GeekRadar / The comparison desk

COMPARE.

GPU

Nvidia

Tesla K20c

Graphics processor

Video memory: 5 GB^*
Memory bus: 320 bit^*
Rated memory bandwidth: 208 GB/s^*

Graphics & compute benchmarks

Archived cohort medians

GFXBench, GLBenchmark and CompuBench results retain the tested system, API, operating system and resolution. Offscreen tests fix the render resolution; onscreen results also reflect the display workload. These historical submissions do not establish performance in current games.

Catmull-Clark Subdivision Level 3Windows / OpenCL / compute · mTriangles/s

Higher is better.

Tesla K20c

98.02^* mTriangles/s

NVIDIA Tesla K20c

Host configuration not reported.

Catmull-Clark Subdivision Level 3Windows / cu / compute · mTriangles/s

Higher is better.

Tesla K20c

96.08^* mTriangles/s

NVIDIA Tesla K20c

Host configuration not reported.

Catmull-Clark Subdivision Level 5Windows / OpenCL / compute · mTriangles/s

Higher is better.

Tesla K20c

130.67^* mTriangles/s

NVIDIA Tesla K20c

Host configuration not reported.

Catmull-Clark Subdivision Level 5Windows / cu / compute · mTriangles/s

Higher is better.

Tesla K20c

131.71^* mTriangles/s

NVIDIA Tesla K20c

Host configuration not reported.

Level Set Segmentation – 128Windows / OpenCL / compute · mVoxels/s

Higher is better.

Tesla K20c

4,900.25^* mVoxels/s

NVIDIA Tesla K20c

Host configuration not reported.

Level Set Segmentation – 256Windows / OpenCL / compute · mVoxels/s

Higher is better.

Tesla K20c

5,048.19^* mVoxels/s

NVIDIA Tesla K20c

Host configuration not reported.

Level Set Segmentation – 256Windows / cu / compute · mVoxels/s

Higher is better.

Tesla K20c

2,288.86^* mVoxels/s

NVIDIA Tesla K20c

Host configuration not reported.

N-Body simulation – 1024kWindows / OpenCL / compute · Iterations/s

Higher is better.

Tesla K20c

20.87^* Iterations/s

NVIDIA Tesla K20c

Host configuration not reported.

N-Body simulation – 1024kWindows / cu / compute · Iterations/s

Higher is better.

Tesla K20c

22.35^* Iterations/s

NVIDIA Tesla K20c

Host configuration not reported.

N-Body simulation – 128kWindows / OpenCL / compute · Iterations/s

Higher is better.

Tesla K20c

138.79^* Iterations/s

NVIDIA Tesla K20c

Host configuration not reported.

N-Body simulation – 128kWindows / cu / compute · Iterations/s

Higher is better.

Tesla K20c

144.97^* Iterations/s

NVIDIA Tesla K20c

Host configuration not reported.

Ocean Surface SimulationWindows / OpenCL / compute · Iterations/s

Higher is better.

Tesla K20c

1,379.25^* Iterations/s

NVIDIA Tesla K20c

Host configuration not reported.

Ocean Surface SimulationWindows / cu / compute · Iterations/s

Higher is better.

Tesla K20c

1,355.08^* Iterations/s

NVIDIA Tesla K20c

Host configuration not reported.

Subsurface Scattering multiple viewWindows / OpenCL / compute · mSample/s

Higher is better.

Tesla K20c

1,914.45^* mSample/s

NVIDIA Tesla K20c

Host configuration not reported.

Subsurface Scattering multiple viewWindows / cu / compute · mSample/s

Higher is better.

Tesla K20c

2,015.25^* mSample/s

NVIDIA Tesla K20c

Host configuration not reported.

Subsurface ScatteringWindows / OpenCL / compute · mSample/s

Higher is better.

Tesla K20c

2,023.84^* mSample/s

NVIDIA Tesla K20c

Host configuration not reported.

Median results, not the best run. Sample counts and individual test dates are unreported. Different systems using the same GPU remain separate configurations.

Benchmark results

Geekbench GPU (reported compilation) · version unreported · CUDA11,850^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · CUDA11,850^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · OpenCL14,766^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · OpenCL14,766^*Platform unreported Compare results

Processing & platform

Architecture: Kepler^*
Process node: 28 nm^*
GPU cores: 2,496^*
GPU base clock: 706 MHz^*
Reported GPU frequency: 706 MHz^*
Graphics interface: PCIe 2.0 x16^*
Reported chip die area: 561 mm²^*
Chip/package TDP: 225 W^*
Transistors: 7,080 million^*
Graphics processor: GK110^*
Texture mapping units: 208^*
Raster output units: 40^*
Chip foundry: TSMC^*
Card or module format: Dual-slot^*
Declared GPU TDP: 225 W^*
Suggested system PSU: 550 W^*
External power connectors: 1x 6-pin + 1x 8-pin^*
DirectX / feature level: 12 (11_0)^*
OpenGL: 4.6^*
OpenCL: 3.0^*
Vulkan: 1.2.175^*
CUDA compute capability: 3.5^*
Shader model: 6.5 (5.1)^*
GPU L2 cache: 1,280 KB^*

Memory & storage

Memory options: 5^*
Video memory: 5 GB^*
Video memory type: GDDR5^*
Memory bus: 320 bit^*
Rated memory bandwidth: 208 GB/s^*

Power specifications

Thermal design power: 225 W^*

System configuration

Detailed specifications

Specifications 1 · 11 fields

Manufacturer: Nvidia^*
GFLOPS: 3,524^* GFLOPS
TDP: 225^*
Class: Datacenter^*
Name: Tesla K20c^*
Year: 2012^*
Fab: 28^*
Transistors (mln): 7,080^*
Die size: 561^*
Memory size: 5,120^*
Memory speed: 208^*

Specifications 2 · 8 fields

Product Name: Tesla K20c^*
GPU Chip: GK110^*
Released: Nov 12th, 2012^*
Bus: PCIe 2.0 x16^*
Memory: 5 GB, GDDR5, 320 bit^*
GPU clock: 706^* MHz
Memory clock: 1,300^* MHz
Shaders TMUs ROPs: 2496 / 208 / 40^*

Specifications 3 · 12 fields

Foundry: TSMC^*
Vendor: NVIDIA^*
FP32 GFLOPS: 3,524^* GFLOPS
FP64 GFLOPS: 1,175^* GFLOPS
Product: NVIDIA Tesla K20c^*
Type: GPU^*
Release Date: 2012-11-12^*
Process Size (nm): 28^* nm
TDP (W): 225^* W
Die Size (mm^2): 561^* mm²
Transistors (million): 7,080^*
Freq (MHz): 706^* MHz

Specifications 4 · 25 fields

proc transistors: 7,080 million^*
proc die size: 561^* mm²
cores: 2,496^*
memory clock: 1,300^*
ram: 5^*
name: NVIDIA Tesla K20c^*
ram type: GDDR5^*
bus width: 320^*
bus interface: PCIe 2.0 x16^*
ram bandwidth: 208^* GB/s
fp32 performance: 3.524^*
fp64 performance: 1.1748^*
tdp: 225^* W
suggested psu: 550^* W
slot width: Dual-slot^*
power connectors: 1x 6-pin + 1x 8-pin^*
api cuda: 3.5^*
is retail board: No^*
gpi value: 3.2^*
vendor: nvd^*
manufacturer: NVIDIA^*
arch name: Kepler^*
card release date: 2012-11-12^*
proc foundry: TSMC^*
proc process size: 28^* nm

Specifications 5 · 36 fields

CUDA compute capability

3.5^*

DirectX / feature level

12 (11_0)^*

OpenCL

3.0^*

OpenGL

4.6^*

Shader model

6.5 (5.1)^*

Vulkan

1.2.175^*

Architecture

Kepler^*

Graphics interface

PCIe 2.0 x16^*

Memory bus

320^* bit

Reported shader processors

2,496^*

Reported theoretical FP32 peak

3.524^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

1.1748^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

16 KB (per SMX)^*

Declared GPU L2 cache

1280 KB^*

Reported display outputs

No outputs^*

Theoretical pixel fill rate

36.71 GPixel/s^*

External power connectors

1x 6-pin + 1x 8-pin^*

Reported chip die area

561 mm²^*

Chip foundry

TSMC^*

Process node declaration

28 nm^*

Transistors

7,080 million^*

Graphics processor

GK110^*

Reported video memory

5^* GB

Rated memory bandwidth

208.0 GB/s^*

Video memory type

GDDR5^*

Raster output units

40^*

Reported shading units

2,496^*

Card or module format

Dual-slot^*

Suggested system PSU

550 W^*

2:4 tensor sparsity

No^*

Declared GPU TDP

225 W^*

Theoretical texture fill rate

146.8 GTexel/s^*

Texture mapping units

208^*

GPU cores

2,496^*

Video memory

5^* GB

Video memory type

GDDR5^*

Specifications 6 · 8 fields

Product Name: Tesla K20c^*
GPU Chip: GK110^*
Released: Nov 12th, 2012^*
Bus: PCIe 2.0 x16^*
Memory: 5 GB, GDDR5, 320 bit^*
GPU clock: 706^* MHz
Memory clock: 1,300^* MHz
Shaders / TMUs / ROPs: 2496 / 208 / 40^*

