GPU Comparison
RADEON
AMD Instinct MI100
CORE STATE
Arcturus
VRAM
32 GB
CLOCK SPEED
1502 MHz
TDP
300 W
BUS WIDTH
4096 bit
ARCHITECTURE
CDNA 1.0
PROCESS
7 nm
LAUNCH DATE
2020
VS
GEFORCE
A10G
CORE STATE
GA102
VRAM
24 GB
CLOCK SPEED
1710 MHz
TDP
150 W
BUS WIDTH
384 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2021
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Instinct MI100
A10G
Core Specs
Shading Units
7,680
9,216
+20.0%
Shaders
7,680
9,216
+20.0%
TMUs
480
288
-40.0%
ROPs
64
96
+50.0%
Compute Units
120
—
SM Count
—
72
Clocks
Base Clock
1000 MHz
1320 MHz
Boost Clock
1502 MHz
1710 MHz
Memory Clock
1200 MHz 2.4 Gbps effective
1563 MHz
12.5 Gbps effective
Memory
Memory Size
32 GB
24 GB
VRAM (MB)
32,768
24,576
-25.0%
Memory Type
HBM2
GDDR6
Memory Bus
4096 bit
384 bit
Bandwidth
1.23 TB/s
600.2 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
8 MB
6 MB
Performance
Pixel Rate
96.13 GPixel/s
164.2 GPixel/s
Texture Rate
721.0 GTexel/s
492.5 GTexel/s
FP32 (TFLOPS)
23.07 TFLOPS
31.52 TFLOPS
FP64 (TFLOPS)
11.54 TFLOPS (1:2)
985.0 GFLOPS (1:32)
FP16 (TFLOPS)
46.14 TFLOPS (2:1)
31.52 TFLOPS (1:1)
AI/RT
RT Cores
—
72
Tensor Cores
—
288
Power
TDP
300 W
150 W
TDP (W)
300
150
-50.0%
Suggested PSU
700 W
450 W
Power Connectors
2x 8-pin
8-pin EPS
Architecture
Architecture
CDNA 1.0
Ampere
GPU Name
Arcturus
GA102
Generation
Instinct (MIx)
Server Ampere
(Axx)
Process Size
7 nm
8 nm
Transistors
25,600 million
28,300 million
Die Size
750 mm²
628 mm²
Foundry
TSMC
Samsung
Density
34.1M / mm²
45.1M / mm²
API Support
DirectX
—
12 Ultimate (12_2)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
2.1
3.0
CUDA
—
8.6
Shader Model
—
6.8
Physical
Slot Width
Dual-slot
Single-slot
Length
267 mm 10.5 inches
267 mm
10.5 inches
Height
111 mm 4.4 inches
112 mm
4.4 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
Radeon Instinct
Tesla Turing
Successor
—
Server Ada