GeekRadar / The comparison desk
COMPARE.
GPU
NVIDIA

Tesla P100 PCIe 16 GB

Graphics processor

Video memory
16 GB*
Memory bus
4,096 bit*
Rated memory bandwidth
732.20 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.

1080p ALU 2 OffscreenLinux / OpenGL / 1920 x 1080 / offscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

1,309.89* fps

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

1080p Driver Overhead 2 OffscreenLinux / OpenGL / 1920 x 1080 / offscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

108.28* fps

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

1080p Manhattan 3.1 OffscreenLinux / OpenGL / 1920 x 1080 / offscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

179.81* fps

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

1080p Manhattan OffscreenLinux / OpenGL / 1920 x 1080 / offscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

198.71* fps

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

1080p T-Rex OffscreenLinux / OpenGL / 1920 x 1080 / offscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

452.21* fps

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

1080p Texturing OffscreenLinux / OpenGL / 1920 x 1080 / offscreen · MTexels/s

Higher is better.

Tesla P100 PCIe 16 GB

194,505* MTexels/s

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

1440p Manhattan 3.1.1 OffscreenLinux / OpenGL / 2560 x 1440 / offscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

113.44* fps

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

Car Chase OffscreenLinux / OpenGL / 1920 x 1080 / offscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

130.52* fps

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

Tessellation OffscreenLinux / OpenGL / 1920 x 1080 / offscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

1,180.14* fps

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

ALU 2Linux / OpenGL / 1920 x 1080 / onscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

59.99* fps

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

Car ChaseLinux / OpenGL / 1920 x 1080 / onscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

56.03* fps

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

Driver Overhead 2Linux / OpenGL / 1920 x 1080 / onscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

49.57* fps

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

Manhattan 3.1Linux / OpenGL / 1920 x 1080 / onscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

59.38* fps

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

ManhattanLinux / OpenGL / 1920 x 1080 / onscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

58.48* fps

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

T-RexLinux / OpenGL / 1920 x 1080 / onscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

60.01* fps

NVIDIA Tesla P100 PCIe 16GB

Host configuration not reported.

TessellationLinux / OpenGL / 1920 x 1080 / onscreen · fps

Higher is better.

Tesla P100 PCIe 16 GB

60.02* fps

NVIDIA Tesla P100 PCIe 16GB

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.

Processing & platform

Architecture
Pascal*
Process node
16 nm*
GPU cores
3,584*
GPU base clock
1,190 MHz*
Reported GPU frequency
1,190 MHz*
Graphics interface
PCIe 3.0 x16*
Reported chip die area
610 mm²*
Chip/package TDP
250 W*
Transistors
15,300 million*
GPU boost clock
1,329 MHz*
GPU L2 cache
4 MB*
Graphics processor
GP100*
Texture mapping units
224*
Raster output units
96*
Streaming multiprocessors
56*
Chip foundry
TSMC*
Card or module format
Dual-slot*
Declared GPU TDP
250 W*
Suggested system PSU
600 W*
External power connectors
1x 8-pin*
DirectX / feature level
12 (12_1)*
OpenGL
4.6*
OpenCL
3.0*
Vulkan
1.3*
CUDA compute capability
6.0*
Shader model
6.0*

Memory & storage

Memory options
16*
Video memory
16 GB*
Video memory type
Reported value 1: HBM2*
Reported value 2: HBM2*
Reported value 3: HBM2*
Reported value 4: HBM2*
Reported value 5: GDDR6*
Reported value 6: HBM2*
Memory bus
4,096 bit*
Rated memory bandwidth
732.20 GB/s*

