NVIDIA Tesla V100 DGXS vs NVIDIA Tesla V100 SXM2 32 GB

Comparative analysis of NVIDIA Tesla V100 DGXS and NVIDIA Tesla V100 SXM2 32 GB videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory. Benchmark videocards performance analysis: Geekbench - OpenCL, GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - T-Rex (Fps).

NVIDIA Tesla V100 DGXS

NVIDIA Tesla V100 SXM2 32 GB

Differences

Reasons to consider the NVIDIA Tesla V100 DGXS

Around 6% higher texture fill rate: 463.0 GTexel / s vs 438.4 GTexel / s
Around 6% better floating-point performance: 14,817 gflops vs 14,029 gflops

Texture fill rate	463.0 GTexel / s vs 438.4 GTexel / s
Floating-point performance	14,817 gflops vs 14,029 gflops

Reasons to consider the NVIDIA Tesla V100 SXM2 32 GB

Around 57% higher core clock speed: 1290 MHz vs 823 MHz
Around 67% higher boost clock speed: 1530 MHz vs 918 MHz

Core clock speed	1290 MHz vs 823 MHz
Boost clock speed	1530 MHz vs 918 MHz

Compare benchmarks

GPU 1: NVIDIA Tesla V100 DGXS
GPU 2: NVIDIA Tesla V100 SXM2 32 GB

Name	NVIDIA Tesla V100 DGXS	NVIDIA Tesla V100 SXM2 32 GB
Geekbench - OpenCL		131696
GFXBench 4.0 - Car Chase Offscreen (Frames)		19081
GFXBench 4.0 - Car Chase Offscreen (Fps)		19081
GFXBench 4.0 - Manhattan (Frames)		62
GFXBench 4.0 - Manhattan (Fps)		62
GFXBench 4.0 - T-Rex (Frames)		57
GFXBench 4.0 - T-Rex (Fps)		57

Compare specifications (specs)

	NVIDIA Tesla V100 DGXS	NVIDIA Tesla V100 SXM2 32 GB
Essentials
Architecture	Volta	Volta
Code name	GV100	GV100
Launch date	27 March 2018	27 March 2018
Place in performance rating	not rated	258
Type	Workstation	Workstation
Technical info
Boost clock speed	918 MHz	1530 MHz
Core clock speed	823 MHz	1290 MHz
Floating-point performance	14,817 gflops	14,029 gflops
Manufacturing process technology	12 nm	12 nm
Pipelines	5120	5120
Texture fill rate	463.0 GTexel / s	438.4 GTexel / s
Thermal Design Power (TDP)	250 Watt	250 Watt
Transistor count	21,100 million	21,100 million
Video outputs and ports
Display Connectors	No outputs	No outputs
Compatibility, dimensions and requirements
Interface	PCIe 3.0 x16	PCIe 3.0 x16
Supplementary power connectors	None	None
API support
DirectX	12.0 (12_1)	12.0 (12_1)
OpenGL	4.6	4.6
Memory
Maximum RAM amount	32 GB	32 GB
Memory bandwidth	897.0 GB / s	897.0 GB / s
Memory bus width	4096 Bit	4096 Bit
Memory clock speed	1752 MHz	1752 MHz
Memory type	HBM2	HBM2