AMD Radeon Pro Vega 48
- Graphics Processor
- Vega 10
- Cores
- 3072
- TMUs
- 192
- ROPs
- 64
- Memory Size
- 8 GB
- Memory Type
- HBM2
- Bus Width
- 2048 bit
Recommended Resolutions:
- 640x480
- 1280x720
- 1366x768
- 1600x900
- 1920x1080
- 2560x1440
- 3840x2160
The Radeon Pro Vega 48 is a professional graphics card by AMD, launched in March 2019. Built on the 14 nm process, and based on the Vega 10 graphics processor, in its Vega 10 PRO variant, the card supports DirectX 12.0. The Vega 10 graphics processor is a large chip with a die area of 495 mm² and 12,500 million transistors. Unlike the fully unlocked Radeon RX Vega 64, which uses the same GPU but has all 4096 shaders enabled, AMD has disabled some shading units on the Radeon Pro Vega 48 to reach the product's target shader count. It features 3072 shading units, 192 texture mapping units and 64 ROPs. AMD has placed 8,192 MB HBM2 memory on the card, which are connected using a 2048-bit memory interface. The GPU is operating at a frequency of 1200 MHz, which can be boosted up to 1300 MHz, memory is running at 786 MHz.
Being a igp card, the AMD Radeon Pro Vega 48 does not require any additional power connector, its power draw is not exactly known. This device has no display connectivity, as it is not designed to have monitors connected to it. Radeon Pro Vega 48 is connected to the rest of the system using a PCI-Express 3.0 x16 interface.
Being a igp card, the AMD Radeon Pro Vega 48 does not require any additional power connector, its power draw is not exactly known. This device has no display connectivity, as it is not designed to have monitors connected to it. Radeon Pro Vega 48 is connected to the rest of the system using a PCI-Express 3.0 x16 interface.
Graphics Processor
- GPU Name
- Vega 10
- GPU Variant
- Vega 10 PRO
- Architecture
- GCN 5.0
- Foundry
- GlobalFoundries
- Process Size
- 14 nm
- Transistors
- 12,500 million
- Die Size
- 495 mm²
Mobile Graphics
- Release Date
- Mar 19th, 2019
- Generation
-
Radeon Pro
(Pro Vega)
- Production
- Active
- Bus Interface
- PCIe 3.0 x16
Relative Performance
Based on TPU review data: "Performance Summary" at 1920x1080
Performance estimated based on architecture, shader count and clocks.
Clock Speeds
- Base Clock
- 1200 MHz
- Boost Clock
- 1300 MHz
- Memory Clock
-
786 MHz
1572 MHz effective
Memory
- Memory Size
- 8 GB
- Memory Type
- HBM2
- Memory Bus
- 2048 bit
- Bandwidth
- 402.4 GB/s
Render Config
- Shading Units
- 3072
- TMUs
- 192
- ROPs
- 64
- Compute Units
- 48
- L1 Cache
- 16 KB (per CU)
- L2 Cache
- 4 MB
Theoretical Performance
- Pixel Rate
- 83.20 GPixel/s
- Texture Rate
- 249.6 GTexel/s
- FP16 (half) performance
- 15.97 TFLOPS (2:1)
- FP32 (float) performance
- 7.987 TFLOPS
- FP64 (double) performance
- 499.2 GFLOPS (1:16)
Board Design
- Slot Width
- IGP
- TDP
- unknown
- Outputs
- No outputs
- Power Connectors
- None
Graphics Features
- DirectX
- 12.0 (12_1)
- OpenGL
- 4.6
- OpenCL
- 2.0
- Vulkan
- 1.1.119
- Shader Model
- 6.4
Card Notes
| specs unknown |
Vega 10 GPU Notes
| Architecture Codename: Vega Codename: Greenland CLRX Version: GCN 1.4 Graphics/Compute: GFX9 (gfx900) / (gfx901) Display Core Engine: 12.0 Unified Video Decoder: 7.0 Video Compression Engine: 4.0 |