Power specifications

Thermal design power
250 W*

System configuration

Detailed specifications

Specifications 1 · 11 fields
Manufacturer
Nvidia*
GFLOPS
9,526* GFLOPS
TDP
250*
Class
Datacenter*
Name
Tesla P100 PCIe 16 GB*
Year
2016*
Fab
16*
Transistors (mln)
15,300*
Die size
610*
Memory size
16,384*
Memory speed
732.2*
Specifications 2 · 8 fields
Product Name
Tesla P100 PCIe 16 GB*
GPU Chip
GP100*
Released
Jun 20th, 2016*
Bus
PCIe 3.0 x16*
Memory
16 GB, HBM2, 4096 bit*
GPU clock
1,190* MHz
Memory clock
715* MHz
Shaders TMUs ROPs
3584 / 224 / 96*
Specifications 3 · 13 fields
Foundry
TSMC*
Vendor
NVIDIA*
FP16 GFLOPS
19,050* GFLOPS
FP32 GFLOPS
9,526* GFLOPS
FP64 GFLOPS
4,763* GFLOPS
Product
NVIDIA Tesla P100 PCIe 16 GB*
Type
GPU*
Release Date
2016-06-20*
Process Size (nm)
16* nm
TDP (W)
250* W
Die Size (mm^2)
610* mm²
Transistors (million)
15,300*
Freq (MHz)
1,190* MHz
Specifications 4 · 29 fields
proc transistors
15,300 million*
proc die size
610* mm²
cores
3,584*
sm count
56*
base clock
1,190*
boost clock
1,329*
memory clock
715*
ram
16*
name
NVIDIA Tesla P100 PCIe 16 GB*
ram type
HBM2*
bus width
4,096*
bus interface
PCIe 3.0 x16*
ram bandwidth
732.2* GB/s
fp16 performance
19.05*
fp32 performance
9.526*
fp64 performance
4.763*
tdp
250* W
suggested psu
600* W
slot width
Dual-slot*
power connectors
1x 8-pin*
api cuda
6*
is retail board
No*
gpi value
10.93*
vendor
nvd*
manufacturer
NVIDIA*
arch name
Pascal*
card release date
2016-06-20*
proc foundry
TSMC*
proc process size
16* nm
Specifications 5 · 38 fields
CUDA compute capability
6.0*
DirectX / feature level
12 (12_1)*
OpenCL
3.0*
OpenGL
4.6*
Shader model
6.0*
Vulkan
1.3*
Architecture
Pascal*
Graphics interface
PCIe 3.0 x16*
Memory bus
4,096* bit
Reported shader processors
3,584*
Reported theoretical FP16 peak
19.05* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Reported theoretical FP32 peak
9.526* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Reported theoretical FP64 peak
4.763* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Declared L1 cache configuration
24 KB (per SM)*
Declared GPU L2 cache
4 MB*
Reported display outputs
No outputs*
Theoretical pixel fill rate
127.6 GPixel/s*
External power connectors
1x 8-pin*
Reported chip die area
610 mm²*
Chip foundry
TSMC*
Process node declaration
16 nm*
Transistors
15,300 million*
Graphics processor
GP100*
Reported video memory
16* GB
Rated memory bandwidth
732.2 GB/s*
Video memory type
HBM2*
Raster output units
96*
Reported shading units
3,584*
Card or module format
Dual-slot*
Streaming multiprocessors
56*
Suggested system PSU
600 W*
2:4 tensor sparsity
No*
Declared GPU TDP
250 W*
Theoretical texture fill rate
297.7 GTexel/s*
Texture mapping units
224*
GPU cores
3,584*
Video memory
16* GB
Video memory type
HBM2*
Specifications 6 · 8 fields
Product Name
Tesla P100 PCIe 16 GB*
GPU Chip
GP100*
Released
Jun 20th, 2016*
Bus
PCIe 3.0 x16*
Memory
16 GB, HBM2, 4096 bit*
GPU clock
1,190* MHz
Memory clock
715* MHz
Shaders / TMUs / ROPs
3584 / 224 / 96*
Specifications 7 · 11 fields
Manufacturer
Nvidia*
GFLOPS
9,526* GFLOPS
TDP
250*
Class
Datacenter*
Name
Tesla P100 PCIe 16 GB*
Year
2016*
Fab
16*
Transistors (mln)
15,300*
Die size
610*
Memory size
16,384*
Memory speed
732.2*
Specifications 8 · 57 fields
Brand
NVIDIA*
Top BUS WIDTH
4,096* bit
Graphics Processor GPU Name
GP100*
Graphics Processor Architecture
Pascal*
Render Config SM Count
56*
Graphics Features CUDA
6*
Graphics Processor Process Size
16* nm
Graphics Processor Transistors
15,300 million*
Graphics Processor Die Size
610* mm²
Graphics Card Release Date
Jun 20th, 2016*
Graphics Card Generation
Tesla Pascal (Pxx)*
Graphics Card Successor
Tesla Volta*
Graphics Card Production
End-of-life*
Name
Tesla P100 PCIe 16 GB*
Graphics Card Bus Interface
PCIe 3.0 x16*
Clock Speeds Memory Clock
715 MHz 1430 Mbps effective*
Memory Memory Size
16* GB
Memory Memory Type
HBM2*
Memory Memory Bus
4,096* bit
Memory Bandwidth
732.2* GB/s
Render Config TMUs
224*
Top GRAPHICS PROCESSOR
GP100*
Render Config ROPs
96*
Theoretical Performance Pixel Rate
127.6 GPixel/s
Theoretical Performance Texture Rate
297.7 GTexel/s
Board Design Slot Width
Dual-slot*
Board Design TDP
250* W
Board Design Suggested PSU
600* W
Board Design Outputs
No outputs*
Board Design Board Number
PH400 SKU 201*
Graphics Features DirectX
12 (12_1)*
Graphics Features OpenGL
4.6*
Graphics Features OpenCL
3*
Graphics Features Vulkan
1.3*
source file
nvidia2016.json*
Graphics Processor Foundry
TSMC*
Graphics Card Predecessor
Tesla Maxwell*
Graphics Card Launch Price
5,699 USD*
Board Design Length
267 mm 10.5 inches*
Graphics Processor GPU Variant
GP100-893-A1*
Board Design Power Connectors
1x 8-pin*
Graphics Processor Density
25.1M / mm²*
Top TMUS
224*
Graphics Processor Chip Package
BGA-2621*
Top ROPS
96*
Clock Speeds Base Clock
1,190* MHz
Clock Speeds Boost Clock
1,329* MHz
Graphics Features Shader Model
6.0*
Top CORES
3,584*
Render Config Shading Units
3,584*
Render Config L2 Cache
4* MB
Top MEMORY SIZE
16* GB
Theoretical Performance FP32 (float)
9.526* TFLOPS
Theoretical Performance FP64 (double)
4.763 TFLOPS (1:2)
Render Config L1 Cache
24 KB (per SM)*
Theoretical Performance FP16 (half)
19.05 TFLOPS (2:1)
Top MEMORY TYPE
HBM2*
Specifications 9 · 27 fields
manufacturer
NVIDIA*
manufacturer
NVIDIA*
rop
96*
rop
96*
igp
No*
igp
No*
bus
PCIe 3.0 x16*
bus
PCIe 4.0 x16*
memType
HBM2*
memType
GDDR6*
gpuChip
Navi 32*
gpuChip
GP100*
productName
Tesla P100 PCIe 16 GB*
productName
Tesla P100 PCIe 16 GB*
releaseYear
2,016*
releaseYear
2,016*
memSize
16*
memSize
16*
memBusWidth
4,096*
gpuClock
1,190*
gpuClock
1,435*
memClock
2,250*
memClock
715*
unifiedShader
3,584*
unifiedShader
3,456*
tmu
224*
tmu
216*

* Provisional data