AMD Ryzen 9 7950X 16-Core testing with a ASUS ProArt X670E-CREATOR WIFI (1004 BIOS) and NVIDIA GeForce RTX 4090 24GB on Ubuntu 22.04 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2304087-NE-NGPUTEST677
ngpu.test
AMD Ryzen 9 7950X 16-Core testing with a ASUS ProArt X670E-CREATOR WIFI (1004 BIOS) and NVIDIA GeForce RTX 4090 24GB on Ubuntu 22.04 via the Phoronix Test Suite.
,,"pts_nvidia-gpu-compute"
Processor,,AMD Ryzen 9 7950X 16-Core @ 4.50GHz (16 Cores / 32 Threads)
Motherboard,,ASUS ProArt X670E-CREATOR WIFI (1004 BIOS)
Chipset,,AMD Device 14d8
Memory,,2 x 32 GB DDR5-5600MT/s Kingston KF556C40-32
Disk,,2000GB Samsung SSD 980 PRO 2TB
Graphics,,NVIDIA GeForce RTX 4090 24GB
Audio,,NVIDIA Device 22ba
Monitor,,LG Ultra HD
Network,,Intel I225-V + MEDIATEK Device 0616
OS,,Ubuntu 22.04
Kernel,,5.19.0-38-generic (x86_64)
Desktop,,KDE Plasma 5.24.7
Display Server,,X Server 1.21.1.3
Display Driver,,NVIDIA 525.105.17
OpenGL,,4.6.0
OpenCL,,OpenCL 3.0 CUDA 12.0.151
Vulkan,,1.3.224
Compiler,,GCC 11.3.0
File-System,,xfs
Screen Resolution,,3840x2160
,,"pts_nvidia-gpu-compute"
"NeatBench - Acceleration: GPU (FPS)",HIB,4090
"MandelGPU - OpenCL Device: GPU (Samples/sec)",HIB,907383065.7
"IndigoBench - Acceleration: OpenCL GPU - Scene: Supercar (M samples/s)",HIB,80.072
"IndigoBench - Acceleration: OpenCL GPU - Scene: Bedroom (M samples/s)",HIB,35.663
"Blender - Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX (sec)",LIB,8.12
"Blender - Blend File: Barbershop - Compute: NVIDIA OptiX (sec)",LIB,29.75
"Blender - Blend File: Fishy Cat - Compute: NVIDIA OptiX (sec)",LIB,5.38
"Blender - Blend File: Classroom - Compute: NVIDIA OptiX (sec)",LIB,7.07
"NCNN - Target: Vulkan GPU - Model: FastestDet (ms)",LIB,1.99
"NCNN - Target: Vulkan GPU - Model: vision_transformer (ms)",LIB,135.14
"NCNN - Target: Vulkan GPU - Model: regnety_400m (ms)",LIB,1.36
"NCNN - Target: Vulkan GPU - Model: squeezenet_ssd (ms)",LIB,3.43
"NCNN - Target: Vulkan GPU - Model: yolov4-tiny (ms)",LIB,5.15
"NCNN - Target: Vulkan GPU - Model: resnet50 (ms)",LIB,2.07
"NCNN - Target: Vulkan GPU - Model: vgg16 (ms)",LIB,1.99
"NCNN - Target: Vulkan GPU - Model: mnasnet (ms)",LIB,0.99
"NCNN - Target: Vulkan GPU - Model: shufflenet-v2 (ms)",LIB,1.28
"NCNN - Target: Vulkan GPU - Model: mobilenet (ms)",LIB,2.68
"ViennaCL - Test: OpenCL BLAS - dGEMM-TT (GFLOPs/s)",HIB,1357
"ViennaCL - Test: OpenCL BLAS - dGEMM-TN (GFLOPs/s)",HIB,1310
"ViennaCL - Test: OpenCL BLAS - dGEMM-NT (GFLOPs/s)",HIB,1290
"ViennaCL - Test: OpenCL BLAS - dGEMM-NN (GFLOPs/s)",HIB,1167
"ViennaCL - Test: OpenCL BLAS - dGEMV-T (GB/s)",HIB,446
"ViennaCL - Test: OpenCL BLAS - dGEMV-N (GB/s)",HIB,221
"ViennaCL - Test: OpenCL BLAS - dDOT (GB/s)",HIB,730
"ViennaCL - Test: OpenCL BLAS - dAXPY (GB/s)",HIB,773
"ViennaCL - Test: OpenCL BLAS - dCOPY (GB/s)",HIB,661
"ViennaCL - Test: OpenCL BLAS - sDOT (GB/s)",HIB,451
"ViennaCL - Test: OpenCL BLAS - sAXPY (GB/s)",HIB,618
"ViennaCL - Test: OpenCL BLAS - sCOPY (GB/s)",HIB,480
"ViennaCL - Test: CPU BLAS - dGEMM-TT (GFLOPs/s)",HIB,111
