NVIDIA vs. Radeon OpenCL compute testing on ubuntu Linux. Tests by Michael Larabel for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1707112-TR-1707100PT51
OpenCL ROCm 1.6 Radeon Compute vs. NVIDIA Linux
NVIDIA vs. Radeon OpenCL compute testing on ubuntu Linux. Tests by Michael Larabel for a future article.
,,"Radeon RX 460","Radeon RX 480","Radeon RX 560","Radeon RX 580","Radeon R9 Fury","GeForce GTX 780 Ti","GeForce GTX 960","GeForce GTX 970","GeForce GTX 980","GeForce GTX 980 Ti","GeForce GTX 1050","GeForce GTX 1060","GeForce GTX 1070","GeForce GTX 1080","GeForce GTX 1080 Ti","Intel Core i7-4790"
Processor,,Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-7740K @ 4.50GHz (8 Cores),Intel Core i7-4790 @ 4.00GHz (8 Cores)
Motherboard,,ASUS PRIME X299-A,ASUS PRIME X299-A,ASUS PRIME X299-A,ASUS PRIME X299-A,ASUS PRIME X299-A,ASUS PRIME X299-A,ASUS PRIME X299-A,ASUS PRIME X299-A,ASUS PRIME X299-A,ASUS PRIME X299-A,ASUS PRIME X299-A,ASUS PRIME X299-A,ASUS PRIME X299-A,ASUS PRIME X299-A,ASUS PRIME X299-A,ASUS H97-PRO
Chipset,,Intel Device 591f,Intel Device 591f,Intel Device 591f,Intel Device 591f,Intel Device 591f,Intel Device 591f,Intel Device 591f,Intel Device 591f,Intel Device 591f,Intel Device 591f,Intel Device 591f,Intel Device 591f,Intel Device 591f,Intel Device 591f,Intel Device 591f,Intel 4th Gen Core DRAM
Memory,,16384MB,16384MB,16384MB,16384MB,16384MB,16384MB,16384MB,16384MB,16384MB,16384MB,16384MB,16384MB,16384MB,16384MB,16384MB,8192MB
Disk,,Samsung SSD 950 PRO 256GB,Samsung SSD 950 PRO 256GB,Samsung SSD 950 PRO 256GB,Samsung SSD 950 PRO 256GB,Samsung SSD 950 PRO 256GB,Samsung SSD 950 PRO 256GB,Samsung SSD 950 PRO 256GB,Samsung SSD 950 PRO 256GB,Samsung SSD 950 PRO 256GB,Samsung SSD 950 PRO 256GB,Samsung SSD 950 PRO 256GB,Samsung SSD 950 PRO 256GB,Samsung SSD 950 PRO 256GB,Samsung SSD 950 PRO 256GB,Samsung SSD 950 PRO 256GB,250GB Samsung SSD 850 + 2000GB Western Digital WD20EZRZ-00Z
Graphics,,AMD POLARIS11 1920MB,AMD POLARIS10 8064MB,AMD POLARIS11 3968MB,MSI AMD POLARIS10 8064MB,Sapphire AMD Radeon R9 FURY / NANO 3968MB,NVIDIA GeForce GTX 780 Ti 3072MB (875/3500MHz),eVGA NVIDIA GeForce GTX 960 2048MB (1277/3505MHz),eVGA NVIDIA GeForce GTX 970 4096MB (1163/3505MHz),NVIDIA GeForce GTX 980 4096MB (1126/3505MHz),NVIDIA GeForce GTX 980 Ti 6144MB (999/3505MHz),Zotac NVIDIA GeForce GTX 1050 2048MB (1354/3504MHz),NVIDIA GeForce GTX 1060 6GB 6144MB (1506/4006MHz),NVIDIA GeForce GTX 1070 8192MB (1506/4006MHz),NVIDIA GeForce GTX 1080 8192MB (1607/5005MHz),NVIDIA GeForce GTX 1080 Ti 11264MB (1480/5508MHz),ASUS NVIDIA GeForce GTX 970
