GPUs

AMD Radeon PRO W7900 vs NVIDIA GeForce RTX 3080 Ti Laptop 115W Full Specs

6,144 Shaders
2.5GHz
7,424 Shaders
1.26GHz
48GB GDDR6864GB/s
16GB GDDR6512GB/s
··
61.32 TFLOPS
··
18.71 TFLOPS
Form Factor
PCIe Card
Form Factor
Soldered
TDP
295W
TDP
115W
Power Connectors
2x 8-Pin
Power Connectors
-

Radeon PRO W7900Radeon PRO W7900245.3 TOPSINT4 Tensor
x1
GeForce RTX 3080 Ti Laptop 115WGeForce RTX 3080 Ti Laptop 115W598.7 TOPSINT4 Tensor Sparse
x2.44

Clock Speed
··
Clock Speed
···
Peak OPS
245.3 TOPSINT4 Tensor
Peak OPS
598.7 TOPSINT4 Tensor Sparse
Tensor FP16-16
61.32 TFLOPS
FP16-16 Tensor Sparse
-
Tensor FP16-32
61.32 TFLOPS
FP16-32 Tensor Sparse
-
Tensor FP16-16
74.83 TFLOPS
FP16-16 Tensor Sparse
149.7 TFLOPS
Tensor FP16-32
37.42 TFLOPS
FP16-32 Tensor Sparse
74.83 TFLOPS
BF16
122.6 TFLOPS
Tensor BF16
61.32 TFLOPS
BF16 Tensor Sparse
-
BF16
18.71 TFLOPS
Tensor BF16
37.42 TFLOPS
BF16 Tensor Sparse
74.83 TFLOPS
Tensor TF32
-
Tensor TF32
18.71 TFLOPS
FP32
61.32 TFLOPS
FP32
18.71 TFLOPS
FP64
1.92 TFLOPS
FP64
292.3 GFLOPS
Tensor INT4
245.3 TOPS
Tensor INT4
299.3 TOPS
Tensor INT8
61.32 TOPS
Tensor INT8
149.7 TOPS
Ray
-
Ray
36.54 TOPS
Pixel Rate
479 GPixel/s
Pixel Rate
121 GPixel/s
Texture Rate
958.1 GTexel/s
Texture Rate
292.3 GTexel/s

Shaders
6,144 Shaders
Shaders
7,424 Shaders
TMUs
384 TMUs
TMUs
232 TMUs
ROPs
192 ROPs
ROPs
96 ROPs
Tensor Cores
192 T-Cores
Tensor Cores
232 T-Cores
RT Cores
96 RT-Cores
RT Cores
58 RT-Cores
CUs
96 CUs
SMs
58 SMs

Base Clock
-
Base Clock
810MHz
Boost Clock
2.5GHz
Boost Clock
1.26GHz

L2 Cache
6.1MB shared
L2 Cache
4.1MB shared
L3 Cache
96MB shared
L3 Cache
-
L3 Bandwidth
3.5TB/s
L3 Bandwidth
-

48GB GDDR6
16GB GDDR6
Memory Bus
384-bit
Memory Bus
256-bit
Memory Speed
18GT/s
Memory Speed
16GT/s
Memory Bandwidth
864GB/s
Memory Bandwidth
512GB/s
ECC
No
ECC
No

TDP
295W
TDP
115W

Multi-Monitor
3
Multi-Monitor
3
HDCP
HDCP 2.3
HDCP
HDCP 2.3

3x DisplayPort 2.1
-
1x Mini DisplayPort 2.1
-

Encoder Model
VCN 4.0
Encoder Model
NVENC 7

Decoder Model
VCN 4.0
Decoder Model
NVDEC 5

Form Factor
PCIe Card
Form Factor
Soldered
PCIe
3-Slots
PCIe
-
Height
110 mm (4.33")
Width
280 mm (11.02")
Depth
51 mm (2.01")
-
Cooling
Blower
1x Fan
Cooling
Open-Air
-
Power Connectors
2x 8-Pin
Power Connectors
-

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
Radeon Pro 2023 branding
Branding
GeForce RTX 2018 branding
Codename
Plum Bonito
Codename
NV173
Chip Variant
Navi 31 XL
Chip Variant
GN20-E8-A1
Market Segment
Workstation
Market Segment
Laptop
Release Date
Apr 13, 2023
Release Date
Jan 12, 2021

Foundry
TSMC
Foundry
Samsung
Other Foundries
TSMCMCD
Other Foundries
-
Fabrication Node
N5
N6MCD
Fabrication Node
8N
-
Die Size
304mm²
225mm²MCD
Die Size
496mm²
-
Transistor Count
45.4 Billion
12.3 BillionMCD
Transistor Count
22 Billion
-
Transistor Density
149.2 MTr/mm²
54.67 MTr/mm²MCD
Transistor Density
44.35 MTr/mm²
-

No images available
No images available