: [clang](<https://devfeed.tech/tags/clang.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [go](<https://devfeed.tech/tags/go.md>), [llvm](<https://devfeed.tech/tags/llvm.md>), [llvmweekly](<https://devfeed.tech/tags/llvmweekly.md>), [news](<https://devfeed.tech/tags/news.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [release-notes](<https://devfeed.tech/tags/release-notes.md>)

### AI overview

Issue 115 of LLVM Weekly covers LLVM and Clang 3.8 releases, related research and community events, LLVM and Clang development discussions, compiler performance concerns, and recent LLVM and Clang commits. It also highlights work involving Go, CUDA, OpenCL, FreeBSD, and parallel runtime libraries.

### Source excerpt

Welcome to the one hundred and fifteenth issue of LLVM Weekly, a weekly newsletter (published every Monday) covering developments in LLVM, Clang, and related projects. LLVM Weekly is brought to you by Alex Bradbury. Subscribe to future issues at http://llvmweekly.org and pass it on to anyone else you think may be interested. Please send any tips or feedback to asb@asbradbury.org, or @llvmweekly or @asbradbury on Twitter. The canonical home for this issue can be found here at llvmweekly.org. We have an LLVM-related research position currently being advertised here at the University of Cambridge Computer Lab. If you'd like an informal chat about what it's like working in this group or on this project please don't hesitate to get in touch with me. News and articles from around the web LLVM and Clang 3.8 have now been released. Check out the LLVM and Clang release notes for a run-down of the new features. It's GDC this week and if you're attending you may be interested that there's an LLVM meetup scheduled for Thursday. Felix Angell has a detailed blog post introducing generating LLVM IR from Go. On the mailing lists Jason Henline has posted a very detailed RFC on creating a new parallel runtime library. StreamExecutor wraps both the CUDA and OpenCL runtimes and is used internally at Google. Ed Maste has shared an update on linking the FreeBSD base system using LLD. With a few workarounds, the full amd64 FreeBSD system is now buildable. Vedant Kumar has shared an RFC on removing redundant profile counter updates. Sean Silva is seeking to formalize the 'revert for more design review policy'. Overall, the comments seem to be positive. With EuroLLVM coming up this week, people have been advertising their birds of a feather sessions. e.g. the LLVM on PowerPC and SystemZ session and the session on surviving downstream. Rafael Espíndola reports that compilation with LLVM and Clang has been getting slower over time. Hal Finkel has some good input on potential areas for improve

## LLVM Weekly - #63, Mar 16th 2015

DevFeed: [LLVM Weekly - #63, Mar 16th 2015](<https://devfeed.tech/articles/llvm-weekly-63-mar-16th-2015-42964.md>)

Original publisher: [Read original article](<https://blog.llvm.org/2015/03/llvm-weekly-63-mar-16th-2015.html>)

Author: Alex Bradbury

Published: 2015-03-16T08:35:00Z

Content type: news

Language: en

Sources: [LLVM Project](<https://devfeed.tech/sources/the-llvm-project-blog.md>)

Topics: [LLVM](<https://devfeed.tech/topics/llvm.md>), [clang](<https://devfeed.tech/topics/clang.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>), [Linux](<https://devfeed.tech/topics/linux.md>)

Tags: [2015](<https://devfeed.tech/tags/2015.md>), [clang](<https://devfeed.tech/tags/clang.md>), [conference](<https://devfeed.tech/tags/conference.md>), [linux](<https://devfeed.tech/tags/linux.md>), [llvm](<https://devfeed.tech/tags/llvm.md>), [llvmweekly](<https://devfeed.tech/tags/llvmweekly.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [performance](<https://devfeed.tech/tags/performance.md>), [release](<https://devfeed.tech/tags/release.md>), [weekly](<https://devfeed.tech/tags/weekly.md>)

### AI overview

LLVM Weekly issue 63 reports LLVM and Clang developments, including Google Summer of Code mentoring opportunities, releases of Pocl and TCE, an upcoming LLVM microconference, mailing-list discussions, and recent LLVM commits.

