GPU Comparison
GEFORCE
NVIDIA T400
CORE STATE
TU117
VRAM
2 GB
CLOCK SPEED
1425 MHz
TDP
30 W
BUS WIDTH
64 bit
ARCHITECTURE
Turing
PROCESS
12 nm
LAUNCH DATE
2021
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_vulkan
geekbench_metal
DETAILED SPECIFICATIONS
SPECIFICATION
T400
Tesla K20Xm
Core Specs
Shading Units
384
2,688
+600.0%
Shaders
384
2,688
+600.0%
TMUs
24
224
+833.3%
ROPs
16
48
+200.0%
SM Count
6
—
Clocks
Base Clock
420 MHz
—
Boost Clock
1425 MHz
—
GPU Clock
—
732 MHz
Memory Clock
1250 MHz
10 Gbps effective
1300 MHz
5.2 Gbps effective
Memory
Memory Size
2 GB
6 GB
VRAM (MB)
2,048
6,144
+200.0%
Memory Type
GDDR6
GDDR5
Memory Bus
64 bit
384 bit
Bandwidth
80.00 GB/s
249.6 GB/s
Cache
L1 Cache
64 KB (per SM)
16 KB (per SMX)
L2 Cache
1024 KB
1536 KB
Performance
Pixel Rate
22.80 GPixel/s
40.99 GPixel/s
Texture Rate
34.20 GTexel/s
164.0 GTexel/s
FP32 (TFLOPS)
1,094.4 GFLOPS
3.935 TFLOPS
FP64 (TFLOPS)
34.20 GFLOPS (1:32)
1,311.7 GFLOPS (1:3)
FP16 (TFLOPS)
2.189 TFLOPS (2:1)
—
Power
TDP
30 W
235 W
TDP (W)
30
235
+683.3%
Suggested PSU
200 W
550 W
Power Connectors
None
—
Architecture
Architecture
Turing
Kepler
GPU Name
TU117
GK110
Generation
Quadro Turing
(Tx000)
Tesla Kepler
(Kxx)
Process Size
12 nm
28 nm
Transistors
4,700 million
7,080 million
Die Size
200 mm²
561 mm²
Foundry
TSMC
TSMC
Density
23.5M / mm²
12.6M / mm²
API Support
DirectX
12 (12_1)
12 (11_0)
OpenGL
4.6
4.6
Vulkan
1.4
1.2.175
OpenCL
3.0
3.0
CUDA
7.5
3.5
Shader Model
6.8
6.5 (5.1)
Physical
Slot Width
Single-slot
Dual-slot
Length
—
267 mm
10.5 inches
Outputs
3x mini-DisplayPort 1.4a
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16
Other
Launch Price
—
7,699 USD
Production
End-of-life
End-of-life
Predecessor
Quadro Volta
Tesla Fermi
Successor
Workstation Ampere
Tesla Maxwell