Performance to price ratio. The higher, the better.
NVIDIA Tesla PG503-216 vs AMD Radeon Pro Vega II Duo
- Interface PCIe 3.0 x16
- Core clock speed 1400 MHz
- Max video memory 32 GB
- Memory type HBM2
- Memory clock speed 2 Gbps
- Maximum resolution
- Interface PCIe 3.0 x16
- Core clock speed
- Max video memory 32 GB
- Memory type HBM2
- Memory clock speed 2.2 Gbps
- Maximum resolution
General info
GPU architecture, market segment, value for money and other general parameters compared.
Place in performance ranking | 66 | not rated |
Value for money | 2.21 | no data |
Architecture | GCN 5.1 (2018−2021) | Volta (2017−2020) |
GPU code name | Vega 20 | GV100 |
Market segment | Workstation | Workstation |
Release date | 3 June 2019 (4 years old) | 26 November 2019 (3 years old) |
Launch price (MSRP) | $4,399 | no data |
Current price | $5226 (1.2x MSRP) | no data |
Technical specs
General performance parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. These parameters indirectly speak of performance, but for precise assessment you have to consider their benchmark and gaming test results. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
Pipelines / CUDA cores | 4096 | 5120 |
Core clock speed | 1400 MHz | no data |
Boost clock speed | 1720 MHz | 1530 MHz |
Number of transistors | 13,230 million | 21,100 million |
Manufacturing process technology | 7 nm | 12 nm |
Power consumption (TDP) | 475 Watt | 250 Watt |
Texture fill rate | 440.3 | 489.6 |
Size and 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 x16 |
Width | Quad-slot | 2-slot |
Supplementary power connectors | None | None |
Memory
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated VRAM and use a shared part of system RAM.
Memory type | HBM2 | HBM2 |
Maximum RAM amount | 32 GB | 32 GB |
Memory bus width | 4096 Bit | 4096 Bit |
Memory clock speed | 2 GB/s | 2.2 GB/s |
Memory bandwidth | 1,024 GB/s | 1,133 GB/s |
Video outputs and ports
Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.
Display Connectors | 1x HDMI 2.0b, 4x Thunderbolt | No outputs |
HDMI | + | no data |
API support
List of supported graphics and general-purpose computing APIs, including their specific versions.
DirectX | 12 (12_1) | 12 (12_1) |
Shader Model | 6.7 (6.4) | 6.4 |
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 1.2 |
Vulkan | 1.3 | 1.2 |
CUDA | no data | 7.0 |
Advantages and disadvantages
Recency | 3 June 2019 | 26 November 2019 |
Pipelines / CUDA cores | 4096 | 5120 |
Chip lithography | 7 nm | 12 nm |
Power consumption (TDP) | 475 Watt | 250 Watt |
We couldn't decide between Radeon Pro Vega II Duo and Tesla PG503-216. We've got no test results to judge.
Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.
Similar GPU comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.