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 P40
CORE STATE
GP102
VRAM
24 GB
CLOCK SPEED
1531 MHz
TDP
250 W
BUS WIDTH
384 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2016
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
PG506-232
Tesla P40
Core Specs
Shading Units
3,584
3,840
+7.1%
Shaders
3,584
3,840
+7.1%
TMUs
224
240
+7.1%
ROPs
96
96
0.0%
SM Count
56
30
-46.4%
Clocks
Base Clock
930 MHz
1303 MHz
Boost Clock
1440 MHz
1531 MHz
Memory Clock
1215 MHz
2.4 Gbps effective
1808 MHz
7.2 Gbps effective
Memory
Memory Size
24 GB
24 GB
VRAM (MB)
24,576
24,576
0.0%
Memory Type
HBM2
GDDR5
Memory Bus
3072 bit
384 bit
Bandwidth
933.1 GB/s
347.1 GB/s
Cache
L1 Cache
192 KB (per SM)
48 KB (per SM)
L2 Cache
24 MB
3 MB
Performance
Pixel Rate
138.2 GPixel/s
147.0 GPixel/s
Texture Rate
322.6 GTexel/s
367.4 GTexel/s
FP32 (TFLOPS)
10.32 TFLOPS
11.76 TFLOPS
FP64 (TFLOPS)
5.161 TFLOPS (1:2)
367.4 GFLOPS (1:32)
FP16 (TFLOPS)
10.32 TFLOPS (1:1)
183.7 GFLOPS (1:64)
AI/RT
Tensor Cores
224
—
Power
TDP
165 W
250 W
TDP (W)
165
250
+51.5%
Suggested PSU
450 W
600 W
Power Connectors
8-pin EPS
8-pin EPS
Architecture
Architecture
Ampere
Pascal
GPU Name
GA100
GP102
Generation
Server Ampere
(Axx)
Tesla Pascal
(Pxx)
Process Size
7 nm
16 nm
Transistors
54,200 million
11,800 million
Die Size
826 mm²
471 mm²
Foundry
TSMC
TSMC
Density
65.6M / mm²
25.1M / 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
Dual-slot
Length
267 mm
10.5 inches
267 mm
10.5 inches
Height
112 mm
4.4 inches
111 mm
4.4 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 4.0 x16
PCIe 3.0 x16
Other
Launch Price
—
5,699 USD
Production
End-of-life
End-of-life
Predecessor
Tesla Turing
Tesla Maxwell
Successor
Server Ada
Tesla Volta