"ViennaCL - Test: CPU BLAS - dGEMM-TN (GFLOPs/s)",HIB,117
"ViennaCL - Test: CPU BLAS - dGEMM-NT (GFLOPs/s)",HIB,106
"ViennaCL - Test: CPU BLAS - dGEMM-NN (GFLOPs/s)",HIB,110
"ViennaCL - Test: CPU BLAS - dGEMV-T (GB/s)",HIB,127
"ViennaCL - Test: CPU BLAS - dGEMV-N (GB/s)",HIB,101.8
"ViennaCL - Test: CPU BLAS - dDOT (GB/s)",HIB,93.4
"ViennaCL - Test: CPU BLAS - dAXPY (GB/s)",HIB,88.3
"ViennaCL - Test: CPU BLAS - dCOPY (GB/s)",HIB,58.7
"ViennaCL - Test: CPU BLAS - sDOT (GB/s)",HIB,300
"ViennaCL - Test: CPU BLAS - sCOPY (GB/s)",HIB,208
"FinanceBench - Benchmark: Black-Scholes OpenCL (ms)",LIB,2.934
"LuxCoreRender - Scene: Rainbow Colors and Prism - Acceleration: GPU (M samples/sec)",HIB,40.94
"LuxCoreRender - Scene: LuxCore Benchmark - Acceleration: GPU (M samples/sec)",HIB,19.26
"LuxCoreRender - Scene: Orange Juice - Acceleration: GPU (M samples/sec)",HIB,17.64
"LuxCoreRender - Scene: Danish Mood - Acceleration: GPU (M samples/sec)",HIB,18.84
"LuxCoreRender - Scene: DLSC - Acceleration: GPU (M samples/sec)",HIB,22.43
"ArrayFire - Test: Conjugate Gradient OpenCL (ms)",LIB,0.8731
"Rodinia - Test: OpenCL Particle Filter (sec)",LIB,2.095
"LeelaChessZero - Backend: OpenCL (Nodes/s)",HIB,46246
"clpeak - OpenCL Test: Global Memory Bandwidth (GBPS)",HIB,870.86
"clpeak - OpenCL Test: Double-Precision Double (GFLOPS)",HIB,1413.35
"clpeak - OpenCL Test: Single-Precision Float (GFLOPS)",HIB,78857.40
"clpeak - OpenCL Test: Integer Compute INT (GIOPS)",HIB,40863.0
"FAHBench - (Ns/Day)",HIB,440.4985
"OctaneBench - Total Score (Score)",HIB,1330.491247
"VkResample - Upscale: 2x - Precision: Single (ms)",LIB,7.784
"VkResample - Upscale: 2x - Precision: Double (ms)",LIB,55.387
"NAMD CUDA - ATPase Simulation - 327,506 Atoms (days/ns)",LIB,0.06968
"cl-mem - Benchmark: Write (GB/s)",HIB,799.4
"cl-mem - Benchmark: Read (GB/s)",HIB,885.5
"cl-mem - Benchmark: Copy (GB/s)",HIB,411.6
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Texture Read Bandwidth (GB/s)",HIB,3032.40
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Bus Speed Readback (GB/s)",HIB,26.3967
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Bus Speed Download (GB/s)",HIB,26.8891
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Max SP Flops (GFLOPS)",HIB,90084.7
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: GEMM SGEMM_N (GFLOPS)",HIB,28105.9
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Reduction (GB/s)",HIB,992.53
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: MD5 Hash (GHash/s)",HIB,93.4700
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: FFT SP (GFLOPS)",HIB,2778.27
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: Triad (GB/s)",HIB,26.3869
"SHOC Scalable HeterOgeneous Computing - Target: OpenCL - Benchmark: S3D (GFLOPS)",HIB,646.626
"Hashcat - Benchmark: TrueCrypt RIPEMD160 + XTS (H/s)",HIB,1867900
"Hashcat - Benchmark: SHA-512 (H/s)",HIB,6389066667
"Hashcat - Benchmark: 7-Zip (H/s)",HIB,2741600
"Hashcat - Benchmark: SHA1 (H/s)",HIB,49962233333
