GPU Comparison
RADEON
AMD Radeon Instinct MI25
CORE STATE
Vega 10
VRAM
16 GB
CLOCK SPEED
1500 MHz
TDP
300 W
BUS WIDTH
2048 bit
ARCHITECTURE
GCN 5.0
PROCESS
14 nm
LAUNCH DATE
2017
VS
GEFORCE
CMP 90HX
CORE STATE
GA102
VRAM
10 GB
CLOCK SPEED
1710 MHz
TDP
320 W
BUS WIDTH
320 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2021
PERFORMANCE BENCHMARKS
geekbench_opencl
DETAILED SPECIFICATIONS
SPECIFICATION
Instinct MI25
CMP 90HX
Core Specs
Shading Units
4,096
6,400
+56.3%
Shaders
4,096
6,400
+56.3%
TMUs
256
200
-21.9%
ROPs
64
80
+25.0%
Compute Units
64
—
SM Count
—
50
Clocks
Base Clock
1400 MHz
1500 MHz
Boost Clock
1500 MHz
1710 MHz
Memory Clock
852 MHz
1704 Mbps effective
1188 MHz
19 Gbps effective
Memory
Memory Size
16 GB
10 GB
VRAM (MB)
16,384
10,240
-37.5%
Memory Type
HBM2
GDDR6X
Memory Bus
2048 bit
320 bit
Bandwidth
436.2 GB/s
760.3 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
4 MB
5 MB
Performance
Pixel Rate
96.00 GPixel/s
136.8 GPixel/s
Texture Rate
384.0 GTexel/s
342.0 GTexel/s
FP32 (TFLOPS)
12.29 TFLOPS
21.89 TFLOPS
FP64 (TFLOPS)
768.0 GFLOPS (1:16)
342.0 GFLOPS (1:64)
FP16 (TFLOPS)
24.58 TFLOPS (2:1)
21.89 TFLOPS (1:1)
AI/RT
RT Cores
—
50
Tensor Cores
—
200
Power
TDP
300 W
320 W
TDP (W)
300
320
+6.7%
Suggested PSU
700 W
700 W
Power Connectors
2x 8-pin
2x 8-pin
Architecture
Architecture
GCN 5.0
Ampere
GPU Name
Vega 10
GA102
Generation
Radeon Instinct
(MIx)
Mining GPUs
Process Size
14 nm
8 nm
Transistors
12,500 million
28,300 million
Die Size
495 mm²
628 mm²
Foundry
GlobalFoundries
Samsung
Density
25.3M / mm²
45.1M / mm²
API Support
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.3
1.4
OpenCL
2.1
3.0
CUDA
—
8.6
Shader Model
6.7
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm
10.5 inches
285 mm
11.2 inches
Height
111 mm
4.4 inches
112 mm
4.4 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 1.0 x4
Other
Production
End-of-life
End-of-life
Predecessor
FirePro Data Center
—