A16 PCIe vs Radeon Instinct MI50

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	GCN 5.1 (2018−2022)	Ampere (2020−2025)
GPU code name	Vega 20	GA107
Market segment	Workstation	Workstation
Release date	18 November 2018 (7 years ago)	12 April 2021 (5 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. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.

Pipelines / CUDA cores	3840	2560 ×4
Core clock speed	1200 MHz	885 MHz
Boost clock speed	1746 MHz	1695 MHz
Number of transistors	13,230 million	17,400 million
Manufacturing process technology	7 nm	8 nm
Power consumption (TDP)	300 Watt	250 Watt
Texture fill rate	419.0	135.6 ×4
Floating-point processing power	13.41 TFLOPS	8.678 TFLOPS ×4
ROPs	64	48 ×4
TMUs	240	80 ×4
Tensor Cores	no data	80 ×4
Ray Tracing Cores	no data	20 ×4
L1 Cache	960 KB	2.5 MB
L2 Cache	4 MB	2 MB

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 4.0 x16	PCIe 4.0 x16
Length	267 mm	267 mm
Width	2-slot	2-slot
Supplementary power connectors	2x 8-pin	8-pin EPS

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	GDDR6
Maximum RAM amount	16 GB	16 GB ×4
Memory bus width	4096 Bit	128 Bit ×4
Memory clock speed	1000 MHz	1812 MHz
Memory bandwidth	1.02 TB/s	231.9 GB/s ×4
Resizable BAR	-	+

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

1x mini-DisplayPort 1.4a

No outputs

API and SDK support

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX	12 (12_1)	12 Ultimate (12_2)
Shader Model	6.7	6.6
OpenGL	4.6	4.6
OpenCL	2.1	3.0
Vulkan	1.3	1.2
CUDA	-	8.6
DLSS	-	+

Pros & cons summary

---

Recency	18 November 2018	12 April 2021
Chip lithography	7 nm	8 nm
Power consumption (TDP)	300 Watt	250 Watt