Audio,,Realtek Generic,Realtek Generic,Realtek Generic,Realtek Generic,Realtek Generic,Realtek Generic,Realtek Generic,Realtek Generic,Realtek Generic,Realtek Generic,Realtek Generic,Realtek Generic,Realtek Generic,Realtek Generic,Realtek Generic,Intel Xeon E3-1200 v3/4th
Network,,Intel Connection,Intel Connection,Intel Connection,Intel Connection,Intel Connection,Intel Connection,Intel Connection,Intel Connection,Intel Connection,Intel Connection,Intel Connection,Intel Connection,Intel Connection,Intel Connection,Intel Connection,Intel Connection
OS,,Ubuntu 16.04,Ubuntu 16.04,Ubuntu 16.04,Ubuntu 16.04,Ubuntu 16.04,Ubuntu 16.04,Ubuntu 16.04,Ubuntu 16.04,Ubuntu 16.04,Ubuntu 16.04,Ubuntu 16.04,Ubuntu 16.04,Ubuntu 16.04,Ubuntu 16.04,Ubuntu 16.04,Arch rolling
Kernel,,4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64),4.11.9-ck (x86_64)
Desktop,,Unity 7.4.0,Unity 7.4.0,Unity 7.4.0,Unity 7.4.0,Unity 7.4.0,Unity 7.4.0,Unity 7.4.0,Unity 7.4.0,Unity 7.4.0,Unity 7.4.0,Unity 7.4.0,Unity 7.4.0,Unity 7.4.0,Unity 7.4.0,Unity 7.4.0,
Display Server,,X Server 1.18.4,X Server 1.18.4,X Server 1.18.4,X Server 1.18.4,X Server 1.18.4,X Server 1.18.4,X Server 1.18.4,X Server 1.18.4,X Server 1.18.4,X Server 1.18.4,X Server 1.18.4,X Server 1.18.4,X Server 1.18.4,X Server 1.18.4,X Server 1.18.4,
Display Driver,,amdgpu 1.1.2,amdgpu 1.1.2,amdgpu 1.1.2,modesetting 1.18.4,modesetting 1.18.4,NVIDIA 384.47,NVIDIA 384.47,NVIDIA 384.47,NVIDIA 384.47,NVIDIA 384.47,NVIDIA 384.47,NVIDIA 384.47,NVIDIA 384.47,NVIDIA 384.47,NVIDIA 384.47,
OpenGL,,4.1 Mesa 12.0.6 Gallium 0.4,4.1 Mesa 12.0.6 Gallium 0.4,4.1 Mesa 12.0.6 Gallium 0.4,4.1 Mesa 12.0.6 Gallium 0.4,4.1 Mesa 12.0.6 Gallium 0.4,4.5.0,4.5.0,4.5.0,4.5.0,4.5.0,4.5.0,4.5.0,4.5.0,4.5.0,4.5.0,
OpenCL,,OpenCL 2.0 AMD-APP (2442.0),OpenCL 2.0 AMD-APP (2442.0),OpenCL 2.0 AMD-APP (2442.0),OpenCL 2.0 AMD-APP (2442.0),OpenCL 2.0 AMD-APP (2442.0),OpenCL 1.2 CUDA 9.0.101,OpenCL 1.2 CUDA 9.0.101,OpenCL 1.2 CUDA 9.0.101,OpenCL 1.2 CUDA 9.0.101,OpenCL 1.2 CUDA 9.0.101,OpenCL 1.2 CUDA 9.0.101,OpenCL 1.2 CUDA 9.0.101,OpenCL 1.2 CUDA 9.0.101,OpenCL 1.2 CUDA 9.0.101,OpenCL 1.2 CUDA 9.0.101,
Compiler,,GCC 5.4.0 20160609,GCC 5.4.0 20160609,GCC 5.4.0 20160609,GCC 5.4.0 20160609,GCC 5.4.0 20160609,GCC 5.4.0 20160609,GCC 5.4.0 20160609,GCC 5.4.0 20160609,GCC 5.4.0 20160609,GCC 5.4.0 20160609,GCC 5.4.0 20160609,GCC 5.4.0 20160609,GCC 5.4.0 20160609,GCC 5.4.0 20160609,GCC 5.4.0 20160609,
File-System,,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,ext4,btrfs
