Intel Arc Pro A40 vs NVIDIA RTX A400

Intel Arc Pro A40
NVIDIA RTX A400
1024 Shaders
6GB GDDR6
1700MHz
768 Shaders
4GB GDDR6
1760MHz
Peak Performance
111.41 TOPS
INT4 Tensor
Peak Performance
86.51 TOPS
INT4 Tensor Sparse
FP32
3.48 TFLOPS
FP32
2.7 TFLOPS
FP16
6.96 TFLOPS
FP16
2.7 TFLOPS
Form Factor
PCIe Card
2.0-Slots
Form Factor
PCIe Card
1.0-Slots
TDP
50W
TDP
50W
-
-
-
-
-
-
-
-
-
-
GB6 Metal N/A
0%
GB6 Metal N/A
0%
GB5 OpenCL 15,155
5%
GB5 OpenCL N/A
0%
GB5 CUDA N/A
0%
GB5 CUDA N/A
0%
GB5 Metal N/A
0%
GB5 Metal N/A
0%
GB5 Vulkan N/A
0%
GB5 Vulkan N/A
0%
OCT 2020.1 N/A
0%
OCT 2020.1 N/A
0%
OCT Metal 50
8%
OCT Metal N/A
0%
Manufacturer
Intel
Manufacturer
NVIDIA
Chip Designer
Intel
Chip Designer
NVIDIA
Architecture
Alchemist
Architecture
Ampere
Family
Arc Pro A
Family
RTX A
Codename
Xe HPG
ACM-G11
Variant
DG2-128
Codename
NV177
GA107
-
-
Market Segment
Workstation
Market Segment
Workstation
Release Date
8/8/2022
Release Date
4/17/2023
Foundry
TSMC
-
Foundry
Samsung
-
Fabrication Node
N6
-
Fabrication Node
8N
-
Die Size
157 mm²
-
Die Size
200 mm²
-
Transistor Count
7.2 Billion
-
Transistor Count
8.7 Billion
-
Transistor Density
45.86M/mm²
-
Transistor Density
43.50M/mm²
-
Form
PCIe Card
Form
PCIe Card
Shading Units
1024 Shaders
-
Shading Units
768 Shaders
-
Texture Mapping Units
64 TMUs
Texture Mapping Units
24 TMUs
Render Output Units
32 ROPs
Render Output Units
16 ROPs
Tensor Cores
128 T-Cores
Tensor Cores
24 T-Cores
Ray-Tracing Cores
8 RT-Cores
Ray-Tracing Cores
6 RT-Cores
-
-
Streaming Multiprocessors
6 SMs
-
-
-
-
Execution Units
128 EUs
-
-
Graphics Processing Clusters
8 GPCs
Graphics Processing Clusters
1 GPC
-
-
1500MHz Base
1700MHz
-
-
1000MHz Base
1760MHz
Peak Performance
111.41 TOPS
INT4 Tensor
Peak Performance
86.51 TOPS
INT4 Tensor Sparse
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
FP16
6.96 TFLOPS
-
-
27.85 TFLOPS Tensor (FP32 Accumulate)
-
FP16
2.7 TFLOPS
10.81 TFLOPS Tensor (FP16 Accumulate)
21.63 TFLOPS Tensor (FP16 Accumulate) Sparse
10.81 TFLOPS Tensor (FP32 Accumulate)
21.63 TFLOPS Tensor (FP32 Accumulate) Sparse
FP32
3.48 TFLOPS
-
-
FP32
2.7 TFLOPS
-
-
FP64
0.87 TFLOPS
-
FP64
0.04 TFLOPS
-
BF16
-
27.85 TFLOPS Tensor
-
BF16
2.7 TFLOPS
10.81 TFLOPS Tensor
21.63 TFLOPS Tensor Sparse
-
-
-
TF32
5.41 TFLOPS Tensor
10.81 TFLOPS Tensor Sparse
INT4
111.41 TOPS Tensor
-
INT4
43.25 TOPS Tensor
86.51 TOPS Tensor Sparse
INT8
-
55.71 TOPS Tensor
-
INT8
-
21.63 TOPS Tensor
43.25 TOPS Tensor Sparse
-
-
INT32
1.35 TOPS
-
-
Ray Tracing
5.3 TOPS
Pixel Fillrate
54.4 GPixel/s
Pixel Fillrate
28.16 GPixel/s
-
-
-
-
Texture Fillrate
108.8 GTexel/s
Texture Fillrate
42.24 GTexel/s
-
-
-
-
L1
-
-
-
Unknown
L1
64KB/SM Tex
128KB/SM
-
-
L2
4MB Shared
L2
1MB Shared
-
-
-
-
-
-
6GB
GDDR6
-
4GB
GDDR6
-
Bus Width
96Bit
Bus Width
64Bit
Clock
2000MHz
Transfer Rate
16GT/s
Bandwidth
192GB/s
Clock
1500MHz
Transfer Rate
12GT/s
Bandwidth
96GB/s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
TDP
50W
TDP
50W
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
4x mini-DisplayPort 2.0
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
4x mini-DisplayPort 1.4
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Max Resolution
7680x4320
Max Resolution
7680x4320
Max Resolution Refresh Rate
60Hz
Max Resolution Refresh Rate
60Hz
Variable Refresh Rate
-
FreeSync
-
Variable Refresh Rate
G-Sync
FreeSync
-
Display Stream Compression (DSC)
Not Supported
Display Stream Compression (DSC)
Supported
Multi Monitor Support
4
Multi Monitor Support
3
-
-
Content Protection
HDCP 2.3
Model
Arc
Model
NVENC 7
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
Model
Arc
Model
NVDEC 5
Codec
-
MPEG-2
-
JPEG
-
-
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
Direct X
12
Direct 3D
12_2
Direct X
12
Direct 3D
12_2
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
OpenGL
4.6
OpenCL
3.0
Vulkan
1.2
Shader Model
6.6
-
-
-
-
-
-
-
-
Shader Model
6.6
CUDA
8.6
-
-
PureVideo HD
VP11
VDPAU
Feature Set K
-
-
-
1x Fan
-
-
-
1x Fan
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Slots Required
2.0
PCIe Version
4.0
PCIe Lanes
8
Slots Required
1.0
PCIe Version
4.0
PCIe Lanes
8
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Height
69 mm (2.72 in)
Width
163 mm (6.42 in)
Depth
40 mm (1.57 in)
Change Comparison