nvidia rtx 5090 compute benchmarks Tests for a future article. Intel Core Ultra 9 285K testing with a ASUS ROG MAXIMUS Z890 HERO (1203 BIOS) and ASUS NVIDIA GeForce RTX 5090 32GB on Ubuntu 24.10 via the Phoronix Test Suite. rtx 5090: Processor: Intel Core Ultra 9 285K @ 5.10GHz (24 Cores), Motherboard: ASUS ROG MAXIMUS Z890 HERO (1203 BIOS), Chipset: Intel Device ae7f, Memory: 2 x 16GB DDR5-6400MT/s Micron CP16G64C38U5B.M8D1, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 4001GB Western Digital WD_BLACK SN850X 4000GB, Graphics: ASUS NVIDIA GeForce RTX 5090 32GB, Audio: Intel Device 7f50, Monitor: ASUS VP28U, Network: Realtek Device 8126 + Intel I226-V + Intel Wi-Fi 7 OS: Ubuntu 24.10, Kernel: 6.11.0-13-generic (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server 1.21.1.13, Display Driver: NVIDIA 570.86.10, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.8.51 + OpenCL 3.0, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 3840x2160 NVIDIA 5090: Processor: Intel Core Ultra 9 285K @ 5.10GHz (24 Cores), Motherboard: ASUS ROG MAXIMUS Z890 HERO (1203 BIOS), Chipset: Intel Device ae7f, Memory: 2 x 16GB DDR5-6400MT/s Micron CP16G64C38U5B.M8D1, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 4001GB Western Digital WD_BLACK SN850X 4000GB, Graphics: ASUS NVIDIA GeForce RTX 5090 32GB, Audio: Intel Device 7f50, Monitor: ASUS VP28U, Network: Realtek Device 8126 + Intel I226-V + Intel Wi-Fi 7 OS: Ubuntu 24.10, Kernel: 6.11.0-13-generic (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server 1.21.1.13, Display Driver: NVIDIA 570.86.10, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.8.51 + OpenCL 3.0, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 3840x2160 GeForce RTX 5090: Processor: Intel Core Ultra 9 285K @ 5.10GHz (24 Cores), Motherboard: ASUS ROG MAXIMUS Z890 HERO (1203 BIOS), Chipset: Intel Device ae7f, Memory: 2 x 16GB DDR5-6400MT/s Micron CP16G64C38U5B.M8D1, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0 + 4001GB Western Digital WD_BLACK SN850X 4000GB, Graphics: ASUS NVIDIA GeForce RTX 5090 32GB, Audio: Intel Device 7f50, Monitor: ASUS VP28U, Network: Realtek Device 8126 + Intel I226-V + Intel Wi-Fi 7 OS: Ubuntu 24.10, Kernel: 6.11.0-13-generic (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server 1.21.1.13, Display Driver: NVIDIA 570.86.10, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.8.51 + OpenCL 3.0, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 3840x2160 Blender 4.3 Blend File: BMW27 - Compute: NVIDIA CUDA Seconds < Lower Is Better rtx 5090 ......... 4.72 |====================================================== NVIDIA 5090 ...... 4.72 |====================================================== GeForce RTX 5090 . 4.65 |===================================================== Blender 4.3 Blend File: BMW27 - Compute: NVIDIA OptiX Seconds < Lower Is Better rtx 5090 ......... 2.92 |===================================================== NVIDIA 5090 ...... 2.97 |====================================================== GeForce RTX 5090 . 2.98 |====================================================== Blender 4.3 Blend File: Junkshop - Compute: NVIDIA CUDA Seconds < Lower Is Better rtx 5090 ......... 8.99 |====================================================== NVIDIA 5090 ...... 8.98 |====================================================== GeForce RTX 5090 . 9.00 |====================================================== Blender 4.3 Blend File: Classroom - Compute: NVIDIA CUDA Seconds < Lower Is Better rtx 5090 ......... 8.38 |====================================================== NVIDIA 5090 ...... 8.38 |====================================================== GeForce RTX 5090 . 8.38 |====================================================== Blender 4.3 Blend File: Fishy Cat - Compute: NVIDIA CUDA Seconds < Lower Is Better rtx 5090 ......... 8.92 |====================================================== NVIDIA 5090 ...... 8.92 |====================================================== GeForce RTX 5090 . 8.92 |====================================================== Blender 4.3 Blend File: Junkshop - Compute: NVIDIA OptiX Seconds < Lower Is Better rtx 5090 ......... 5.66 |====================================================== NVIDIA 5090 ...... 5.67 |====================================================== GeForce RTX 5090 . 5.66 |====================================================== Blender 4.3 Blend File: Barbershop - Compute: NVIDIA CUDA Seconds < Lower Is Better rtx 5090 ......... 35.14 |===================================================== NVIDIA 5090 ...... 35.28 |===================================================== GeForce RTX 5090 . 35.10 |===================================================== Blender 4.3 Blend File: Classroom - Compute: NVIDIA OptiX Seconds < Lower Is Better rtx 5090 ......... 6.16 |====================================================== NVIDIA 5090 ...... 6.14 |====================================================== GeForce RTX 5090 . 6.17 |====================================================== Blender 4.3 Blend File: Fishy Cat - Compute: NVIDIA OptiX Seconds < Lower Is Better rtx 5090 ......... 4.55 |====================================================== NVIDIA 5090 ...... 