Home GPU Comparison Intel Arc A770 vs NVIDIA GeForce RTX 3090 Ti

Intel Arc A770 vs NVIDIA GeForce RTX 3090 Ti

We compared two Desktop platform GPUs: 16GB VRAM Arc A770 and 24GB VRAM GeForce RTX 3090 Ti to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

Intel Arc A770 's Advantages
Released 9 months late
Boost Clock has increased by 29% (2400MHz vs 1860MHz)
Lower TDP (225W vs 450W)
NVIDIA GeForce RTX 3090 Ti 's Advantages
More VRAM (24GB vs 16GB)
Larger VRAM bandwidth (1008GB/s vs 512.0GB/s)
6656 additional rendering cores

Score

Benchmark

FP32 (float)
Arc A770
19.66 TFLOPS
GeForce RTX 3090 Ti +103%
40 TFLOPS
3DMark Time Spy
Arc A770
13660
GeForce RTX 3090 Ti +61%
22082
Blender
Arc A770
2085
GeForce RTX 3090 Ti +209%
6459
Shadow of the Tomb Raider 2160p
Arc A770
45
GeForce RTX 3090 Ti +133%
105
Shadow of the Tomb Raider 1440p
Arc A770
80
GeForce RTX 3090 Ti +108%
167
Shadow of the Tomb Raider 1080p
Arc A770
105
GeForce RTX 3090 Ti +100%
210
Horizon Forbidden West 1080p
Arc A770
49
GeForce RTX 3090 Ti +132%
114
Horizon Forbidden West 1440p
Arc A770
45
GeForce RTX 3090 Ti +106%
93
Horizon Forbidden West 2160p
Arc A770
26
GeForce RTX 3090 Ti +138%
62
VS

Graphics Card

Oct 2022
Release Date
Jan 2022
Alchemist
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

2100 MHz
Base Clock
1560 MHz
2400 MHz
Boost Clock
1860 MHz
2000 MHz
Memory Clock
1313 MHz

Memory

16GB
Memory Size
24GB
GDDR6
Memory Type
GDDR6X
256bit
Memory Bus
384bit
512.0GB/s
Bandwidth
1008GB/s

Render Config

-
SM Count
84
-
Compute Units
-
4096
Shading Units
10752
256
TMUs
336
128
ROPs
112
512
Tensor Cores
336
32
RT Cores
84
-
L1 Cache
128 KB (per SM)
16 MB
L2 Cache
6 MB

Theoretical Performance

307.2 GPixel/s
Pixel Rate
208.3 GPixel/s
614.4 GTexel/s
Texture Rate
625.0 GTexel/s
39.32 TFLOPS
FP16 (half)
40.00 TFLOPS
19.66 TFLOPS
FP32 (float)
40.00 TFLOPS
-
FP64 (double)
625.0 GFLOPS

Graphics Processor

DG2-512
GPU Name
GA102
ACM-G10
GPU Variant
GA102-350-A1
Generation 12.7
Architecture
Ampere
TSMC
Foundry
Samsung
6 nm
Process Size
8 nm
21.7 billion
Transistors
28.3 billion
406 mm²
Die Size
628 mm²

Board Design

225W
TDP
450W
550 W
Suggested PSU
850 W
1x HDMI 2.1 3x DisplayPort 2.0
Outputs
1x HDMI 2.1 3x DisplayPort 1.4a
1x 6-pin + 1x 8-pin
Power Connectors
1x 16-pin

Graphics Features

12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
-
CUDA
8.6
6.6
Shader Model
6.6

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy