GPU

NVIDIA Tesla K8

Edit@2 months ago

Intergrated Memory(VRAM)
Capacity

8 GB

(GDDR5 256-bit)

Bandwidth

160 GB/s

22 Token/s

Vector Compute
FP64
103.80 G
FP32
2.49 T
FP16
X
BF16
X
INT32
NI
INT8
X

NVIDIA Tesla K8 General-Purpose Float-Point performance (Vector Performance / Scalar Performance)

FP64: 103.80 GFLOPS

FP32: 2.49 TFLOPS

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

NVIDIA Tesla K8 AI performance (Tensor Performance / Matrix Performance)

Hardware Specs
NVIDIA Tesla K8 is a 28nm chip, has 3540 million transistors, launched by NVIDIA at 2014. It has 8 GB built-in(On-Board/On-Chip) memory with bandwidth up to 160 GB/s. It has 1536 general-purpose ALUs(CUDA cores/Shader cores).
Process Node
28 nm
Launch Year
2014
Vector(CUDA) Cores
1536
Matrix(Tensor) Cores
Core Frequency
693 ~ 811 MHz
Cache
0.5MB