Screen Resolution,,3840x2160,3840x2160,3840x2160,3840x2160,3840x2160,3840x2160,3840x2160,3840x2160,3840x2160,3840x2160,3840x2160,3840x2160,3840x2160,3840x2160,3840x2160,1024x768
Vulkan,,,,,,,,,,,,,,,,,1.0.24
,,"Radeon RX 460","Radeon RX 480","Radeon RX 560","Radeon RX 580","Radeon R9 Fury","GeForce GTX 780 Ti","GeForce GTX 960","GeForce GTX 970","GeForce GTX 980","GeForce GTX 980 Ti","GeForce GTX 1050","GeForce GTX 1060","GeForce GTX 1070","GeForce GTX 1080","GeForce GTX 1080 Ti","Intel Core i7-4790"
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Bus Speed Download (GB/s)",HIB,5.71,11.47,5.72,11.49,11.38,13.00,13.00,13.00,13.00,13.00,13.00,12.99,13.00,13.00,13.00,
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Bus Speed Readback (GB/s)",HIB,5.20,10.42,5.24,10.21,10.61,13.20,13.19,13.20,13.20,13.20,13.20,13.20,13.20,13.20,13.20,
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Texture Read Bandwidth (GB/s)",HIB,83.67,176.79,105.19,190.13,239.03,286.87,279.37,288.61,333.05,350.63,276.45,381.92,456.70,528.02,600.45,
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Texture Read Bandwidth (GB/s/Watt)",HIB,0.96,1.33,1.21,1.45,1.51,1.12,2.47,1.84,2.25,1.82,3.12,3.16,2.95,3.64,3.15,
"SHOC Scalable HeterOgeneous Computing - System Power Consumption Monitor (Watts)",LIB,87.53,133.18,86.87,131.39,157.83,255.96,113.15,156.96,147.85,192.16,88.68,120.86,154.6,145.13,190.56,
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: FFT SP (GFLOPS)",HIB,173.12,460.84,208.75,496.76,550.95,429.63,207.09,384.81,447.24,694.57,253.32,404.59,553.04,652.64,980.92,
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: MD5 Hash (GHash/s)",HIB,,,,,,4.68,4.49,6.54,7.56,9.29,3.23,7.36,10.69,14.36,19.99,
"SHOC Scalable HeterOgeneous Computing - System Power Consumption Monitor (Watts)",LIB,75.45,98.95,56.9,68.8,98.9,139.5,72.85,84,55.9,142.7,67.65,71,74.45,49.0,118.8,
"LuxMark - OpenCL Device: GPU - Scene: Luxball HDR (Score)",HIB,3872,9731,4481,10160,12894,9516,6114,10731,11955,14961,6576,11627,16184,12923,19842,
"LuxMark - OpenCL Device: GPU - Scene: Luxball HDR (Score/Watt)",HIB,36.39,51.41,43.14,51.48,54.91,32.63,43.35,57.14,59.86,60.65,60.76,78.53,89.05,72.32,78.40,
"LuxMark - System Power Consumption Monitor (Watts)",LIB,106.41,189.27,103.88,197.35,234.81,291.66,141.04,187.81,199.7,246.7,108.23,148.06,181.74,178.68,253.08,
"LuxMark - System Power Consumption Monitor (Watts)",LIB,81.4,103.14,77.41,,116.66,,,,,,,86.49,,97.96,,
"LuxMark - OpenCL Device: GPU - Scene: Hotel (Score)",HIB,430,1063,507,1206,1369,1200,1125,1756,1863,2034,1023,1782,2506,2643,3739,