4.56 |====================================================== GeForce RTX 5090 . 4.55 |====================================================== Blender 4.3 Blend File: Barbershop - Compute: NVIDIA OptiX Seconds < Lower Is Better rtx 5090 ......... 24.33 |==================================================== NVIDIA 5090 ...... 24.60 |===================================================== GeForce RTX 5090 . 24.50 |===================================================== Blender 4.3 Blend File: Pabellon Barcelona - Compute: NVIDIA CUDA Seconds < Lower Is Better rtx 5090 ......... 17.35 |===================================================== NVIDIA 5090 ...... 17.34 |===================================================== GeForce RTX 5090 . 17.44 |===================================================== Blender 4.3 Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX Seconds < Lower Is Better rtx 5090 ......... 7.00 |====================================================== NVIDIA 5090 ...... 7.06 |====================================================== GeForce RTX 5090 . 7.04 |====================================================== Chaos Group V-RAY 6.0 Mode: NVIDIA RTX GPU vpaths > Higher Is Better rtx 5090 ......... 11923 |===================================================== NVIDIA 5090 ...... 11923 |===================================================== GeForce RTX 5090 . 11923 |===================================================== Chaos Group V-RAY 6.0 Mode: NVIDIA CUDA GPU vpaths > Higher Is Better rtx 5090 ......... 4851 |====================================================== NVIDIA 5090 ...... 4882 |====================================================== GeForce RTX 5090 . 4882 |====================================================== clpeak 1.1.2 OpenCL Test: Kernel Latency us < Lower Is Better rtx 5090 ......... 5.15 |====================================================== NVIDIA 5090 ...... 5.16 |====================================================== GeForce RTX 5090 . 5.15 |====================================================== clpeak 1.1.2 OpenCL Test: Integer Compute GIOPS > Higher Is Better rtx 5090 ......... 62151.94 |================================================== NVIDIA 5090 ...... 62119.51 |================================================== GeForce RTX 5090 . 62178.05 |================================================== clpeak 1.1.2 OpenCL Test: Integer 24-bit Compute GIOPS > Higher Is Better rtx 5090 ......... 61843.11 |================================================== NVIDIA 5090 ...... 61866.86 |================================================== GeForce RTX 5090 . 61903.93 |================================================== clpeak 1.1.2 OpenCL Test: Global Memory Bandwidth GBPS > Higher Is Better rtx 5090 ......... 1562.97 |=================================================== NVIDIA 5090 ...... 1564.49 |=================================================== GeForce RTX 5090 . 1564.61 |=================================================== clpeak 1.1.2 OpenCL Test: Double-Precision Compute GFLOPS > Higher Is Better rtx 5090 ......... 1976.90 |=================================================== NVIDIA 5090 ...... 1977.26 |=================================================== GeForce RTX 5090 . 1976.78 |=================================================== clpeak 1.1.2 OpenCL Test: Single-Precision Compute GFLOPS > Higher Is Better rtx 5090 ......... 121415.53 |================================================= NVIDIA 5090 ...... 121438.41 |================================================= GeForce RTX 5090 . 121419.57 |================================================= clpeak 1.1.2 OpenCL Test: Transfer Bandwidth enqueueReadBuffer GBPS > Higher Is Better rtx 5090 ......... 13.83 |===================================================== NVIDIA 5090 ...... 13.89 |===================================================== GeForce RTX 5090 . 13.78 |===================================================== clpeak 1.1.2 OpenCL Test: Transfer Bandwidth enqueueWriteBuffer GBPS > Higher Is Better rtx 5090 ......... 18.41 |===================================================== NVIDIA 5090 ...... 18.42 |===================================================== GeForce RTX 5090 . 18.33 |===================================================== FluidX3D 3.0 Test: FP32-FP32 MLUPs/s > Higher Is Better rtx 5090 ......... 9524 |====================================================== NVIDIA 5090 ...... 9527 |====================================================== GeForce RTX 5090 . 9525 |====================================================== FluidX3D 3.0 Test: FP32-FP16C MLUPs/s > Higher Is Better rtx 5090 ......... 19140 |===================================================== NVIDIA 5090 ...... 19121 |===================================================== GeForce RTX 5090 . 19135 |===================================================== FluidX3D 3.0 Test: FP32-FP16S MLUPs/s > Higher Is Better rtx 5090 ......... 18499 |===================================================== NVIDIA 5090 ...... 18496 |===================================================== GeForce RTX 5090 . 18500 |===================================================== Hashcat 6.2.4 Benchmark: MD5 H/s > Higher Is Better rtx 5090 ......... 