Radeon ROCm vs. NVIDIA OpenCL August 2017

SHOC Scalable HeterOgeneous Computing
Target: OpenCL - Benchmark: Texture Read Bandwidth

< Previous Result [SHOC Scalable HeterOgeneous Computing]
Next Result [SHOC Scalable HeterOgeneous Computing] >

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing v2015-11-10Target: OpenCL - Benchmark: Texture Read BandwidthRadeon R9 290Radeon RX 480Radeon RX 560Radeon RX 580Radeon R9 FuryGeForce GTX 780 TiGeForce GTX 960GeForce GTX 970GeForce GTX 980GeForce GTX 980 TiGeForce GTX 1050GeForce GTX 1060GeForce GTX 1070GeForce GTX 1080GeForce GTX 1080 TiRadeon Vega FE130260390520650SE +/- 1.41SE +/- 0.23SE +/- 0.14SE +/- 0.08SE +/- 0.89SE +/- 0.11SE +/- 0.45SE +/- 0.24SE +/- 1.03SE +/- 0.74SE +/- 1.17SE +/- 0.59SE +/- 0.27SE +/- 0.88SE +/- 0.23SE +/- 1.01253.64193.43115.81207.97245.68287.39277.11288.87332.11351.45274.91382.21454.47520.13596.82422.09Phoronix Test Suite 7.4.01. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

System Hardware & Software - Comments & Discussion - View All Results


The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite.

Radeon ROCm vs. NVIDIA OpenCL August 2017

Radeon ROCm and NVIDIA OpenCL Linux testing by Michael Larabel for a future article on Phoronix.

This test can be reproduced via the Phoronix Test Suite by running the phoronix-test-suite benchmark 1708103-TY-1708107TY43 command.