"LuxMark - OpenCL Device: GPU - Scene: Hotel (Score/Watt)",HIB,4.28,6.29,5.15,6.83,6.34,4.38,7.56,9.24,9.22,8.73,9.61,12.40,13.70,13.70,13.96,
"LuxMark - System Power Consumption Monitor (Watts)",LIB,100.49,169.01,98.46,176.61,215.97,274.22,148.91,190.14,201.97,233.07,106.45,143.77,182.92,192.91,267.82,
"Mixbench - Benchmark: Single Precision (GFLOPS)",HIB,1851.75,5442.89,2303.86,5854.94,6501.19,4260.60,2726.15,4121.47,4692.97,5816.30,2037.30,4403.62,6374.80,8489.90,,
"Mixbench - Benchmark: Double Precision (GFLOPS)",HIB,134.11,362.18,149.51,389.88,440.79,245.04,92.73,137.54,159.89,197.04,66.66,152.40,222.10,293.93,,
"Mixbench - Benchmark: Integer (GIOPS)",HIB,422.38,1139.87,487.82,1226.84,1385.89,967.53,835.02,1220.95,1404.21,1717.69,615.44,1370.35,2027.70,2656.67,,
"Mixbench - System Power Consumption Monitor (Watts)",LIB,79.72,95.82,84.7,113.58,84.5,195.9,53.1,104.8,121.0,151.8,90.8,77.7,50.9,49.6,,
"Darktable - Test: Boat - Acceleration: OpenCL (sec)",LIB,7.98,4.25,6.96,4.22,3.50,15.11,19.13,15.46,15.02,4.05,17.76,4.51,3.71,3.55,3.03,
"Darktable - Test: Masskrug - Acceleration: OpenCL (sec)",LIB,0.29,0.17,0.29,0.17,0.13,0.22,0.20,0.17,0.16,0.17,0.17,0.14,0.13,0.13,0.13,
"Darktable - Test: Server Room - Acceleration: OpenCL (sec)",LIB,0.28,0.17,0.31,0.16,0.15,0.21,0.20,0.17,0.17,0.17,0.18,0.14,0.14,0.13,0.13,
"ViennaCL - OpenCL LU Factorization (GFLOPS)",HIB,7.33,12.36,9.54,13.01,20.60,56.89,47.42,52.87,54.76,56.98,42.12,54.25,58.69,61.06,63.36,
"cl-mem - Benchmark: Read (GB/s)",HIB,91.50,151.13,89.47,156.93,121.03,271.70,,143.67,164.50,266.07,94.90,153.40,205.37,228.73,337.90,
"cl-mem - Benchmark: Read (GB/s/Watt)",HIB,0.92,1.00,0.95,1.08,0.73,1.04,,1.05,1.12,1.53,1.05,1.33,1.57,1.76,1.82,
"cl-mem - Benchmark: Write (GB/s)",HIB,78.57,146.30,74.50,158.07,300.30,250.80,,129.20,151.80,238.07,85.70,139.37,191.20,214.97,334.80,
"cl-mem - Benchmark: Copy (GB/s)",HIB,77.87,173.13,77.20,172.20,198.43,237.00,,125.30,142.50,216.40,86.70,138.97,186.57,208.83,316.60,
"FAHBench - Phoronix Test Suite v7.2.1 (Ns/Day)",HIB,,,,,,72.76,58.59,86.07,97.56,109.12,49.72,97.88,132.83,146.29,186.33,83.97
"FAHBench - Phoronix Test Suite v7.2.1 (Ns/Day/Watt)",HIB,,,,,,0.36,0.50,0.62,0.67,0.63,0.54,0.85,0.96,1.01,1.02,
"FAHBench - System Power Consumption Monitor (Watts)",LIB,,,,63.5,,204.01,118.26,139.24,145.25,172.14,92.89,114.63,138.5,145.55,183.12,
"clpeak - OpenCL Test: Global Memory Bandwidth (GBPS)",HIB,89.25,203.08,88.69,201.45,388.73,252.46,81.13,143.41,164.05,262.13,92.42,146.64,196.24,222.43,329.40,
"clpeak - OpenCL Test: Single-Precision Float (GFLOPS)",HIB,2135.23,5755.59,2599.84,6195.09,7064.24,3661.68,2498.99,3725.85,4286.78,5303.61,1941.07,4264.43,6332.82,8398.22,11828.88,