106848250000 |============================================== NVIDIA 5090 ...... 106216550000 |============================================== GeForce RTX 5090 . 106544000000 |============================================== Hashcat 6.2.4 Benchmark: SHA1 H/s > Higher Is Better rtx 5090 ......... 68852500000 |=============================================== NVIDIA 5090 ...... 69072700000 |=============================================== GeForce RTX 5090 . 69104300000 |=============================================== Hashcat 6.2.4 Benchmark: 7-Zip H/s > Higher Is Better rtx 5090 ......... 3272300 |=================================================== NVIDIA 5090 ...... 3276600 |=================================================== GeForce RTX 5090 . 3264300 |=================================================== Hashcat 6.2.4 Benchmark: SHA-512 H/s > Higher Is Better rtx 5090 ......... 8900400000 |================================================ NVIDIA 5090 ...... 8901200000 |================================================ GeForce RTX 5090 . 8895900000 |================================================ Hashcat 6.2.4 Benchmark: TrueCrypt RIPEMD160 + XTS H/s > Higher Is Better rtx 5090 ......... 2776000 |=================================================== NVIDIA 5090 ...... 2770700 |=================================================== GeForce RTX 5090 . 2777600 |=================================================== IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Bedroom M samples/s > Higher Is Better rtx 5090 ......... 42.76 |===================================================== NVIDIA 5090 ...... 42.85 |===================================================== GeForce RTX 5090 . 42.92 |===================================================== IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Supercar M samples/s > Higher Is Better rtx 5090 ......... 92.70 |===================================================== NVIDIA 5090 ...... 92.52 |===================================================== GeForce RTX 5090 . 92.71 |===================================================== NAMD CUDA 2.14 ATPase Simulation - 327,506 Atoms days/ns < Lower Is Better rtx 5090 ......... 0.05810 |================================================== NVIDIA 5090 ...... 0.05851 |================================================== GeForce RTX 5090 . 0.05943 |=================================================== NCNN 20241226 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better rtx 5090 ......... 42.44 |===================================================== NVIDIA 5090 ...... 39.74 |================================================== GeForce RTX 5090 . 38.91 |================================================= NCNN 20241226 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better rtx 5090 ......... 10.21 |================================================ NVIDIA 5090 ...... 11.25 |===================================================== GeForce RTX 5090 . 8.37 |======================================= NCNN 20241226 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better rtx 5090 ......... 4.68 |====================================================== NVIDIA 5090 ...... 4.28 |================================================= GeForce RTX 5090 . 4.29 |================================================== NCNN 20241226 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better rtx 5090 ......... 4.53 |================================================ NVIDIA 5090 ...... 4.04 |=========================================== GeForce RTX 5090 . 5.12 |====================================================== NCNN 20241226 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better rtx 5090 ......... 9.80 |====================================================== NVIDIA 5090 ...... 4.77 |========================== GeForce RTX 5090 . 6.55 |==================================== NCNN 20241226 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better rtx 5090 ......... 27.44 |===================================================== NVIDIA 5090 ...... 20.78 |======================================== GeForce RTX 5090 . 19.79 |====================================== NCNN 20241226 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better rtx 5090 ......... 2.67 |=============================================== NVIDIA 5090 ...... 3.05 |====================================================== GeForce RTX 5090 . 2.67 |=============================================== NCNN 20241226 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better rtx 5090 ......... 13.92 |========================================= NVIDIA 5090 ...... 12.78 |====================================== GeForce RTX 5090 . 18.06 |===================================================== NCNN 20241226 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better rtx 5090 ......... 37.05 |=================================================== NVIDIA 5090 ...... 38.73 |===================================================== GeForce RTX 5090 . 37.49 |=================================================== NCNN 20241226 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better rtx 5090 ......... 10.93 |===================================================== NVIDIA 5090 ...... 