NVIDIA RTX 40 Series Compute

Benchmarks 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 2401305-NE-NVIDIACOM43
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

CPU Massive 2 Tests
Creator Workloads 4 Tests
Multi-Core 4 Tests
NVIDIA GPU Compute 4 Tests
Renderers 4 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
RTX 2060 SUPER
January 23
  1 Hour, 58 Minutes
RTX 2070
January 27
  2 Hours
RTX 2070 SUPER
January 23
  1 Hour, 45 Minutes
RTX 2080
January 24
  1 Hour, 39 Minutes
RTX 2080 SUPER
January 24
  1 Hour, 33 Minutes
TITAN RTX
January 26
  1 Hour, 19 Minutes
RTX 3060
January 22
  2 Hours, 9 Minutes
RTX 3060 Ti
January 21
  1 Hour, 38 Minutes
RTX 3070
January 20
  1 Hour, 33 Minutes
RTX 3070 Ti
January 21
  1 Hour, 26 Minutes
RTX 3080
January 22
  1 Hour, 13 Minutes
RTX 3080 Ti
January 21
  1 Hour, 10 Minutes
RTX 3090
January 24
  1 Hour, 6 Minutes
RTX 4060
January 20
  1 Hour, 56 Minutes
RTX 4070
January 27
  1 Hour, 22 Minutes
RTX 4070 SUPER
January 28
  1 Hour, 17 Minutes
RTX 4070 Ti SUPER
January 28
  1 Hour, 7 Minutes
RTX 4080
January 22
  1 Hour, 5 Minutes
RTX 4080 SUPER
January 29
  1 Hour, 1 Minute
RTX 4090
January 21
  53 Minutes
Invert Hiding All Results Option
  1 Hour, 28 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

NVIDIA RTX 40 Series Compute Suite 1.0.0 System Test suite extracted from NVIDIA RTX 40 Series Compute. pts/pytorch-1.0.1 cuda 512 resnet50 Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-50 pts/pytorch-1.0.1 cuda 512 resnet152 Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-152 pts/opencl-benchmark-1.0.0 Operation: Memory Bandwidth Coalesced Read pts/opencl-benchmark-1.0.0 Operation: Memory Bandwidth Coalesced Write pts/gpuowl-1.0.0 -iters 100000 -prp 57885161 Exponent: 57885161 pts/gpuowl-1.0.0 -iters 100000 -prp 77936867 Exponent: 77936867 pts/gpuowl-1.0.0 -iters 20000 -prp 332220523 Exponent: 332220523 pts/indigobench-1.1.0 --gpuonly --scenes supercar Acceleration: OpenCL GPU - Scene: Supercar pts/indigobench-1.1.0 --gpuonly --scenes bedroom Acceleration: OpenCL GPU - Scene: Bedroom pts/luxcorerender-1.4.0 DLSC/LuxCoreScene/render.cfg -D renderengine.type PATHOCL -D opencl.native.threads.count 0 -D context.cuda.optix.enable 0 Scene: DLSC - Acceleration: GPU pts/luxcorerender-1.4.0 RainbowColorsAndPrism/LuxCoreScene/render.cfg -D renderengine.type PATHOCL -D opencl.native.threads.count 0 -D context.cuda.optix.enable 0 Scene: Rainbow Colors and Prism - Acceleration: GPU pts/luxcorerender-1.4.0 LuxCore2.1Benchmark/LuxCoreScene/render.cfg -D renderengine.type PATHOCL -D opencl.native.threads.count 0 -D context.cuda.optix.enable 0 Scene: LuxCore Benchmark - Acceleration: GPU pts/luxcorerender-1.4.0 OrangeJuice/LuxCoreScene/render.cfg -D renderengine.type PATHOCL -D opencl.native.threads.count 0 -D context.cuda.optix.enable 0 Scene: Orange Juice - Acceleration: GPU pts/luxcorerender-1.4.0 DanishMood/LuxCoreScene/render.cfg -D renderengine.type PATHOCL -D opencl.native.threads.count 0 -D context.cuda.optix.enable 0 Scene: Danish Mood - Acceleration: GPU pts/fluidx3d-1.2.0 FP32-FP32 Test: FP32-FP32 pts/fluidx3d-1.2.0 FP32-FP16S Test: FP32-FP16S pts/fluidx3d-1.2.0 FP32-FP16C Test: FP32-FP16C pts/opencl-benchmark-1.0.0 Operation: FP64 Compute pts/opencl-benchmark-1.0.0 Operation: FP32 Compute pts/opencl-benchmark-1.0.0 Operation: INT64 Compute pts/opencl-benchmark-1.0.0 Operation: INT32 Compute pts/opencl-benchmark-1.0.0 Operation: INT16 Compute pts/opencl-benchmark-1.0.0 Operation: INT8 Compute pts/v-ray-1.4.0 -m vray-gpu-cuda Mode: NVIDIA CUDA GPU pts/v-ray-1.4.0 -m vray-gpu-rtx Mode: NVIDIA RTX GPU pts/blender-4.0.0 -b ../bmw27_gpu.blend -o output.test -x 1 -F JPEG -f 1 -- --cycles-device OPTIX Blend File: BMW27 - Compute: NVIDIA OptiX pts/blender-4.0.0 -b ../classroom_gpu.blend -o output.test -x 1 -F JPEG -f 1 -- --cycles-device OPTIX Blend File: Classroom - Compute: NVIDIA OptiX pts/blender-4.0.0 -b ../fishy_cat_gpu.blend -o output.test -x 1 -F JPEG -f 1 -- --cycles-device OPTIX Blend File: Fishy Cat - Compute: NVIDIA OptiX pts/blender-4.0.0 -b ../pavillon_barcelone_gpu.blend -o output.test -x 1 -F JPEG -f 1 -- --cycles-device OPTIX Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX pts/blender-4.0.0 -b ../barbershop_interior_gpu.blend -o output.test -x 1 -F JPEG -f 1 -- --cycles-device OPTIX Blend File: Barbershop - Compute: NVIDIA OptiX