@hgpu

High performance computing on graphics processing units (GPU): AMD/ATI, nVidia, Intel Xeon Phi, CUDA, OpenCL, OpenGL, GPGPU, HPC

hgpu.org/
Joined May 2011
  • Tweets10.7K
  • Following119
  • Followers3.9K
10Media
DeepSeek-V4-Flash on AMD gfx90a: Correctness Recovery and Inference Performance Engineering #AMD #HIP #LLM #Performance #DeepSeek hgpu.org/?p=31229

DeepSeek-V4-Flash on AMD gfx90a: Correctness Recovery and Inference Performance Engineering

We present the enablement, correctness recovery, and performance engineering of DeepSeek-V4-Flash inference on AMD Instinct MI250 GPUs using the gfx90a/CDNA2 architecture. The system integrates nat…

hgpu.org
1
2
11
729
Automated Instruction Encoding Synthesis for Modern GPU ISA Compression #CUDA #ISA #HardwareArchitecture #Package hgpu.org/?p=31226

Automated Instruction Encoding Synthesis for Modern GPU ISA Compression

Modern GPU kernels increasingly stress the instruction supply path, while fixed instruction containers can leave substantial footprint slack. This paper presents an automated encoding-synthesis fra…

hgpu.org
2
7
542
PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving #CUDA #LLM #Performance #Package hgpu.org/?p=31227

PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving

Repeated prompt prefixes are increasingly common in LLM serving workloads, appearing in system prompts, templated retrieval-augmented generation pipelines, agent frameworks, and multi-turn conversa…

hgpu.org
4
332
Accelerating the Solving of Many Tiny General Linear Systems on GPUs: Application to Constitutive Laws #CUDA #LinearAlgebra hgpu.org/?p=31228

Accelerating the Solving of Many Tiny General Linear Systems on GPUs: Application to Constitutive...

Many applications require solving large numbers of independent linear systems on GPUs. While this need is well addressed for small to large systems, tiny ones, understood here as systems of dimensi…

hgpu.org
2
1
266
AutoTuneBench: Trustworthy Measurement for Agent Auto-Tuning of LLM Serving Engines #CUDA #LLM #Performance #Package hgpu.org/?p=31225

AutoTuneBench: Trustworthy Measurement for Agent Auto-Tuning of LLM Serving Engines

Large language model agents tune GPU kernels and serving engines through a closed loop of propose, measure, and keep, but the measurements behind this loop are not trustworthy. We characterize four…

hgpu.org
178
Stencil Computation at the Intersection of AI and HPC #Triton #SYCL #AI #HPC #Stencil hgpu.org/?p=31200

Stencil Computation at the Intersection of AI and HPC

Tensor compilers such as TinyTC and OpenAI Triton were originally developed for AI workloads, but the same tiling and memory abstractions can be applied to implement efficient high-order stencils f…

hgpu.org
273
MaxKernel: Agentic Kernel Generation for TPUs #TPU #Package hgpu.org/?p=31198

MaxKernel: Agentic Kernel Generation for TPUs

Designing and authoring high-performance custom kernels for accelerators is a complex task that requires deep hardware-level expertise. Large Language Models (LLM) can be leveraged together with re…

hgpu.org
4
1
7
848
Taming Bitwise Behavior in GPU Kernels with Tensor Core: Black-Box Reconstruction, Compiler Enforcement, and Static Verification #CUDA #PTX #Triton hgpu.org/?p=31199

Taming Bitwise Behavior in GPU Kernels with Tensor Core: Black-Box Reconstruction, Compiler...

Determinism and numerical reproducibility are increasingly required of GPU kernels in machine learning systems, yet deterministic implementations of the same kernel can still differ bit for bit. Fl…

hgpu.org
2
1
8
625
Every Kernel Is a Join: Automatic Multi-GPU Parallelism for AI Computations in Einsummable #CUDA #Triton #LLM #AI #Package hgpu.org/?p=31197
1
4
30
2,127
Hardware-Aware FP4 FlashAttention-4 #CUDA #PTX #FP4 #Package hgpu.org/?p=31196

Hardware-Aware FP4 FlashAttention-4

Blackwell’s 4-bit floating-point (FP4) tensor cores do not automatically make attention faster because softmax conversion and on-chip dependencies dominate once its matrix products shrink. We…

hgpu.org
3
18
1,412
PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX #PTX #LLM #Package hgpu.org/?p=31135

PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX

We introduce PTXBench, a benchmark for evaluating and adapting large language models (LLMs) to use architecture-specific PTX for GPU kernel optimization. PTXBench measures functional correctness, w…

hgpu.org
2
5
26
2,043
Benchmarking Confidential Computing Performance on NVIDIA Blackwell GPUs #CUDA #Security hgpu.org/?p=31134

Benchmarking Confidential Computing Performance on NVIDIA Blackwell GPUs

This paper measures the performance impact of running large language model inference and training inside a Trusted Execution Environment (TEE) on NVIDIA B200 GPUs, using Intel Trust Domain Extensio…

hgpu.org
1
3
377
Concurrency Response of Plain Global Loads on the NVIDIA H100 #CUDA #Performance #HardwareArchitecture hgpu.org/?p=31133

Concurrency Response of Plain Global Loads on the NVIDIA H100

The bandwidth a memory-bound GPU kernel sustains is set by how many bytes it keeps in flight. We use Little’s Law here as throughput accounting, not as a measured hardware pool. CUDA fills th…

hgpu.org
1
306
An HPC Approach to Accelerate Tensor Decompositions #CUDA #HPC hgpu.org/?p=31132

An HPC Approach to Accelerate Tensor Decompositions

Quantum systems grow in complexity so rapidly that even modest models become difficult to simulate, creating a strong need for methods that can handle high-dimensional data, also known as tensors. …

hgpu.org
2
12
798
RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks #Triton #CUDA #LLM #Package hgpu.org/?p=31131

RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks

In modern AI frameworks, GPU kernels are key to overall system performance. Combining usability, portability, and near-handwritten CUDA performance, Triton is widely adopted for implementing GPU ke…

hgpu.org
223
Hand-Written PTX Tensor-Core GEMM Kernels: A Multi-Precision Study on NVIDIA L4 #PTX #Package hgpu.org/?p=31108

Hand-Written PTX Tensor-Core GEMM Kernels: A Multi-Precision Study on NVIDIA L4

High-performance Tensor Core kernels rely on a low-level PTX pipeline built from asynchronous data movement with this http URL, warp-level matrix loads with ldmatrix, and matrix multiply-accumulate…

hgpu.org
1
9
53
3,714
A Contract-Grade Verifier for LLM-Generated GPU Kernels, and a Native Blackwell Backward for the Gated-Linear-Recurrence Family #Triton #LLM hgpu.org/?p=31107

A Contract-Grade Verifier for LLM-Generated GPU Kernels, and a Native Blackwell Backward for the...

Systems that generate GPU kernels with language models report high correctness rates. Those rates come from a single loose test: run the kernel on a few random inputs at one fixed shape and accept …

hgpu.org
1
10
789
Spec Sheets Are Not Kernels: An ISA- and Source-Level Audit of INT8 Availability on NVIDIA Blackwell Ultra #PTX #Triton #ISA hgpu.org/?p=31106

Spec Sheets Are Not Kernels: An ISA- and Source-Level Audit of INT8 Availability on NVIDIA Blackw...

NVIDI’s published specifications give the Blackwell Ultra GPU (B300) a dense-compute ratio of roughly 30:1 between FP8 and INT8 tensor-core throughput; its predecessors, H200 and B200, both p…

hgpu.org
2
13
1,187
CAKE: Compiler-Agent Co-Design for Frontier Kernel Evolution #PTX #CUDA #Compilers hgpu.org/?p=31105

CAKE: Compiler-Agent Co-Design for Frontier Kernel Evolution

GPU kernel agents and GPU programming languages have advanced separately, leaving expert kernels difficult to reproduce. Agents usually treat the compiler as a fixed black box and receive only erro…

hgpu.org
3
6
678
Validation-Centric AI-Assisted GPU Porting of a 250,000+ Line Legacy Weather Simulation Code #OpenACC #Fortran #OpenMP #CodeGeneration hgpu.org/?p=31104

Validation-Centric AI-Assisted GPU Porting of a 250,000+ Line Legacy Weather Simulation Code

Recent advances in large language models have made CLI-based AI agents a practical tool for accelerating GPU porting of large legacy scientific applications. Such applications, however, are not mer…

hgpu.org
356
Load more