GPU Comparison
RADEON
AMD Radeon 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
GeForce RTX 3070 Max-Q
CORE STATE
GA104
VRAM
8 GB
CLOCK SPEED
1290 MHz
TDP
80 W
BUS WIDTH
256 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2021
DETAILED SPECIFICATIONS
SPECIFICATION
Instinct MI100
RTX 3070 Max-Q
Core Specs
Shading Units
7,680
5,120
-33.3%
Shaders
7,680
5,120
-33.3%
TMUs
480
160
-66.7%
ROPs
64
80
+25.0%
Compute Units
120
—
SM Count
—
40
Clocks
Base Clock
1000 MHz
780 MHz
Boost Clock
1502 MHz
1290 MHz
Memory Clock
1200 MHz
2.4 Gbps effective
1500 MHz
12 Gbps effective
Memory
Memory Size
32 GB
8 GB
VRAM (MB)
32,768
8,192
-75.0%
Memory Type
HBM2
GDDR6
Memory Bus
4096 bit
256 bit
Bandwidth
1.23 TB/s
384.0 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
8 MB
4 MB
Performance
Pixel Rate
96.13 GPixel/s
103.2 GPixel/s
Texture Rate
721.0 GTexel/s
206.4 GTexel/s
FP32 (TFLOPS)
23.07 TFLOPS
13.21 TFLOPS
FP64 (TFLOPS)
11.54 TFLOPS (1:2)
206.4 GFLOPS (1:64)
FP16 (TFLOPS)
184.6 TFLOPS (8:1)
13.21 TFLOPS (1:1)
AI/RT
RT Cores
—
40
Tensor Cores
—
160
Power
TDP
300 W
80 W
TDP (W)
300
80
-73.3%
Suggested PSU
700 W
—
Power Connectors
2x 8-pin
None
Architecture
Architecture
CDNA 1.0
Ampere
GPU Name
Arcturus
GA104
Generation
Radeon Instinct
(MIx)
GeForce 30 Mobile
Process Size
7 nm
8 nm
Transistors
25,600 million
17,400 million
Die Size
750 mm²
392 mm²
Foundry
TSMC
Samsung
Density
34.1M / mm²
44.4M / 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
—
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 x16
Other
Production
End-of-life
End-of-life
Predecessor
FirePro Data Center
GeForce 20 Mobile