Intel Data Center GPU Max 1350 General-Purpose Float-Point performance (Vector Performance / Scalar Performance)
FP64: 44.44 TFLOPS
FP32: 44.44 TFLOPS
FP16: 44.44 TFLOPS
Matirx Compute
FP64
X
FP32
X
FP16
X
FP8
X
TF32
X
BF16
X
INT16
X
INT8
X
INT4
X
Intel Data Center GPU Max 1350 AI performance (Tensor Performance / Matrix Performance)
Hardware Specs
Intel Data Center GPU Max 1350 is a 10nm chip, has 100000 million transistors, launched by Intel at 2023.
It has 96 GB built-in(On-Board/On-Chip) memory with bandwidth up to 2457 GB/s.
It has 14336 general-purpose ALUs(CUDA cores/Shader cores) and 896 matrix cores(Tensor cores) .
Process Node
10 nm
Launch Year
2023
Vector(CUDA) Cores
14336
Matrix(Tensor) Cores
896
Core Frequency
750 ~ 1550 MHz
Cache
408MB
Comment without registration
Share your experience with Intel Data Center GPU Max 1350 / Found an Error? Help Us Improve!