GPU Comparison
RADEON
AMD Radeon Instinct MI25
CORE STATE
Vega 10
VRAM
16 GB
CLOCK SPEED
1500 MHz
TDP
300 W
BUS WIDTH
2048 bit
ARCHITECTURE
GCN 5.0
PROCESS
14 nm
LAUNCH DATE
2017
VS
GEFORCE
Tesla K80
CORE STATE
GK210
VRAM
12 GB
CLOCK SPEED
824 MHz
TDP
300 W
BUS WIDTH
384 bit
ARCHITECTURE
Kepler 2.0
PROCESS
28 nm
LAUNCH DATE
2014
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Instinct MI25
Tesla K80
Core Specs
Shading Units
4,096
2,496
-39.1%
Shaders
4,096
2,496
-39.1%
TMUs
256
208
-18.8%
ROPs
64
48
-25.0%
Compute Units
64
—
Clocks
Base Clock
1400 MHz
562 MHz
Boost Clock
1500 MHz
824 MHz
Memory Clock
852 MHz
1704 Mbps effective
1253 MHz
5 Gbps effective
Memory
Memory Size
16 GB
12 GB
VRAM (MB)
16,384
12,288
-25.0%
Memory Type
HBM2
GDDR5
Memory Bus
2048 bit
384 bit
Bandwidth
436.2 GB/s
240.6 GB/s
Cache
L1 Cache
16 KB (per CU)
16 KB (per SMX)
L2 Cache
4 MB
1536 KB
Performance
Pixel Rate
96.00 GPixel/s
42.85 GPixel/s
Texture Rate
384.0 GTexel/s
171.4 GTexel/s
FP32 (TFLOPS)
12.29 TFLOPS
4.113 TFLOPS
FP64 (TFLOPS)
768.0 GFLOPS (1:16)
1,371.1 GFLOPS (1:3)
FP16 (TFLOPS)
24.58 TFLOPS (2:1)
—
Power
TDP
300 W
300 W
TDP (W)
300
300
0.0%
Suggested PSU
700 W
700 W
Power Connectors
2x 8-pin
1x 8-pin
Architecture
Architecture
GCN 5.0
Kepler 2.0
GPU Name
Vega 10
GK210
Generation
Radeon Instinct
(MIx)
Tesla Kepler
(Kxx)
Process Size
14 nm
28 nm
Transistors
12,500 million
7,100 million
Die Size
495 mm²
561 mm²
Foundry
GlobalFoundries
TSMC
Density
25.3M / mm²
12.7M / mm²
API Support
DirectX
12 (12_1)
12 (11_1)
OpenGL
4.6
4.6
Vulkan
1.3
1.2.175
OpenCL
2.1
3.0
CUDA
—
3.7
Shader Model
6.7
6.5 (5.1)
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 3.0 x16
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
FirePro Data Center
Tesla Fermi
Successor
—
Tesla Maxwell