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
GPU
Arc A350M
CORE STATE
DG2-128
VRAM
4 GB
CLOCK SPEED
2200 MHz
TDP
25 W
BUS WIDTH
64 bit
ARCHITECTURE
Xe-HPG
PROCESS
6 nm
LAUNCH DATE
2022
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Instinct MI100
A350M
Core Specs
Shading Units
7,680
768
-90.0%
Shaders
7,680
768
-90.0%
TMUs
480
48
-90.0%
ROPs
64
24
-62.5%
Compute Units
120
—
Execution Units
—
96
Clocks
Base Clock
1000 MHz
1150 MHz
Boost Clock
1502 MHz
2200 MHz
Memory Clock
1200 MHz 2.4 Gbps effective
1750 MHz
14 Gbps effective
Memory
Memory Size
32 GB
4 GB
VRAM (MB)
32,768
4,096
-87.5%
Memory Type
HBM2
GDDR6
Memory Bus
4096 bit
64 bit
Bandwidth
1.23 TB/s
112.0 GB/s
Cache
L1 Cache
16 KB (per CU)
—
L2 Cache
8 MB
4 MB
Performance
Pixel Rate
96.13 GPixel/s
52.80 GPixel/s
Texture Rate
721.0 GTexel/s
105.6 GTexel/s
FP32 (TFLOPS)
23.07 TFLOPS
3.379 TFLOPS
FP64 (TFLOPS)
11.54 TFLOPS (1:2)
844.8 GFLOPS (1:4)
FP16 (TFLOPS)
46.14 TFLOPS (2:1)
6.758 TFLOPS (2:1)
AI/RT
RT Cores
—
6
XMX Cores
—
96
Power
TDP
300 W
25 W
TDP (W)
300
25
-91.7%
Suggested PSU
700 W
—
Power Connectors
2x 8-pin
—
Architecture
Architecture
CDNA 1.0
Xe-HPG
GPU Name
Arcturus
DG2-128
Generation
Instinct (MIx)
Alchemist
(Arc 3 Mobile)
Process Size
7 nm
6 nm
Transistors
25,600 million
7,200 million
Die Size
750 mm²
157 mm²
Foundry
TSMC
TSMC
Density
34.1M / mm²
45.9M / mm²
API Support
DirectX
—
12 Ultimate (12_2)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
2.1
3.0
Shader Model
—
6.6
Physical
Slot Width
Dual-slot
IGP
Length
267 mm 10.5 inches
—
Height
111 mm 4.4 inches
—
Outputs
No outputs
Portable Device Dependent
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x8
Other
Production
End-of-life
End-of-life
Predecessor
Radeon Instinct
—