GPU Comparison

NVIDIA
GEFORCE

NVIDIA PG506-232

CORE STATE GA100
VRAM 24 GB
CLOCK SPEED 1440 MHz
TDP 165 W
BUS WIDTH 3072 bit
ARCHITECTURE Ampere
nm
PROCESS 7 nm
LAUNCH DATE 2021
VS
NVIDIA
GEFORCE

Tesla P4

CORE STATE GP104
VRAM 8 GB
CLOCK SPEED 1114 MHz
TDP 75 W
BUS WIDTH 256 bit
ARCHITECTURE Pascal
nm
PROCESS 16 nm
LAUNCH DATE 2016

PERFORMANCE BENCHMARKS

geekbench_opencl
225,124
37,896
geekbench_vulkan
N/A
40,309

DETAILED SPECIFICATIONS

SPECIFICATION
PG506-232
Tesla P4
Core Specs
Shading Units
3,584
2,560 -28.6%
Shaders
3,584
2,560 -28.6%
TMUs
224
160 -28.6%
ROPs
96
64 -33.3%
SM Count
56
20 -64.3%
Clocks
Base Clock
930 MHz
886 MHz
Boost Clock
1440 MHz
1114 MHz
Memory Clock
1215 MHz 2.4 Gbps effective
1502 MHz 6 Gbps effective
Memory
Memory Size
24 GB
8 GB
VRAM (MB)
24,576
8,192 -66.7%
Memory Type
HBM2
GDDR5
Memory Bus
3072 bit
256 bit
Bandwidth
933.1 GB/s
192.3 GB/s
Cache
L1 Cache
192 KB (per SM)
48 KB (per SM)
L2 Cache
24 MB
2 MB
Performance
Pixel Rate
138.2 GPixel/s
71.30 GPixel/s
Texture Rate
322.6 GTexel/s
178.2 GTexel/s
FP32 (TFLOPS)
10.32 TFLOPS
5.704 TFLOPS
FP64 (TFLOPS)
5.161 TFLOPS (1:2)
178.2 GFLOPS (1:32)
FP16 (TFLOPS)
10.32 TFLOPS (1:1)
89.12 GFLOPS (1:64)
AI/RT
Tensor Cores
224
Power
TDP
165 W
75 W
TDP (W)
165
75 -54.5%
Suggested PSU
450 W
250 W
Power Connectors
8-pin EPS
None
Architecture
Architecture
Ampere
Pascal
GPU Name
GA100
GP104
Generation
Server Ampere (Axx)
Tesla Pascal (Pxx)
Process Size
7 nm
16 nm
Transistors
54,200 million
7,200 million
Die Size
826 mm²
314 mm²
Foundry
TSMC
TSMC
Density
65.6M / mm²
22.9M / mm²
API Support
DirectX
12 (12_1)
OpenGL
4.6
Vulkan
1.4
OpenCL
3.0
3.0
CUDA
8.0
6.1
Shader Model
6.8
Physical
Slot Width
Dual-slot
Single-slot
Length
267 mm 10.5 inches
168 mm 6.6 inches
Height
112 mm 4.4 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 4.0 x16
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
Tesla Turing
Tesla Maxwell
Successor
Server Ada
Tesla Volta
View PG506-232 Details View Tesla P4 Details