GeekRadar / The comparison desk
COMPARE.
GPU
INTEL

Intel Arctic Sound-M

Graphics processor

Video memory
16 GB*
Memory bus
4,096 bit*
Rated memory bandwidth
1,230 GB/s*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture
Generation 12.5*
Process node
10 nm*
GPU cores
8,192*
Graphics interface
PCIe 4.0 x16*
Reported chip die area
190 mm²*
Transistors
8,000 million*
GPU L2 cache
8 MB*
Graphics processor
Arctic*
Texture mapping units
256*
Raster output units
128*
Chip foundry
Intel*
Card or module format
Single-slot*
Declared GPU TDP
500 W*
Suggested system PSU
900 W*
External power connectors
8-pin EPS*
DirectX / feature level
12 (12_1)*
OpenGL
4.6*
OpenCL
3.0*
Shader model
6.6*

Memory & storage

Memory options
16*
Video memory
16 GB*
Video memory type
HBM2e*
Memory bus
4,096 bit*
Rated memory bandwidth
1,230 GB/s*

Power specifications

Thermal design power
500 W*

System configuration

Detailed specifications

Specifications 1 · 25 fields
proc transistors
8,000 million*
proc die size
190* mm²
cores
8,192*
memory clock
1,200*
ram
16*
name
Intel Arctic Sound-M*
ram type
HBM2e*
bus width
4,096*
bus interface
PCIe 4.0 x16*
ram bandwidth
1.23 TB/s*
fp16 performance
29.49*
fp32 performance
14.75*
fp64 performance
3.686*
tdp
500* W
suggested psu
900* W
slot width
Single-slot*
power connectors
8-pin EPS*
is retail board
No*
gpi value
15.42*
vendor
int*
manufacturer
INTEL*
arch name
Generation 12.5*
card release date
2022-03-12*
proc foundry
Intel*
proc process size
10* nm
Specifications 2 · 34 fields
DirectX / feature level
12 (12_1)*
OpenCL
3.0*
OpenGL
4.6*
Shader model
6.6*
Architecture
Generation 12.5*
Graphics interface
PCIe 4.0 x16*
Memory bus
4,096* bit
Reported shader processors
8,192*
Reported theoretical FP16 peak
29.49* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Reported theoretical FP32 peak
14.75* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Reported theoretical FP64 peak
3.686* TFLOPS
Scope and conditions
Arithmetic density
Not stated*
Declared GPU L2 cache
8 MB*
Reported display outputs
No outputs*
Theoretical pixel fill rate
115.2 GPixel/s*
External power connectors
8-pin EPS*
Reported chip die area
190 mm²*
Chip foundry
Intel*
Process node declaration
10 nm*
Transistors
8,000 million*
Graphics processor
Arctic*
Reported video memory
16* GB
Rated memory bandwidth
1.23 TB/s*
Video memory type
HBM2e*
Raster output units
128*
Reported shading units
8,192*
Card or module format
Single-slot*
Suggested system PSU
900 W*
2:4 tensor sparsity
No*
Declared GPU TDP
500 W*
Theoretical texture fill rate
230.4 GTexel/s*
Texture mapping units
256*
GPU cores
8,192*
Video memory
16* GB
Video memory type
HBM2e*

* Provisional data