GPU

NVIDIA Tesla P100 SXM2

Edit@2 months ago

Intergrated Memory(VRAM)
Capacity

16 GB

(HBM2 4096-bit)

Bandwidth

732 GB/s

104 Token/s

Vector Compute
FP64
5.30 T
FP32
10.61 T
FP16
21.22 T
BF16
X
INT32
NI
INT8
X

NVIDIA Tesla P100 SXM2 General-Purpose Float-Point performance (Vector Performance / Scalar Performance)

FP64: 5.30 TFLOPS

FP32: 10.61 TFLOPS

FP16: 21.22 TFLOPS

Matirx Compute
FP64
X
FP32
X
FP16
X
FP8
X
TF32
X
BF16
X
INT16
X
INT8
X
INT4
X

NVIDIA Tesla P100 SXM2 AI performance (Tensor Performance / Matrix Performance)

Hardware Specs
NVIDIA Tesla P100 SXM2 is a 16nm chip, has 15300 million transistors, launched by NVIDIA at 2016. It has 16 GB built-in(On-Board/On-Chip) memory with bandwidth up to 732 GB/s. It has 3584 general-purpose ALUs(CUDA cores/Shader cores).
Process Node
16 nm
Launch Year
2016
Vector(CUDA) Cores
3584
Matrix(Tensor) Cores
Core Frequency
1328 ~ 1480 MHz
Cache
4MB