"clpeak - OpenCL Test: Double-Precision Double (GFLOPS)",HIB,135.17,364.11,164.57,391.92,447.25,246.92,92.88,137.42,159.90,197.36,66.72,151.32,225.42,298.47,417.87,
"clpeak - OpenCL Test: Integer Compute INT (GIOPS)",HIB,414.21,1161.64,525.62,1252.48,1429.19,958.80,781.83,1134.30,1293.68,1605.34,562.46,1227.52,1657.74,2372.63,3276.83,
"clpeak - OpenCL Test: Integer Compute INT (GIOPS/Watt)",HIB,4.79,8.59,5.33,9.62,8.60,,5.35,,7.08,,,,,,,
"clpeak - System Power Consumption Monitor (Watts)",LIB,86.44,135.3,98.6,130.17,166.19,148.7,146.17,75.15,182.83,195.05,87.6,185.3,117.05,93.75,158.7,
"clpeak - OpenCL Test: Transfer Bandwidth enqueueWriteBuffer (GBPS)",HIB,30.03,30.13,30.04,30.47,30.52,12.36,12.44,12.47,12.46,12.46,12.53,12.61,12.60,12.63,12.62,
"clpeak - OpenCL Test: Transfer Bandwidth enqueueReadBuffer (GBPS)",HIB,12.24,12.25,12.25,12.26,12.25,11.24,11.32,11.33,11.25,11.37,11.32,11.32,11.36,11.32,11.36,
"clpeak - OpenCL Test: Kernel Latency (us)",LIB,42.49,39.87,41.06,39.54,41.62,5.67,3.94,4.08,4.12,4.32,3.68,3.60,3.60,3.59,3.60,
"Rodinia - Test: OpenCL Particle Filter (sec)",LIB,,,,6.62,,15.30,18.47,13.11,11.87,10.14,26.09,12.15,8.27,6.56,5.03,13.52
"Lulesh OpenCL - Phoronix Test Suite v7.2.1 (z/s)",HIB,840.73,878.41,852.97,866.99,845.27,,,,,,,,,,,
"Xsbench OpenCL - Phoronix Test Suite v7.2.1 (Lookups/s)",HIB,36982576,74635621,38606004,74435707,85206540,,,,,,,,,,,
"CoMD OpenCL - Average Atom Update Rate (us/atom/task)",HIB,4.85,4.84,4.84,4.85,4.85,4.84,4.84,4.84,4.84,4.85,4.84,4.85,4.84,4.84,4.84,3.50
"Ethereum Ethminer - Device: GPU OpenCL (H/s)",HIB,7176920,12543590,7203134,12811559,16587889,15689318,10341580,17974339,19740899,18018030,11398894,18653001,25311459,20721026,31569419,
"Ethereum Ethminer - Device: GPU OpenCL (H/s/Watt)",HIB,67367.83,72609.92,69113.46,72012.98,80363.35,60749.50,70561.75,94763.88,96016.05,76784.79,102539.74,124485.61,135952.92,115090.84,126492.71,
"Ethereum Ethminer - System Power Consumption Monitor (Watts)",LIB,106.53,172.75,104.22,177.91,206.41,258.26,146.56,189.68,205.6,234.66,111.17,149.84,186.18,180.04,249.58,
"System Power Consumption Monitor - Phoronix Test Suite System Monitoring (Watts)",,84.6,129.75,82.97,135.51,150.69,201.83,116.21,141.74,145.65,185.09,90.71,109.18,139.11,140.7,184.89,
"Darktable - Test: Boat - Acceleration: OpenCL (sec)",LIB,,,,,,,,,,,,,,,,4.96
"Darktable - Test: Masskrug - Acceleration: OpenCL (sec)",LIB,,,,,,,,,,,,,,,,12.85
"Darktable - Test: Server Room - Acceleration: OpenCL (sec)",LIB,,,,,,,,,,,,,,,,7.81