GPU Comparison
GEFORCE
NVIDIA PG506-232
CORE STATE
GA100
VRAM
24 GB
CLOCK SPEED
1440 MHz
TDP
165 W
BUS WIDTH
3072 bit
ARCHITECTURE
Ampere
PROCESS
7 nm
LAUNCH DATE
2021
VS
GEFORCE
Tesla P4
CORE STATE
GP104
VRAM
8 GB
CLOCK SPEED
1114 MHz
TDP
75 W
BUS WIDTH
256 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2016
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
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