LLVM Clang Shows Off Great Performance Advantage On NVIDIA GH200's Neoverse-V2 Cores

Written by Michael Larabel in Software on 18 March 2024 at 11:20 AM EDT. Page 3 of 4. 14 Comments.
TSCP benchmark with settings of AI Chess Performance. Clang 17 was the fastest.
GraphicsMagick benchmark with settings of Operation: Swirl. Clang 17 was the fastest.
GraphicsMagick benchmark with settings of Operation: Rotate. Clang 17 was the fastest.
GraphicsMagick benchmark with settings of Operation: Sharpen. Clang 17 was the fastest.
GraphicsMagick benchmark with settings of Operation: Enhanced. GCC 13 was the fastest.
GraphicsMagick benchmark with settings of Operation: Resizing. GCC 13 was the fastest.
GraphicsMagick benchmark with settings of Operation: Noise-Gaussian. GCC 13 was the fastest.
GraphicsMagick benchmark with settings of Operation: HWB Color Space. GCC 13 was the fastest.

GCC did pick up a few wins in the OpenMP-threaded GraphicsMagick software but overall this was quite a fascinating race between these two open-source compilers.

libavif avifenc benchmark with settings of Encoder Speed: 0. GCC 13 was the fastest.
libavif avifenc benchmark with settings of Encoder Speed: 2. GCC 13 was the fastest.
libavif avifenc benchmark with settings of Encoder Speed: 6, Lossless. Clang 17 was the fastest.
C-Ray benchmark with settings of Total Time, 4K, 16 Rays Per Pixel. GCC 13 was the fastest.
Primesieve benchmark with settings of Length: 1e13. GCC 13 was the fastest.
FLAC Audio Encoding benchmark with settings of WAV To FLAC. Clang 17 was the fastest.
Opus Codec Encoding benchmark with settings of WAV To Opus Encode. Clang 17 was the fastest.
Helsing benchmark with settings of Digit Range: 14 digit. GCC 13 was the fastest.
In some of the tested workloads the performance advantage to compiling the software with Clang rather than the default GCC was very significant on the NVIDIA GH200 server.


Related Articles
Intel Core Ultra "Meteor Lake" Performance Improves With Linux 6.9
GCC 14 vs. LLVM Clang 18 Compiler Performance On Fedora 40
Intel Xeon Max Sees Some Performance Gains For OpenVINO & ONNX With Linux 6.9
Linux 6.9 Drives AMD 4th Gen EPYC Performance Even Higher For Some Workloads
Intel Core Ultra "Meteor Lake" Yields Faster Performance With Linux 6.9
Google Cloud's C3D Instances Provide Strong Performance Value For PingCAP's TiDB