Radeon 550X 640SP vs Tesla V100 SMX2
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | not rated | not rated |
| Place by popularity | not in top-100 | not in top-100 |
| Architecture | Volta (2017−2020) | GCN 4.0 (2016−2020) |
| GPU code name | GV100 | Lexa |
| Market segment | Workstation | Desktop |
| Release date | 21 June 2017 (8 years ago) | 11 April 2018 (7 years ago) |
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 5120 | 640 |
| Core clock speed | 1370 MHz | 1019 MHz |
| Boost clock speed | no data | 1071 MHz |
| Number of transistors | 21,100 million | 2,200 million |
| Manufacturing process technology | 12 nm | 14 nm |
| Power consumption (TDP) | 250 Watt | 50 Watt |
| Texture fill rate | 438.4 | 42.84 |
| Floating-point processing power | no data | 1.371 TFLOPS |
| ROPs | 128 | 16 |
| TMUs | 320 | 40 |
| L1 Cache | no data | 160 KB |
| L2 Cache | no data | 256 KB |
Form factor & compatibility
Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).
| Interface | PCIe 3.0 x16 | PCIe 3.0 x8 |
| Width | 2-slot | IGP |
| Supplementary power connectors | None | None |
VRAM capacity and type
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.
| Memory type | HBM2 | GDDR5 |
| Maximum RAM amount | 16 GB | 4 GB |
| Memory bus width | 4096 Bit | 64 Bit |
| Memory clock speed | 1758 MHz | 1500 MHz |
| Memory bandwidth | 900.1 GB/s | 48 GB/s |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | no data | 1x DVI, 1x HDMI, 1x DisplayPort |
| HDMI | - | + |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12.0 | 12 (12_0) |
| Shader Model | 5.0 | 6.4 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 2.0 |
| Vulkan | - | 1.2.131 |
| CUDA | 7.0 | - |
Pros & cons summary
| Recency | 21 June 2017 | 11 April 2018 |
| Maximum RAM amount | 16 GB | 4 GB |
| Chip lithography | 12 nm | 14 nm |
| Power consumption (TDP) | 250 Watt | 50 Watt |
Tesla V100 SMX2 has a 300% higher maximum VRAM amount, and a 16.7% more advanced lithography process.
550X 640SP, on the other hand, has an age advantage of 9 months, and 400% lower power consumption.
We couldn't decide between Tesla V100 SMX2 and Radeon 550X 640SP. We've got no test results to judge.
Be aware that Tesla V100 SMX2 is a workstation graphics card while Radeon 550X 640SP is a desktop one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
