GPU

NVIDIA Tesla M40

Edit@2 months ago

Intergrated Memory(VRAM)
Capacity

12 GB

(GDDR5 384-bit)

Bandwidth

288 GB/s

41 Token/s

Vector Compute
FP64
213.50 G
FP32
6.83 T
FP16
X
BF16
X
INT32
NI
INT8
X

NVIDIA Tesla M40 General-Purpose Float-Point performance (Vector Performance / Scalar Performance)

FP64: 213.50 GFLOPS

FP32: 6.83 TFLOPS

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

NVIDIA Tesla M40 AI performance (Tensor Performance / Matrix Performance)

Hardware Specs
NVIDIA Tesla M40 is a 28nm chip, has 8000 million transistors, launched by NVIDIA at 2015. It has 12 GB built-in(On-Board/On-Chip) memory with bandwidth up to 288 GB/s. It has 3072 general-purpose ALUs(CUDA cores/Shader cores).
Process Node
28 nm
Launch Year
2015
Vector(CUDA) Cores
3072
Matrix(Tensor) Cores
Core Frequency
948 ~ 1112 MHz
Cache
3MB