"Hashcat - Benchmark: MD5 (H/s)",HIB,156200000000
"VkFFT - (Benchmark Score)",HIB,63576
"Waifu2x-NCNN Vulkan - Scale: 2x - Denoise: 3 - TAA: Yes (sec)",LIB,2.468
"RealSR-NCNN - Scale: 4x - TAA: Yes (sec)",LIB,19.116
"RealSR-NCNN - Scale: 4x - TAA: No (sec)",LIB,4.211
"vkpeak - int16-vec4 (GIOPS)",HIB,39957.84
"vkpeak - int16-scalar (GIOPS)",HIB,29976.88
"vkpeak - int32-vec4 (GIOPS)",HIB,44803.57
"vkpeak - int32-scalar (GIOPS)",HIB,45045.95
"vkpeak - fp64-vec4 (GFLOPS)",HIB,1419.84
"vkpeak - fp64-scalar (GFLOPS)",HIB,1419.89
"vkpeak - fp16-vec4 (GFLOPS)",HIB,89348.10
"vkpeak - fp16-scalar (GFLOPS)",HIB,45059.05
"vkpeak - fp32-vec4 (GFLOPS)",HIB,59636.96
"vkpeak - fp32-scalar (GFLOPS)",HIB,45133.99
"Blender - Blend File: BMW27 - Compute: NVIDIA OptiX (sec)",LIB,13.27
"PlaidML - FP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL (Examples/sec)",HIB,
"PlaidML - FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL (Examples/sec)",HIB,
"PlaidML - FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL (Examples/sec)",HIB,
"PlaidML - FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL (Examples/sec)",HIB,
"PlaidML - FP16: No - Mode: Training - Network: Mobilenet - Device: OpenCL (Examples/sec)",HIB,
"NCNN - Target: Vulkan GPU - Model: alexnet (ms)",LIB,1.99
"NCNN - Target: Vulkan GPU - Model: resnet18 (ms)",LIB,1.47
"NCNN - Target: Vulkan GPU - Model: googlenet (ms)",LIB,2.30
"NCNN - Target: Vulkan GPU - Model: blazeface (ms)",LIB,0.84
"NCNN - Target: Vulkan GPU - Model: efficientnet-b0 (ms)",LIB,2.27
"NCNN - Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 (ms)",LIB,1.53
"NCNN - Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 (ms)",LIB,1.11
"Caffe - Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 1000 (ms)",LIB,
"Caffe - Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 200 (ms)",LIB,
"Caffe - Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 100 (ms)",LIB,
"Caffe - Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 1000 (ms)",LIB,
"Caffe - Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 200 (ms)",LIB,
"Caffe - Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 100 (ms)",LIB,
"GROMACS - Implementation: NVIDIA CUDA GPU - Input: water_GMX50_bare (Ns/Day)",HIB,
"ViennaCL - Test: CPU BLAS - sAXPY (GB/s)",HIB,305
"RedShift Demo - (sec)",LIB,
"Betsy GPU Compressor - Codec: ETC2 RGB - Quality: Highest (sec)",LIB,
"Betsy GPU Compressor - Codec: ETC1 - Quality: Highest (sec)",LIB,
"Libplacebo - (FPS)",HIB,
"Mixbench - Backend: NVIDIA CUDA - Benchmark: Single Precision ()",HIB,
"Mixbench - Backend: NVIDIA CUDA - Benchmark: Double Precision ()",HIB,
"Mixbench - Backend: NVIDIA CUDA - Benchmark: Half Precision ()",HIB,
"Mixbench - Backend: OpenCL - Benchmark: Single Precision ()",HIB,
"Mixbench - Backend: OpenCL - Benchmark: Double Precision ()",HIB,
"Mixbench - Backend: NVIDIA CUDA - Benchmark: Integer ()",HIB,
"Mixbench - Backend: OpenCL - Benchmark: Integer ()",HIB,
"Waifu2x-NCNN Vulkan - Scale: 2x - Denoise: 3 - TAA: No (sec)",LIB,