GPU

NVIDIA GeForce RTX 2080

Edit@2 months ago

Intergrated Memory(VRAM)
Capacity

8 GB

(GDDR6 256-bit)

Bandwidth

448 GB/s

64 Token/s

Vector Compute
FP64
314.60 G
FP32
10.07 T
FP16
20.14 T
BF16
X
INT32
10.07 T
INT8
X

NVIDIA GeForce RTX 2080 General-Purpose Float-Point performance (Vector Performance / Scalar Performance)

FP64: 314.60 GFLOPS

FP32: 10.07 TFLOPS

FP16: 20.14 TFLOPS

INT32: 10.07 TOPS

Matirx Compute
FP64
X
FP32
X
FP16
40.27 T
FP8
X
TF32
X
BF16
X
INT16
X
INT8
161.10 T
INT4
322.19 T

NVIDIA GeForce RTX 2080 AI performance (Tensor Performance / Matrix Performance)

FP16: 40.27 TFLOPS

INT8: 161.10 TOPS

INT4: 322.19 TOPS

Hardware Specs
NVIDIA GeForce RTX 2080 is a 12nm chip, has 13600 million transistors, launched by NVIDIA at 2018. It has 8 GB built-in(On-Board/On-Chip) memory with bandwidth up to 448 GB/s. It has 2944 general-purpose ALUs(CUDA cores/Shader cores) and 368 matrix cores(Tensor cores) .
Process Node
12 nm
Launch Year
2018
Vector(CUDA) Cores
2944
Matrix(Tensor) Cores
368
Core Frequency
1515 ~ 1710 MHz
Cache
4MB

Comment without registration

Share your experience with NVIDIA GeForce RTX 2080 / Found an Error? Help Us Improve!