9.41 |============================================= GeForce RTX 5090 . 11.01 |===================================================== NCNN 20241226 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better rtx 5090 ......... 8.74 |==================================================== NVIDIA 5090 ...... 8.55 |=================================================== GeForce RTX 5090 . 8.99 |====================================================== NCNN 20241226 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better rtx 5090 ......... 28.58 |================================================== NVIDIA 5090 ...... 30.10 |===================================================== GeForce RTX 5090 . 29.47 |==================================================== NCNN 20241226 Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 ms < Lower Is Better rtx 5090 ......... 42.44 |===================================================== NVIDIA 5090 ...... 39.74 |================================================== GeForce RTX 5090 . 38.91 |================================================= NCNN 20241226 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better rtx 5090 ......... 39.34 |===================================================== NVIDIA 5090 ...... 38.91 |==================================================== GeForce RTX 5090 . 36.86 |================================================== NCNN 20241226 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better rtx 5090 ......... 22.02 |============================================ NVIDIA 5090 ...... 26.39 |===================================================== GeForce RTX 5090 . 25.57 |=================================================== NCNN 20241226 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better rtx 5090 ......... 47.90 |================================================ NVIDIA 5090 ...... 52.59 |===================================================== GeForce RTX 5090 . 36.20 |==================================== NCNN 20241226 Target: Vulkan GPU - Model: vision_transformer ms < Lower Is Better rtx 5090 ......... 62.76 |===================================================== NVIDIA 5090 ...... 62.86 |===================================================== GeForce RTX 5090 . 62.83 |===================================================== NCNN 20241226 Target: Vulkan GPU - Model: FastestDet ms < Lower Is Better rtx 5090 ......... 11.01 |===================================================== NVIDIA 5090 ...... 8.68 |========================================== GeForce RTX 5090 . 9.29 |============================================= ProjectPhysX OpenCL-Benchmark 1.6 Operation: FP64 Compute TFLOPs/s > Higher Is Better rtx 5090 ......... 1.950 |===================================================== NVIDIA 5090 ...... 1.950 |===================================================== GeForce RTX 5090 . 1.951 |===================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: FP32 Compute TFLOPs/s > Higher Is Better rtx 5090 ......... 117.85 |==================================================== NVIDIA 5090 ...... 117.86 |==================================================== GeForce RTX 5090 . 117.88 |==================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: FP16 Compute TFLOPs/s > Higher Is Better rtx 5090 ......... 122.91 |==================================================== NVIDIA 5090 ...... 122.94 |==================================================== GeForce RTX 5090 . 122.94 |==================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: INT64 Compute TIOPs/s > Higher Is Better rtx 5090 ......... 4.396 |===================================================== NVIDIA 5090 ...... 4.400 |===================================================== GeForce RTX 5090 . 4.392 |===================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: INT32 Compute TIOPs/s > Higher Is Better rtx 5090 ......... 61.76 |===================================================== NVIDIA 5090 ...... 61.76 |===================================================== GeForce RTX 5090 . 61.77 |===================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: INT16 Compute TIOPs/s > Higher Is Better rtx 5090 ......... 54.02 |===================================================== NVIDIA 5090 ...... 54.04 |===================================================== GeForce RTX 5090 . 53.95 |===================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: INT8 Compute TIOPs/s > Higher Is Better rtx 5090 ......... 41.80 |===================================================== NVIDIA 5090 ...... 41.72 |===================================================== GeForce RTX 5090 . 41.76 |===================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: Memory Bandwidth Coalesced Read GB/s > Higher Is Better rtx 5090 ......... 1596.24 |=================================================== NVIDIA 5090 ...... 1603.93 |=================================================== GeForce RTX 5090 . 1596.88 |=================================================== ProjectPhysX OpenCL-Benchmark 1.6 Operation: Memory Bandwidth Coalesced Write GB/s > Higher Is Better rtx 5090 ......... 