GeekRadar / The comparison desk
COMPARE.
GPU
HIS

HIS RX Vega 56 Air Black

Graphics processor

Video memory
8 GB*
Memory bus
2,048 bit*
Rated memory bandwidth
409.60 GB/s*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture
GCN 5.0*
Process node
14 nm*
GPU cores
3,584*
Graphics interface
PCIe 3.0 x16*
Reported chip die area
495 mm²*
Transistors
12,500 million*
GPU L2 cache
4 MB*
Graphics processor
Vega*
Texture mapping units
224*
Raster output units
64*
Chip foundry
GlobalFoundries*
Card or module format
Dual-slot*
Declared GPU TDP
210 W*
Suggested system PSU
550 W*
External power connectors
2x 8-pin*
DirectX / feature level
12 (12_1)*
OpenGL
4.6*
OpenCL
2.1*
Vulkan
1.3*
Shader model
6.7*

Memory & storage

Memory options
8*
Video memory
8 GB*
Video memory type
HBM2*
Memory bus
2,048 bit*
Rated memory bandwidth
409.60 GB/s*

Power specifications

Thermal design power
210 W*

System configuration

Detailed specifications

Specifications 1 · 26 fields
proc transistors
12,500 million*
proc die size
495* mm²
cores
3,584*
base clock
1,156*
boost clock
1,471*
memory clock
800*
ram
8*
name
HIS RX Vega 56 Air Black*
ram type
HBM2*
bus width
2,048*
bus interface
PCIe 3.0 x16*
ram bandwidth
409.6* GB/s
fp16 performance
21.09*
fp32 performance
10.54*
fp64 performance
0.659*
tdp
210* W
suggested psu
550* W
slot width
Dual-slot*
power connectors
2x 8-pin*
is retail board
Yes*
gpi value
8.65*
manufacturer
HIS*
arch name
GCN 5.0*
card release date
2017-08-14*
proc foundry
GlobalFoundries*
proc process size
14* nm
Specifications 2 · 36 fields
DirectX / feature level
12 (12_1)*
OpenCL
2.1*
OpenGL
4.6*
Shader model
6.7*
Vulkan
1.3*
Architecture
GCN 5.0*
Graphics interface
PCIe 3.0 x16*
Memory bus
2,048* bit
Reported shader processors
3,584*
Reported theoretical FP16 peak
21.09* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Reported theoretical FP32 peak
10.54* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Reported theoretical FP64 peak
0.659* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Declared L1 cache configuration
16 KB (per CU)*
Declared GPU L2 cache
4 MB*
Reported display outputs
1x HDMI 2.0b, 3x DisplayPort 1.4a*
Theoretical pixel fill rate
94.14 GPixel/s*
External power connectors
2x 8-pin*
Reported chip die area
495 mm²*
Chip foundry
GlobalFoundries*
Process node declaration
14 nm*
Transistors
12,500 million*
Graphics processor
Vega*
Reported video memory
8* GB
Rated memory bandwidth
409.6 GB/s*
Video memory type
HBM2*
Raster output units
64*
Reported shading units
3,584*
Card or module format
Dual-slot*
Suggested system PSU
550 W*
2:4 tensor sparsity
No*
Declared GPU TDP
210 W*
Theoretical texture fill rate
329.5 GTexel/s*
Texture mapping units
224*
GPU cores
3,584*
Video memory
8* GB
Video memory type
HBM2*

* Provisional data