GPU Comparison
RADEON
AMD Radeon Pro Duo
CORE STATE
Capsaicin
VRAM
4 GB
CLOCK SPEED
—
TDP
350 W
BUS WIDTH
4096 bit
ARCHITECTURE
GCN 3.0
PROCESS
28 nm
LAUNCH DATE
2016
VS
GEFORCE
Tesla K20Xm
CORE STATE
GK110
VRAM
6 GB
CLOCK SPEED
—
TDP
235 W
BUS WIDTH
384 bit
ARCHITECTURE
Kepler
PROCESS
28 nm
LAUNCH DATE
2012
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_metal
DETAILED SPECIFICATIONS
SPECIFICATION
Pro Duo
Tesla K20Xm
Core Specs
Shading Units
4,096
2,688
-34.4%
Shaders
4,096
2,688
-34.4%
TMUs
256
224
-12.5%
ROPs
64
48
-25.0%
Compute Units
64
—
Clocks
GPU Clock
1000 MHz
732 MHz
Memory Clock
500 MHz
1000 Mbps effective
1300 MHz
5.2 Gbps effective
Memory
Memory Size
4 GB
6 GB
VRAM (MB)
4,096
6,144
+50.0%
Memory Type
HBM
GDDR5
Memory Bus
4096 bit
384 bit
Bandwidth
512.0 GB/s
249.6 GB/s
Cache
L1 Cache
16 KB (per CU)
16 KB (per SMX)
L2 Cache
2 MB
1536 KB
Performance
Pixel Rate
64.00 GPixel/s
40.99 GPixel/s
Texture Rate
256.0 GTexel/s
164.0 GTexel/s
FP32 (TFLOPS)
8.192 TFLOPS
3.935 TFLOPS
FP64 (TFLOPS)
512.0 GFLOPS (1:16)
1,311.7 GFLOPS (1:3)
FP16 (TFLOPS)
8.192 TFLOPS (1:1)
—
Power
TDP
350 W
235 W
TDP (W)
350
235
-32.9%
Suggested PSU
750 W
550 W
Power Connectors
3x 8-pin
—
Architecture
Architecture
GCN 3.0
Kepler
GPU Name
Capsaicin
GK110
Generation
Radeon Pro GCN
Tesla Kepler
(Kxx)
Process Size
28 nm
28 nm
Transistors
8,900 million
7,080 million
Die Size
596 mm²
561 mm²
Foundry
TSMC
TSMC
Density
14.9M / mm²
12.6M / mm²
API Support
DirectX
12 (12_0)
12 (11_0)
OpenGL
4.6
4.6
Vulkan
1.2.170
1.2.175
OpenCL
2.1
3.0
CUDA
—
3.5
Shader Model
6.5
6.5 (5.1)
Physical
Slot Width
Dual-slot
Dual-slot
Length
277 mm
10.9 inches
267 mm
10.5 inches
Height
111 mm
4.4 inches
—
Outputs
1x HDMI 1.4a3x DisplayPort 1.2
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16
Other
Launch Price
1,499 USD
7,699 USD
Production
End-of-life
End-of-life
Predecessor
FirePro GCN
Tesla Fermi
Successor
Radeon Pro Polaris
Tesla Maxwell