GPU Comparison
GEFORCE
NVIDIA P104-100
CORE STATE
GP104
VRAM
4 GB
CLOCK SPEED
1733 MHz
TDP
—
BUS WIDTH
256 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2017
VS
GEFORCE
Tesla T4
CORE STATE
TU104
VRAM
16 GB
CLOCK SPEED
1590 MHz
TDP
70 W
BUS WIDTH
256 bit
ARCHITECTURE
Turing
PROCESS
12 nm
LAUNCH DATE
2018
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
P104-100
Tesla T4
Core Specs
Shading Units
1,920
2,560
+33.3%
Shaders
1,920
2,560
+33.3%
TMUs
120
160
+33.3%
ROPs
64
64
0.0%
SM Count
15
40
+166.7%
Clocks
Base Clock
1607 MHz
585 MHz
Boost Clock
1733 MHz
1590 MHz
Memory Clock
1251 MHz
10 Gbps effective
1250 MHz
10 Gbps effective
Memory
Memory Size
4 GB
16 GB
VRAM (MB)
4,096
16,384
+300.0%
Memory Type
GDDR5X
GDDR6
Memory Bus
256 bit
256 bit
Bandwidth
320.3 GB/s
320.0 GB/s
Cache
L1 Cache
48 KB (per SM)
64 KB (per SM)
L2 Cache
2 MB
4 MB
Performance
Pixel Rate
110.9 GPixel/s
101.8 GPixel/s
Texture Rate
208.0 GTexel/s
254.4 GTexel/s
FP32 (TFLOPS)
6.655 TFLOPS
8.141 TFLOPS
FP64 (TFLOPS)
208.0 GFLOPS (1:32)
254.4 GFLOPS (1:32)
FP16 (TFLOPS)
104.0 GFLOPS (1:64)
65.13 TFLOPS (8:1)
AI/RT
RT Cores
—
40
Tensor Cores
—
320
Power
TDP
—
70 W
TDP (W)
—
70
Suggested PSU
200 W
250 W
Power Connectors
1x 8-pin
None
Architecture
Architecture
Pascal
Turing
GPU Name
GP104
TU104
Generation
Mining GPUs
Tesla Turing
(Txx)
Process Size
16 nm
12 nm
Transistors
7,200 million
13,600 million
Die Size
314 mm²
545 mm²
Foundry
TSMC
TSMC
Density
22.9M / mm²
25.0M / mm²
API Support
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
6.1
7.5
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Single-slot
Length
267 mm
10.5 inches
168 mm
6.6 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 1.0 x4
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
—
Tesla Volta
Successor
—
Server Ampere