1687.49 |=================================================== NVIDIA 5090 ...... 1679.44 |=================================================== GeForce RTX 5090 . 1680.23 |=================================================== RealSR-NCNN 20200818 Scale: 4x - TAA: No Seconds < Lower Is Better rtx 5090 ......... 4.630 |===================================================== NVIDIA 5090 ...... 4.400 |================================================== GeForce RTX 5090 . 4.446 |=================================================== RealSR-NCNN 20200818 Scale: 4x - TAA: Yes Seconds < Lower Is Better rtx 5090 ......... 13.48 |===================================================== NVIDIA 5090 ...... 13.50 |===================================================== GeForce RTX 5090 . 13.49 |===================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: S3D GFLOPS > Higher Is Better rtx 5090 ......... 1117.54 |=================================================== NVIDIA 5090 ...... 1120.51 |=================================================== GeForce RTX 5090 . 1120.88 |=================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Triad GB/s > Higher Is Better rtx 5090 ......... 27.83 |===================================================== NVIDIA 5090 ...... 27.81 |===================================================== GeForce RTX 5090 . 27.75 |===================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: FFT SP GFLOPS > Higher Is Better rtx 5090 ......... 4398.39 |=================================================== NVIDIA 5090 ...... 4400.85 |=================================================== GeForce RTX 5090 . 4375.95 |=================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash GHash/s > Higher Is Better rtx 5090 ......... 142.41 |==================================================== NVIDIA 5090 ...... 142.24 |==================================================== GeForce RTX 5090 . 142.53 |==================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Reduction GB/s > Higher Is Better rtx 5090 ......... 837.21 |==================================================== NVIDIA 5090 ...... 836.98 |==================================================== GeForce RTX 5090 . 837.24 |==================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: GEMM SGEMM_N GFLOPS > Higher Is Better rtx 5090 ......... 35937.2 |=================================================== NVIDIA 5090 ...... 36016.5 |=================================================== GeForce RTX 5090 . 35961.3 |=================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Max SP Flops GFLOPS > Higher Is Better rtx 5090 ......... 124615 |==================================================== NVIDIA 5090 ...... 124556 |==================================================== GeForce RTX 5090 . 124646 |==================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Download GB/s > Higher Is Better rtx 5090 ......... 28.79 |===================================================== NVIDIA 5090 ...... 28.79 |===================================================== GeForce RTX 5090 . 28.79 |===================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Bus Speed Readback GB/s > Higher Is Better rtx 5090 ......... 28.69 |===================================================== NVIDIA 5090 ...... 28.59 |===================================================== GeForce RTX 5090 . 28.14 |==================================================== SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Texture Read Bandwidth GB/s > Higher Is Better rtx 5090 ......... 2870.68 |=================================================== NVIDIA 5090 ...... 2872.53 |=================================================== GeForce RTX 5090 . 2875.50 |=================================================== VkFFT 1.3.4 Test: FFT + iFFT R2C / C2R Benchmark Score > Higher Is Better rtx 5090 ......... 164933 |==================================================== NVIDIA 5090 ...... 164801 |==================================================== GeForce RTX 5090 . 164873 |==================================================== VkFFT 1.3.4 Test: FFT + iFFT C2C 1D batched in half precision Benchmark Score > Higher Is Better rtx 5090 ......... 302221 |=================================================== NVIDIA 5090 ...... 305671 |==================================================== GeForce RTX 5090 . 300737 |=================================================== VkFFT 1.3.4 Test: FFT + iFFT C2C Bluestein in single precision Benchmark Score > Higher Is Better rtx 5090 ......... 36054 |===================================================== NVIDIA 5090 ...... 36026 |===================================================== GeForce RTX 5090 . 35954 |===================================================== VkFFT 1.3.4 Test: FFT + iFFT C2C 1D batched in double precision Benchmark Score > Higher Is Better rtx 5090 ......... 63738 |===================================================== NVIDIA 5090 ...... 62773 |==================================================== GeForce RTX 5090 . 63637 |===================================================== VkFFT 1.3.4 Test: FFT + iFFT C2C 1D batched in single precision Benchmark Score > Higher Is Better rtx 5090 ......... 