Specifications 7 · 11 fields

Manufacturer: Nvidia^*
GFLOPS: 3,524^* GFLOPS
TDP: 225^*
Class: Datacenter^*
Name: Tesla K20c^*
Year: 2012^*
Fab: 28^*
Transistors (mln): 7,080^*
Die size: 561^*
Memory size: 5,120^*
Memory speed: 208^*

Specifications 8 · 55 fields

Brand: NVIDIA^*
Top BUS WIDTH: 320^* bit
Graphics Processor GPU Name: GK110^*
Graphics Processor Architecture: Kepler^*
Graphics Features CUDA: 3.5^*
Render Config SMX Count: 13^*
Graphics Processor Process Size: 28^* nm
Graphics Processor Transistors: 7,080 million^*
Graphics Processor Die Size: 561^* mm²
Graphics Card Release Date: Nov 12th, 2012^*
Graphics Card Generation: Tesla Kepler (Kxx)^*
Graphics Card Successor: Tesla Maxwell^*
Graphics Card Production: End-of-life^*
Name: Tesla K20c^*
Graphics Card Bus Interface: PCIe 2.0 x16^*
Clock Speeds GPU Clock: 706^* MHz
Clock Speeds Memory Clock: 1300 MHz 5.2 Gbps effective^*
Memory Memory Size: 5^* GB
Memory Memory Type: GDDR5^*
Memory Memory Bus: 320^* bit
Memory Bandwidth: 208^* GB/s
Render Config TMUs: 208^*
Top GRAPHICS PROCESSOR: GK110^*
Render Config ROPs: 40^*
Theoretical Performance Pixel Rate: 36.71 GPixel/s
Theoretical Performance Texture Rate: 146.8 GTexel/s
Board Design Slot Width: Dual-slot^*
Board Design TDP: 225^* W
Board Design Suggested PSU: 550^* W
Board Design Outputs: No outputs^*
Board Design Board Number: P2081 SKU 204^*
Graphics Features DirectX: 12 (11_0)^*
Graphics Features OpenGL: 4.6^*
Graphics Features OpenCL: 3^*
Graphics Features Vulkan: 1.2.175^*
source file: nvidia2012.json^*
Graphics Processor Foundry: TSMC^*
Graphics Card Predecessor: Tesla Fermi^*
Graphics Card Launch Price: 3,199 USD^*
Board Design Length: 267 mm 10.5 inches^*
Graphics Processor GPU Variant: GK110-885-KA-A1^*
Board Design Power Connectors: 1x 6-pin + 1x 8-pin^*
Graphics Processor Density: 12.6M / mm²^*
Top TMUS: 208^*
Graphics Processor Chip Package: BGA-2152^*
Top ROPS: 40^*
Graphics Features Shader Model: 6.5 (5.1)^*
Top CORES: 2,496^*
Render Config Shading Units: 2,496^*
Render Config L2 Cache: 1,280^* KB
Top MEMORY SIZE: 5^* GB
Theoretical Performance FP32 (float): 3.524^* TFLOPS
Theoretical Performance FP64 (double): 1,174.8 GFLOPS (1:3)
Render Config L1 Cache: 16 KB (per SMX)^*
Top MEMORY TYPE: GDDR5^*

Specifications 9 · 4 fields

Manufacturer

Nvidia^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

Device

Tesla K20c^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

CUDA

11,850^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

OpenCL

14,766^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

Specifications 10 · 4 fields

Manufacturer

Nvidia^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

Device

Tesla K20c^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

CUDA

11,850^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

OpenCL

14,766^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

Specifications 11 · 27 fields

manufacturer: NVIDIA^*
manufacturer: NVIDIA^*
rop: 32^*
rop: 40^*
igp: No^*
igp: No^*
bus: PCIe 2.0 x16^*
bus: PCIe 3.0 x16^*
memType: GDDR5^*
memType: GDDR5^*
gpuChip: Tahiti^*
gpuChip: GK110^*
productName: Tesla K20c^*
productName: Tesla K20c^*
releaseYear: 2,012^*
releaseYear: 2,012^*
memSize: 5^*
memSize: 5^*
memBusWidth: 320^*
gpuClock: 925^*
gpuClock: 706^*
memClock: 1,375^*
memClock: 1,300^*
unifiedShader: 2,496^*
unifiedShader: 2,048^*
tmu: 128^*
tmu: 208^*

* Provisional data