### Source excerpt

Welcome to the sixty-third issue of LLVM Weekly, a weekly newsletter (published every Monday) covering developments in LLVM, Clang, and related projects. LLVM Weekly is brought to you by Alex Bradbury. Subscribe to future issues at http://llvmweekly.org and pass it on to anyone else you think may be interested. Please send any tips or feedback to asb@asbradbury.org, or @llvmweekly or @asbradbury on Twitter. The canonical home for this issue can be found here at llvmweekly.org. News and articles from around the web LLVM is taking part in Google Summer of Code as a mentoring organisation. Students can earn a $5500 stipend by working on open source projects over the summer, and applications upon today (March 16th). See here for the list of mentoring organisations advertising LLVM-related projects. Please do help spread the word. I am biased, but I'd like to draw particular attention to the wide variety of lowRISC GSoC ideas, including a project to implement an LLVM pass using tagged memory to provide protection against control-flow hijacking. Version 0.11 of Pocl, the portable open-source OpenCL implementation has been released. Additions in this release include initial Android support and MIPS architecture support. Version 1.11 of TCE, the TTA-based (Transport Triggered Architecture) Co-design Environment, which uses LLVM has been released. This release adds support for LLVM 3.6. There will be a LLVM microconference at the Linux Plumbers Conference in August. There is a call for speakers. On the mailing lists If you enjoy bikesheds, this thread may be for you. Renato Golin has kicked off a thread on commit message policy. Rui Ueyama has posted to the mailing list summarising his recent work on LLD performance improvements. The follow up responses discuss potential remaining bottlenecks. William Moses is interested in parallel extensions to LLVM IR, and the thread spawned quite a few interesting responses. Mohammad Kazem's question about counting loads and stores of va

## What's new in CPUs since the 80s?

DevFeed: [What's new in CPUs since the 80s?](<https://devfeed.tech/articles/what-s-new-in-cpus-since-the-80s-77724.md>)

Original publisher: [Read original article](<https://danluu.com/new-cpu-features/>)

Published: 2015-01-11T00:00:00Z

Content type: article

Language: en

Sources: [Danluu](<https://devfeed.tech/sources/danluu.md>)

Topics: [CPU Cache](<https://devfeed.tech/topics/cpu-cache.md>), [Supercomputing](<https://devfeed.tech/topics/supercomputing.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>), [Running Median](<https://devfeed.tech/topics/running-median.md>)

Tags: [cpus](<https://devfeed.tech/tags/cpus.md>), [linux](<https://devfeed.tech/tags/linux.md>), [memory](<https://devfeed.tech/tags/memory.md>), [pipelining](<https://devfeed.tech/tags/pipelining.md>), [simd](<https://devfeed.tech/tags/simd.md>), [smt](<https://devfeed.tech/tags/smt.md>), [supercomputing](<https://devfeed.tech/tags/supercomputing.md>), [x86](<https://devfeed.tech/tags/x86.md>)

### AI overview

The article surveys x86 and Linux CPU features that affect software performance, including caches, memory ordering and concurrency, SIMD, GPUs, virtualization, and system calls. It explains practical guidance such as improving memory locality, benchmarking on target hardware, and using specialized hardware or I/O paths for demanding workloads. It also discusses possible future developments in hardware acceleration, fast I/O, and chip design.

### Source excerpt

This is a response to the following question from David Albert: My mental model of CPUs is stuck in the 1980s: basically boxes that do arithmetic, logic, bit twiddling and shifting, and loading and storing things in memory. I'm vaguely aware of various newer developments like vector instructions (SIMD) and the idea that newer CPUs have support for virtualization (though I have no idea what that means in practice). What cool developments have I been missing? What can today's CPU do that last year's CPU couldn't? How about a CPU from two years ago, five years ago, or ten years ago? The things I'm most interested in are things that programmers have to manually take advantage of (or programming environments have to be redesigned to take advantage of) in order to use and as a result might not be using yet. I think this excludes things like Hyper-threading/SMT, but I'm not honestly sure. I'm also interested in things that CPUs can't do yet but will be able to do in the near future. Everything below refers to x86 and linux, unless otherwise indicated. History has a tendency to repeat itself, and a lot of things that were new to x86 were old hat to supercomputing, mainframe, and workstation folks. The Present Miscellania For one thing, chips have wider registers and can address more memory. In the 80s, you might have used an 8-bit CPU, but now you almost certainly have a 64-bit CPU in your machine. I'm not going to talk about this too much, since I assume you're familiar with programming a 64-bit machine. In addition to providing more address space, 64-bit mode provides more registers and more consistent floating point results (via the avoidance of pseudo-randomly getting 80-bit precision for 32 and 64 bit operations via x87 floating point). Other things that you're very likely to be using that were introduced to x86 since the early 80s include paging / virtual memory, pipelining, and floating point. Esoterica I'm also going to avoid discussing things that are now irrelevan

