Intel Arc A780 vs NVIDIA GeForce GTX 1070 GDDR5X
We compared two Desktop platform GPUs: 16GB VRAM Arc A780 and 8GB VRAM GeForce GTX 1070 GDDR5X to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Intel Arc A780 's Advantages
Boost Clock has increased by 31% (2200MHz vs 1683MHz)
More VRAM (16GB vs 8GB)
Larger VRAM bandwidth (559.6GB/s vs 256.3GB/s)
2176 additional rendering cores
NVIDIA GeForce GTX 1070 GDDR5X 's Advantages
Lower TDP (150W vs 200W)
Score
Benchmark
FP32 (float)
Arc A780
+178%
18.02 TFLOPS
GeForce GTX 1070 GDDR5X
6.463 TFLOPS
Graphics Card
Unknown
Release Date
Dec 2018
Alchemist(Arc 7)
Generation
GeForce 10
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
2200 MHz
Base Clock
1506 MHz
2200 MHz
Boost Clock
1683 MHz
1093 MHz
Memory Clock
1001 MHz
Memory
16GB
Memory Size
8GB
GDDR6X
Memory Type
GDDR5X
256bit
Memory Bus
256bit
559.6GB/s
Bandwidth
256.3GB/s
Render Config
-
-
-
-
SM Count
15
4096
Shading Units
1920
256
TMUs
120
128
ROPs
64
512
Tensor Cores
-
32
RT Cores
-
-
L1 Cache
48 KB (per SM)
16 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
281.6 GPixel/s
Pixel Rate
107.7 GPixel/s
563.2 GTexel/s
Texture Rate
202.0 GTexel/s
36.04 TFLOPS
FP16 (half)
101.0 GFLOPS
18.02 TFLOPS
FP32 (float)
6.463 TFLOPS
2.253 TFLOPS
FP64 (double)
202.0 GFLOPS
Board Design
200W
TDP
150W
550 W
Suggested PSU
450 W
1x HDMI 2.13x DisplayPort 2.0
Outputs
1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a
2x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
DG2-512
GPU Name
GP104
ACM-G10
GPU Variant
GP104-200-A1
Generation 12.7
Architecture
Pascal
TSMC
Foundry
TSMC
6 nm
Process Size
16 nm
21.7 billion
Transistors
7.2 billion
406 mm²
Die Size
314 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
-
CUDA
6.1
6.6
Shader Model
6.4
