GPUs

AMD Radeon HD 7990 vs NVIDIA GeForce RTX 5080 Full Specs

4,096 Shaders
1GHz
10,752 Shaders
2.62GHz
6GB GDDR5576GB/s
16GB GDDR7960GB/s
··
8.19 TFLOPS
··
56.28 TFLOPS
Form Factor
PCIe Card
Form Factor
PCIe Card
TDP
375W
TDP
360W
Power Connectors
-
2x 8-Pin
Power Connectors
1x 16-Pin 12VHPWR
-

Radeon HD 7990Radeon HD 79908.19 TFLOPSFP32 (2x 4.1 TFLOPS)
x1
GeForce RTX 5080GeForce RTX 50801.8 PFLOPSFP4 Tensor Sparse
x219.83

Clock Speed
···
Clock Speed
···
Peak OPS
8.19 TFLOPSFP32
Peak OPS
1.8 PFLOPSFP4 Tensor Sparse
-
Tensor FP4
900.4 TFLOPS
FP4 Tensor Sparse
1.8 PFLOPS
-
Tensor FP8-16
450.2 TFLOPS
FP8-16 Tensor Sparse
900.4 TFLOPS
Tensor FP8-32
225.1 TFLOPS
FP8-32 Tensor Sparse
450.2 TFLOPS
-
Tensor FP16-16
225.1 TFLOPS
FP16-16 Tensor Sparse
450.2 TFLOPS
Tensor FP16-32
112.6 TFLOPS
FP16-32 Tensor Sparse
225.1 TFLOPS
-
BF16
56.28 TFLOPS
Tensor BF16
112.6 TFLOPS
BF16 Tensor Sparse
225.1 TFLOPS
Tensor TF32
-
Tensor TF32
56.28 TFLOPS
FP32
8.19 TFLOPS
FP32
56.28 TFLOPS
FP64
2.05 TFLOPS
FP64
879.3 GFLOPS
-
Tensor INT8
450.2 TOPS
Ray
-
Ray
170.7 TOPS
Pixel Rate
32 GPixel/s
Pixel Rate
293.1 GPixel/s
Texture Rate
128 GTexel/s
Texture Rate
879.3 GTexel/s

Shaders
4,096 Shaders
Shaders
10,752 Shaders
TMUs
256 TMUs
TMUs
336 TMUs
ROPs
64 ROPs
ROPs
112 ROPs
Tensor Cores
-
Tensor Cores
336 T-Cores
RT Cores
-
RT Cores
84 RT-Cores
CUs
64 CUs
SMs
84 SMs

Base Clock
950MHz
Base Clock
2.3GHz
Boost Clock
1GHz
Boost Clock
2.62GHz

L2 Cache
768KB shared
L2 Cache
65.5MB shared

6GB GDDR5
16GB GDDR7
Memory Bus
384-bit
Memory Bus
256-bit
Memory Speed
6GT/s
Memory Speed
30GT/s
Memory Bandwidth
576GB/s
Memory Bandwidth
960GB/s
ECC
No
ECC
No

TDP
375W
TDP
360W
Max Temp
-
Max Temp
88°C Max

Multi-Monitor
4
Multi-Monitor
4
HDCP
-
HDCP
HDCP 2.3

-
3x DisplayPort 2.1
4x Mini DisplayPort 1.2
-
-
1x HDMI 2.1
1x DVI-I Dual-Link
-

Encoder Model
VCE 1.0
Encoder Model
2x NVENC 9

Decoder Model
UVD 3.2
Decoder Model
2x NVDEC 6

Form Factor
PCIe Card
Form Factor
PCIe Card
PCIe
2-Slots
PCIe
2.1-Slots
Height
115 mm (4.53")
Width
304 mm (11.97")
Depth
38 mm (1.5")
Height
137 mm (5.39")
Width
304 mm (11.97")
Depth
42 mm (1.65")
Cooling
Open-Air
3x Fans
Cooling
Open-Air
2x Fans
Power Connectors
2x 8-Pin
Power Connectors
1x 16-Pin 12VHPWR

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
Radeon 2011 branding
Branding
GeForce RTX 2022 branding
Codename
Tahiti
Codename
NV193
Chip Variant
Tahiti LE
Chip Variant
GB203-200-A1
Market Segment
Desktop
Market Segment
Desktop
Release Date
Apr 24, 2013
Release Date
Jan 6, 2025

Foundry
TSMC
Foundry
TSMC
Fabrication Node
28nm
Fabrication Node
4NP
Die Size
352mm²
Die Size
378mm²
Transistor Count
4.3 Billion
Transistor Count
45.6 Billion
Transistor Density
12.25 MTr/mm²
Transistor Density
120.6 MTr/mm²

No images available
No images available