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
Quadro K5100M
CORE STATE
GK104
VRAM
8 GB
CLOCK SPEED
771 MHz
TDP
100 W
BUS WIDTH
256 bit
ARCHITECTURE
Kepler
PROCESS
28 nm
LAUNCH DATE
2013
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_metal
DETAILED SPECIFICATIONS
SPECIFICATION
Instinct MI100
Quadro K5100M
Core Specs
Shading Units
7,680
1,536
-80.0%
Shaders
7,680
1,536
-80.0%
TMUs
480
128
-73.3%
ROPs
64
32
-50.0%
Compute Units
120
—
Clocks
Base Clock
1000 MHz
771 MHz
Boost Clock
1502 MHz
771 MHz
Memory Clock
1200 MHz 2.4 Gbps effective
900 MHz
3.6 Gbps effective
Memory
Memory Size
32 GB
8 GB
VRAM (MB)
32,768
8,192
-75.0%
Memory Type
HBM2
GDDR5
Memory Bus
4096 bit
256 bit
Bandwidth
1.23 TB/s
115.2 GB/s
Cache
L1 Cache
16 KB (per CU)
16 KB (per SMX)
L2 Cache
8 MB
512 KB
Performance
Pixel Rate
96.13 GPixel/s
24.67 GPixel/s
Texture Rate
721.0 GTexel/s
98.69 GTexel/s
FP32 (TFLOPS)
23.07 TFLOPS
2.369 TFLOPS
FP64 (TFLOPS)
11.54 TFLOPS (1:2)
98.69 GFLOPS (1:24)
FP16 (TFLOPS)
46.14 TFLOPS (2:1)
—
Power
TDP
300 W
100 W
TDP (W)
300
100
-66.7%
Suggested PSU
700 W
—
Power Connectors
2x 8-pin
None
Architecture
Architecture
CDNA 1.0
Kepler
GPU Name
Arcturus
GK104
Generation
Instinct (MIx)
Quadro Kepler-M
(Kx100M)
Process Size
7 nm
28 nm
Transistors
25,600 million
3,540 million
Die Size
750 mm²
294 mm²
Foundry
TSMC
TSMC
Density
34.1M / mm²
12.0M / mm²
API Support
DirectX
—
12 (11_0)
OpenGL
—
4.6
Vulkan
—
1.2.175
OpenCL
2.1
3.0
CUDA
—
3.0
Shader Model
—
6.5 (5.1)
Physical
Slot Width
Dual-slot
MXM Module
Length
267 mm 10.5 inches
—
Height
111 mm 4.4 inches
—
Outputs
No outputs
Portable Device Dependent
Bus Interface
PCIe 4.0 x16
MXM-B (3.0)
Other
Production
End-of-life
End-of-life
Predecessor
Radeon Instinct
Quadro Fermi-M
Successor
—
Quadro Maxwell-M