GeekRadar / The comparison desk
COMPARE.
GPU
NVIDIA

NVIDIA Jetson TX2

Graphics processor

Video memory
8 GB*
Memory bus
128 bit*
Rated memory bandwidth
59.71 GB/s*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture
Pascal*
Process node
16 nm*
GPU cores
256*
Graphics interface
PCIe 2.0 x4*
Graphics processor
GP10B*
Texture mapping units
16*
Raster output units
16*
Streaming multiprocessors
2*
Chip foundry
TSMC*
Card or module format
IGP*
Declared GPU TDP
15 W*
DirectX / feature level
12 (12_1)*
OpenGL
4.6*
OpenCL
1.2*
Vulkan
1.2*
CUDA compute capability
6.2*
Shader model
6.0*
GPU L2 cache
512 KB*

Memory & storage

Memory options
8*
Video memory
8 GB*
Video memory type
LPDDR4*
Memory bus
128 bit*
Rated memory bandwidth
59.71 GB/s*

Power specifications

Thermal design power
15 W*

System configuration

Detailed specifications

Specifications 1 · 23 fields
cores
256*
sm count
2*
memory clock
1,866*
ram
8*
name
NVIDIA Jetson TX2*
ram type
LPDDR4*
bus width
128*
bus interface
PCIe 2.0 x4*
ram bandwidth
59.71* GB/s
fp16 performance
1.3312*
fp32 performance
0.6656*
fp64 performance
0.0208*
tdp
15* W
slot width
IGP*
api cuda
6.2*
is retail board
No*
gpi value
0.98*
vendor
nvd*
manufacturer
NVIDIA*
arch name
Pascal*
card release date
2016-03-12*
proc foundry
TSMC*
proc process size
16* nm
Specifications 2 · 34 fields
CUDA compute capability
6.2*
DirectX / feature level
12 (12_1)*
OpenCL
1.2*
OpenGL
4.6*
Shader model
6.0*
Vulkan
1.2*
Architecture
Pascal*
Graphics interface
PCIe 2.0 x4*
Memory bus
128* bit
Reported shader processors
256*
Reported theoretical FP16 peak
1.3312* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Reported theoretical FP32 peak
0.6656* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Reported theoretical FP64 peak
0.0208* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Declared L1 cache configuration
48 KB (per SM)*
Declared GPU L2 cache
512 KB*
Reported display outputs
Portable Device Dependent*
Theoretical pixel fill rate
20.80 GPixel/s*
Chip foundry
TSMC*
Process node declaration
16 nm*
Graphics processor
GP10B*
Reported video memory
8* GB
Rated memory bandwidth
59.71 GB/s*
Video memory type
LPDDR4*
Raster output units
16*
Reported shading units
256*
Card or module format
IGP*
Streaming multiprocessors
2*
2:4 tensor sparsity
No*
Declared GPU TDP
15 W*
Theoretical texture fill rate
20.80 GTexel/s*
Texture mapping units
16*
GPU cores
256*
Video memory
8* GB
Video memory type
LPDDR4*

* Provisional data