237717 |==================================================== NVIDIA 5090 ...... 235884 |=================================================== GeForce RTX 5090 . 239575 |==================================================== VkFFT 1.3.4 Test: FFT + iFFT C2C multidimensional in single precision Benchmark Score > Higher Is Better rtx 5090 ......... 144624 |==================================================== NVIDIA 5090 ...... 144600 |==================================================== GeForce RTX 5090 . 144695 |==================================================== VkFFT 1.3.4 Test: FFT + iFFT C2C Bluestein benchmark in double precision Benchmark Score > Higher Is Better rtx 5090 ......... 9931 |====================================================== NVIDIA 5090 ...... 9940 |====================================================== GeForce RTX 5090 . 9934 |====================================================== VkFFT 1.3.4 Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling Benchmark Score > Higher Is Better rtx 5090 ......... 243937 |==================================================== NVIDIA 5090 ...... 243913 |==================================================== GeForce RTX 5090 . 241913 |==================================================== vkpeak 20240505 fp32-scalar GFLOPS > Higher Is Better rtx 5090 ......... 63013.32 |================================================== NVIDIA 5090 ...... 63035.62 |================================================== GeForce RTX 5090 . 63035.62 |================================================== vkpeak 20240505 fp32-vec4 GFLOPS > Higher Is Better rtx 5090 ......... 83296.84 |================================================== NVIDIA 5090 ...... 83290.22 |================================================== GeForce RTX 5090 . 83257.59 |================================================== vkpeak 20240505 fp16-scalar GFLOPS > Higher Is Better rtx 5090 ......... 62611.78 |================================================== NVIDIA 5090 ...... 62611.17 |================================================== GeForce RTX 5090 . 62597.51 |================================================== vkpeak 20240505 fp16-vec4 GFLOPS > Higher Is Better rtx 5090 ......... 72592.93 |================================================== NVIDIA 5090 ...... 72578.62 |================================================== GeForce RTX 5090 . 72575.33 |================================================== vkpeak 20240505 fp64-scalar GFLOPS > Higher Is Better rtx 5090 ......... 1967.37 |=================================================== NVIDIA 5090 ...... 1967.49 |=================================================== GeForce RTX 5090 . 1967.43 |=================================================== vkpeak 20240505 fp64-vec4 GFLOPS > Higher Is Better rtx 5090 ......... 1965.70 |=================================================== NVIDIA 5090 ...... 1965.39 |=================================================== GeForce RTX 5090 . 1965.32 |=================================================== vkpeak 20240505 int32-scalar GIOPS > Higher Is Better rtx 5090 ......... 62142.56 |================================================== NVIDIA 5090 ...... 62142.07 |================================================== GeForce RTX 5090 . 62141.02 |================================================== vkpeak 20240505 int32-vec4 GIOPS > Higher Is Better rtx 5090 ......... 61885.37 |================================================== NVIDIA 5090 ...... 61894.95 |================================================== GeForce RTX 5090 . 61914.51 |================================================== vkpeak 20240505 int16-scalar GIOPS > Higher Is Better rtx 5090 ......... 40006.60 |================================================== NVIDIA 5090 ...... 39989.70 |================================================== GeForce RTX 5090 . 39998.42 |================================================== vkpeak 20240505 int16-vec4 GIOPS > Higher Is Better rtx 5090 ......... 43806.13 |================================================== NVIDIA 5090 ...... 43799.96 |================================================== GeForce RTX 5090 . 43803.60 |================================================== VkResample 1.0 Upscale: 2x - Precision: Double ms < Lower Is Better rtx 5090 ......... 103.51 |==================================================== NVIDIA 5090 ...... 103.48 |==================================================== GeForce RTX 5090 . 103.45 |==================================================== VkResample 1.0 Upscale: 2x - Precision: Single ms < Lower Is Better rtx 5090 ......... 5.648 |===================================================== NVIDIA 5090 ...... 5.649 |===================================================== GeForce RTX 5090 . 5.648 |===================================================== Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: No Seconds < Lower Is Better Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: Yes Seconds < Lower Is Better rtx 5090 ......... 2.299 |===================================================== NVIDIA 5090 ...... 2.267 |==================================================== GeForce RTX 5090 . 2.278 |=====================================================