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
Tesla M2090
CORE STATE
GF110
VRAM
6 GB
CLOCK SPEED
—
TDP
250 W
BUS WIDTH
384 bit
ARCHITECTURE
Fermi 2.0
PROCESS
40 nm
LAUNCH DATE
2011
PERFORMANCE BENCHMARKS
geekbench_opencl
DETAILED SPECIFICATIONS
SPECIFICATION
Instinct MI100
Tesla M2090
Core Specs
Shading Units
7,680
512
-93.3%
Shaders
7,680
512
-93.3%
TMUs
480
64
-86.7%
ROPs
64
48
-25.0%
Compute Units
120
—
SM Count
—
16
Clocks
Base Clock
1000 MHz
—
Boost Clock
1502 MHz
—
GPU Clock
—
651 MHz
Shader Clock
—
1301 MHz
Memory Clock
1200 MHz 2.4 Gbps effective
924 MHz
3.7 Gbps effective
Memory
Memory Size
32 GB
6 GB
VRAM (MB)
32,768
6,144
-81.3%
Memory Type
HBM2
GDDR5
Memory Bus
4096 bit
384 bit
Bandwidth
1.23 TB/s
177.4 GB/s
Cache
L1 Cache
16 KB (per CU)
64 KB (per SM)
L2 Cache
8 MB
768 KB
Performance
Pixel Rate
96.13 GPixel/s
20.83 GPixel/s
Texture Rate
721.0 GTexel/s
41.66 GTexel/s
FP32 (TFLOPS)
23.07 TFLOPS
1,332.2 GFLOPS
FP64 (TFLOPS)
11.54 TFLOPS (1:2)
666.1 GFLOPS (1:2)
FP16 (TFLOPS)
46.14 TFLOPS (2:1)
—
Power
TDP
300 W
250 W
TDP (W)
300
250
-16.7%
Suggested PSU
700 W
600 W
Power Connectors
2x 8-pin
1x 6-pin + 1x 8-pin
Architecture
Architecture
CDNA 1.0
Fermi 2.0
GPU Name
Arcturus
GF110
Generation
Instinct (MIx)
Tesla Fermi
(x20xx)
Process Size
7 nm
40 nm
Transistors
25,600 million
3,000 million
Die Size
750 mm²
520 mm²
Foundry
TSMC
TSMC
Density
34.1M / mm²
5.8M / mm²
API Support
DirectX
—
12 (11_0)
OpenGL
—
4.6
OpenCL
2.1
1.1
CUDA
—
2.0
Shader Model
—
5.1
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm 10.5 inches
248 mm
9.8 inches
Height
111 mm 4.4 inches
—
Outputs
No outputs
No outputs
Bus Interface
PCIe 4.0 x16
PCIe 2.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
Radeon Instinct
Tesla
Successor
—
Tesla Kepler