gluon-beyond-loop-opt

Apply XCD remapping and epilogue slicing to Gluon GEMM kernels.

Updated Mar 14, 2026

Search Tags:#gluon #gemm #mfma #gpus #xcd-remapping #epilogue-slicing #l2-cache

Ready to run

npx skills add https://github.com/leonling-ll/claude-skills --skill gluon-beyond-loop-opt

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gluon-beyond-loop-opt
Source: https://github.com/leonling-ll/claude-skills/tree/main/gluon-beyond-loop-opt
Command: npx skills add https://github.com/leonling-ll/claude-skills --skill gluon-beyond-loop-opt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill identifies and applies two advanced optimizations to a Gluon GEMM kernel: XCD-aware PID remapping to improve L2 cache reuse for matrix B and epilogue M-slicing to reduce register pressure and hide store latency, enabling higher MFMA throughput on CDNA GPUs.

Core Features & Use Cases

Stage 1: XCD-aware PID remapping with grouped swizzle improves L2 hit rates for B reads by distributing PIDs across XCDs and reusing B tiles across M-block groups.
Stage 2: Epilogue M-slicing reduces VGPR pressure by slicing the final accumulator into smaller live portions, overlapping MFMA with buffer_store to hide latency.
Use Case: Optimizing a large GEMM kernel on MI300X/MI350 where B tiles are large and L2 bandwidth is a bottleneck.

Quick Start

Run the /gluon-beyond-loop-opt skill to enable XCD remapping and epilogue slicing on your Gluon GEMM kernel and verify correctness against a reference matmul.

Frequently Asked Questions about gluon-beyond-loop-opt

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I improve L2 cache reuse for matrix B in Gluon GEMM kernels on MI300X?▼

To reduce register pressure in Gluon GEMM kernels, apply epilogue M-slicing. This technique slices the final accumulator into smaller live portions, overlapping MFMA operations with buffer_store instructions to hide store latency and lower VGPR pressure.

What is XCD remapping and how does it optimize GEMM performance on CDNA GPUs?▼

XCD remapping is an optimization technique for GEMM kernels that improves L2 cache efficiency on CDNA GPUs. It distributes program IDs across XCDs using a grouped swizzle pattern, maximizing matrix B tile reuse across M-block groups for higher throughput.

How do I reduce register pressure in Gluon GEMM kernels with large accumulator shapes?▼

Does the Gluon GEMM optimization support tuning controls for XCD remapping and group sizes?▼

Yes, the Gluon GEMM optimization requires the kernel to expose NUM_XCDS and GROUP_SIZE_M controls. These parameters are necessary for tuning XCD remapping and ensuring compatibility with Gluon kernels on MI300X and MI350 GPUs.

When should I apply beyond-loop GEMM optimizations for high MFMA utilization?▼

Apply beyond-loop GEMM optimizations when targeting MI300X or MI350 GPUs with large M, N, and K shapes where L2 bandwidth is a bottleneck. These optimizations maximize MFMA utilization by improving cache efficiency and reducing register spills.

How to verify correctness after applying XCD remapping and epilogue slicing to a Gluon kernel?▼

To verify correctness after applying XCD remapping and epilogue slicing, run the optimization skill to execute the modified Gluon GEMM kernel and compare its output against a reference matmul implementation to ensure numerical accuracy.