NVIDIA Tesla V100S PCIe 32 GB vs NVIDIA Tesla V100 PCIe

Comparative analysis of NVIDIA Tesla V100S PCIe 32 GB and NVIDIA Tesla V100 PCIe videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory, Technologies. Benchmark videocards performance analysis: Geekbench - OpenCL.

NVIDIA Tesla V100S PCIe 32 GB

NVIDIA Tesla V100 PCIe

Differences

Reasons to consider the NVIDIA Tesla V100S PCIe 32 GB

Videocard is newer: launch date 2 year(s) 5 month(s) later
Around 16% higher boost clock speed: 1597 MHz vs 1380 MHz
1157.2x more texture fill rate: 511.0 GTexel/s vs 441.6 GTexel / s
2x more maximum memory size: 32 GB vs 16 GB

Launch date	26 Nov 2019 vs 21 June 2017
Boost clock speed	1597 MHz vs 1380 MHz
Texture fill rate	511.0 GTexel/s vs 441.6 GTexel / s
Maximum memory size	32 GB vs 16 GB

Reasons to consider the NVIDIA Tesla V100 PCIe

Around 59% higher memory clock speed: 1758 MHz vs 1106 MHz (2.2 Gbps effective)

Core clock speed	1246 MHz vs 1245 MHz
Memory clock speed	1758 MHz vs 1106 MHz (2.2 Gbps effective)

Compare benchmarks

GPU 1: NVIDIA Tesla V100S PCIe 32 GB
GPU 2: NVIDIA Tesla V100 PCIe

Name	NVIDIA Tesla V100S PCIe 32 GB	NVIDIA Tesla V100 PCIe
Geekbench - OpenCL	194461

Compare specifications (specs)

	NVIDIA Tesla V100S PCIe 32 GB	NVIDIA Tesla V100 PCIe
Essentials
Architecture	Volta	Volta
Code name	GV100	GV100
Launch date	26 Nov 2019	21 June 2017
Place in performance rating	34	not rated
Type	Workstation	Desktop
Technical info
Boost clock speed	1597 MHz	1380 MHz
Core clock speed	1245 MHz	1246 MHz
Manufacturing process technology	12 nm	12 nm
Peak Double Precision (FP64) Performance	8.177 TFLOPS (1:2)
Peak Half Precision (FP16) Performance	32.71 TFLOPS (2:1)
Peak Single Precision (FP32) Performance	16.35 TFLOPS
Pipelines	5120	5120
Pixel fill rate	204.4 GPixel/s
Texture fill rate	511.0 GTexel/s	441.6 GTexel / s
Thermal Design Power (TDP)	250 Watt	250 Watt
Transistor count	21100 million	21,100 million
Floating-point performance		14,131 gflops
Video outputs and ports
Display Connectors	No outputs	No outputs
Compatibility, dimensions and requirements
Form factor	Dual-slot
Interface	PCIe 3.0 x16	PCIe 3.0 x16
Recommended system power (PSU)	600 Watt
Supplementary power connectors	2x 8-pin	2x 8-pin
API support
DirectX	12.0 (12_1)
OpenCL	3.0
OpenGL	4.6
Shader Model	6.6
Vulkan
Memory
High bandwidth memory (HBM)
Maximum RAM amount	32 GB	16 GB
Memory bandwidth	1133 GB/s	900.1 GB / s
Memory bus width	4096 Bit	4096 Bit
Memory clock speed	1106 MHz (2.2 Gbps effective)	1758 MHz
Memory type	HBM2	HBM2
Technologies
CUDA