GPU Comparison
RADEON
AMD Radeon Instinct MI60
CORE STATE
Vega 20
VRAM
32 GB
CLOCK SPEED
1800 MHz
TDP
300 W
BUS WIDTH
4096 bit
ARCHITECTURE
GCN 5.1
PROCESS
7 nm
LAUNCH DATE
2018
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
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Instinct MI60
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
1200 MHz
1500 MHz
Boost Clock
1800 MHz
1710 MHz
Memory Clock
1000 MHz
2 Gbps effective
1188 MHz
19 Gbps effective
Memory
Memory Size
32 GB
10 GB
VRAM (MB)
32,768
10,240
-68.8%
Memory Type
HBM2
GDDR6X
Memory Bus
4096 bit
320 bit
Bandwidth
1.02 TB/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
115.2 GPixel/s
136.8 GPixel/s
Texture Rate
460.8 GTexel/s
342.0 GTexel/s
FP32 (TFLOPS)
14.75 TFLOPS
21.89 TFLOPS
FP64 (TFLOPS)
7.373 TFLOPS (1:2)
342.0 GFLOPS (1:64)
FP16 (TFLOPS)
29.49 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
1x 6-pin + 1x 8-pin
2x 8-pin
Architecture
Architecture
GCN 5.1
Ampere
GPU Name
Vega 20
GA102
Generation
Radeon Instinct
(MIx)
Mining GPUs
Process Size
7 nm
8 nm
Transistors
13,230 million
28,300 million
Die Size
331 mm²
628 mm²
Foundry
TSMC
Samsung
Density
40.0M / 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
1x mini-DisplayPort 1.4a
No outputs
Bus Interface
PCIe 4.0 x16
PCIe 1.0 x4
Other
Production
End-of-life
End-of-life
Predecessor
FirePro Data Center
—