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 M40
CORE STATE
GM200
VRAM
12 GB
CLOCK SPEED
1112 MHz
TDP
250 W
BUS WIDTH
384 bit
ARCHITECTURE
Maxwell 2.0
PROCESS
28 nm
LAUNCH DATE
2015
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Instinct MI100
Tesla M40
Core Specs
Shading Units
7,680
3,072
-60.0%
Shaders
7,680
3,072
-60.0%
TMUs
480
192
-60.0%
ROPs
64
96
+50.0%
Compute Units
120
—
Clocks
Base Clock
1000 MHz
948 MHz
Boost Clock
1502 MHz
1112 MHz
Memory Clock
1200 MHz 2.4 Gbps effective
1502 MHz
6 Gbps effective
Memory
Memory Size
32 GB
12 GB
VRAM (MB)
32,768
12,288
-62.5%
Memory Type
HBM2
GDDR5
Memory Bus
4096 bit
384 bit
Bandwidth
1.23 TB/s
288.4 GB/s
Cache
L1 Cache
16 KB (per CU)
48 KB (per SMM)
L2 Cache
8 MB
3 MB
Performance
Pixel Rate
96.13 GPixel/s
106.8 GPixel/s
Texture Rate
721.0 GTexel/s
213.5 GTexel/s
FP32 (TFLOPS)
23.07 TFLOPS
6.832 TFLOPS
FP64 (TFLOPS)
11.54 TFLOPS (1:2)
213.5 GFLOPS (1:32)
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
8-pin EPS
Architecture
Architecture
CDNA 1.0
Maxwell 2.0
GPU Name
Arcturus
GM200
Generation
Instinct (MIx)
Tesla Maxwell
(Mxx)
Process Size
7 nm
28 nm
Transistors
25,600 million
8,000 million
Die Size
750 mm²
601 mm²
Foundry
TSMC
TSMC
Density
34.1M / mm²
13.3M / mm²
API Support
DirectX
—
12 (12_1)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
2.1
3.0
CUDA
—
5.2
Shader Model
—
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm 10.5 inches
267 mm
10.5 inches
Height
111 mm 4.4 inches
—
Outputs
No outputs
No outputs
Bus Interface
PCIe 4.0 x16
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
Radeon Instinct
Tesla Kepler
Successor
—
Tesla Pascal