## LLVM Weekly - #53, Jan 5th 2015

DevFeed: [LLVM Weekly - #53, Jan 5th 2015](<https://devfeed.tech/articles/llvm-weekly-53-jan-5th-2015-42952.md>)

Original publisher: [Read original article](<https://blog.llvm.org/2015/01/llvm-weekly-53-jan-5th-2015.html>)

Author: Alex Bradbury

Published: 2015-01-05T06:30:00Z

Content type: news

Language: en

Sources: [LLVM Project](<https://devfeed.tech/sources/the-llvm-project-blog.md>)

Topics: [LLVM](<https://devfeed.tech/topics/llvm.md>), [clang](<https://devfeed.tech/topics/clang.md>), [OpenCL](<https://devfeed.tech/topics/opencl.md>), [RISC-V](<https://devfeed.tech/topics/riscv.md>), [C++](<https://devfeed.tech/topics/c-plus-plus.md>), [Python](<https://devfeed.tech/topics/python.md>), [test](<https://devfeed.tech/topics/test.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [win32](<https://devfeed.tech/topics/win32.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [clang](<https://devfeed.tech/tags/clang.md>), [llvm](<https://devfeed.tech/tags/llvm.md>), [llvmweekly](<https://devfeed.tech/tags/llvmweekly.md>), [opencl](<https://devfeed.tech/tags/opencl.md>), [python](<https://devfeed.tech/tags/python.md>), [risc-v](<https://devfeed.tech/tags/risc-v.md>), [tests](<https://devfeed.tech/tags/tests.md>), [win32](<https://devfeed.tech/tags/win32.md>)

### AI overview

The fifty-third LLVM Weekly issue covers LLVM and Clang developments, including LLVM repository activity, RadeonSI performance improvements in OpenCL benchmarks, libclang usage with Python bindings, the C++ Filesystem Technical Specification, Clang questions and tooling changes, fuzz testing, and a possible delay to LLVM/Clang 3.5.1.

### Source excerpt

Welcome to the fifty-third issue of LLVM Weekly, a weekly newsletter (published every Monday) covering developments in LLVM, Clang, and related projects. LLVM Weekly is brought to you by Alex Bradbury. Subscribe to future issues at http://llvmweekly.org and pass it on to anyone else you think may be interested. Please send any tips or feedback to asb@asbradbury.org, or @llvmweekly or @asbradbury on Twitter. I'm going to be in California next week for the RISC-V workshop. I'm arriving at SFO on Monday 12th and leaving on Sunday the 18th. Do let me know if you want to meet and talk lowRISC/RISC-V or LLVM, and we'll see what we can do. The canonical home for this issue can be found here at llvmweekly.org. News and articles from around the web I was getting ready to break out gitstats for some analysis of the LLVM repo and I find to my delight that Phoronix has saved me the trouble and has shared some stats on activity in the LLVM repo over the past year. Tom Stellard has made a blog post announcing some recent RadeonSI performance improvements on his LLVM development branch. This includes 60% improvement in one OpenCL benchmark and 10-25% in a range of other OpenCL tests. Gaëtan Lehmann has written a blog post about getting started with libclang using the Python bindings. The C++ Filesystem Technical Specification, based on the Boost.Filesystem library has been approved. On the mailing lists Virgile Bello has some questions on how he can control the calling convention in LLVM. In this case, he has an CLR frontend and is trying to pass an object on the CLR stack to a native Win32 function. Reid Kleckner suggests the best way may be to just link with Clang and use its implementation. In another followup, he links to the talk on this topic at the last LLVM dev meeting. Is anybody using the ModuleBuilder class in Clang?. If so, now is the time to speak up as it's slated to be removed. Sami Liedes has set up a new bot to test Clang with fuzzed inputs. A report from the bot

[Next page](<https://devfeed.tech/topics/opencl.md?cursor=WyIyMDE1LTAxLTA1VDA2OjMwOjAwKzAwOjAwIiwgIjI0YmE3N2RlLTFjOWEtNDAzOC1hZTkzLWM5Y2M5OGNmMzMxYyJd>)