NVIDIA GA10B 32SM vs ARM Mali-T820 MP1 600MHz

NVIDIA GA10B 32SM
ARM Mali-T820 MP1 600MHz
2048 Shaders
Shared Memory
1300MHz
10 Shaders
Shared Memory
600MHz
Peak AI Performance
340.79 TOPS
INT4 Tensor Sparse
Peak AI Performance
10 GFLOPS
FP32
FP32
5.33 TFLOPS
FP32
10 GFLOPS
FP16
10.65 TFLOPS
-
-
Form Factor
iGPU
-
Form Factor
iGPU
-
TDP
Shared
TDP
Shared
-
-
-
-
-
-
-
-
-
-
GB6 OpenCL N/A
0%
GB6 OpenCL N/A
0%
GB6 Metal N/A
0%
GB6 Metal N/A
0%
GB6 Vulkan N/A
0%
GB6 Vulkan N/A
0%
GB5 OpenCL N/A
0%
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 N/A
0%
OCT Metal N/A
0%
Peak AI Performance
340.79 TOPS
INT4 Tensor Sparse
Peak AI Performance
10 GFLOPS
FP32
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
FP16
10.65 TFLOPS
42.6 TFLOPS Tensor (FP16 Accumulate)
85.2 TFLOPS Tensor (FP16 Accumulate) Sparse
42.6 TFLOPS Tensor (FP32 Accumulate)
85.2 TFLOPS Tensor (FP32 Accumulate) Sparse
-
-
-
-
-
-
FP32
5.33 TFLOPS
-
-
FP32
10 GFLOPS
-
-
-
-
-
-
-
-
BF16
-
42.6 TFLOPS Tensor
85.2 TFLOPS Tensor Sparse
-
-
-
-
TF32
21.3 TFLOPS Tensor
42.6 TFLOPS Tensor Sparse
-
-
-
INT4
170.39 TOPS Tensor
340.79 TOPS Tensor Sparse
-
-
-
INT8
-
85.2 TOPS Tensor
170.39 TOPS Tensor Sparse
-
-
-
-
-
-
-
-
-
-
-
-
Pixel Fillrate
41.6 GPixel/s
Pixel Fillrate
0.6 GPixel/s
-
-
-
-
Texture Fillrate
20.8 GTexel/s
Texture Fillrate
0.6 GTexel/s
Manufacturer
NVIDIA
Manufacturer
ARM
Chip Designer
NVIDIA
Chip Designer
ARM
Architecture
Ampere
Architecture
Midgard 4
Family
Jetson
Family
T Series
Codename
Hercules
GA10B
-
-
Codename
-
Exynos 7 Octa 7870
-
-
Market Segment
Mobile
Market Segment
Mobile
Release Date
1/1/2021
Release Date
12/4/2018
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Form
iGPU
Form
iGPU
Shading Units
2048 Shaders
-
Shading Units
10 Shaders
-
Texture Mapping Units
16 TMUs
Texture Mapping Units
1 TMU
Render Output Units
32 ROPs
Render Output Units
1 ROP
Tensor Cores
64 T-Cores
-
-
-
-
-
-
Streaming Multiprocessors
16 SMs
-
-
-
-
-
-
-
-
Execution Units
1 EU
Graphics Processing Clusters
2 GPCs
Graphics Processing Clusters
1 GPC
-
-
-
1300MHz
-
-
-
600MHz
-
-
-
-
L1
64KB/SM Tex
192KB/SM
-
-
L1
-
-
-
Unknown
L2
4MB Shared
L2
Unknown
-
-
-
-
-
-
Shared Memory
-
-
Shared Memory
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
TDP
Shared
TDP
Shared
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
Max Resolution
Unknown
Max Resolution
Unknown
Max Resolution Refresh Rate
-
Max Resolution Refresh Rate
-
Variable Refresh Rate
G-Sync
FreeSync
-
Variable Refresh Rate
-
-
-
Display Stream Compression (DSC)
Not Supported
Display Stream Compression (DSC)
Not Supported
Multi Monitor Support
Unknown
Multi Monitor Support
Unknown
-
-
-
-
Model
NVENC 7
No Encoders
-
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Model
NVDEC 5
No Decoders
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
-
-
-
-
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
-
-
-
-
-
-
Shader Model
6.7
CUDA
8.7
-
-
PureVideo HD
VP11
VDPAU
Feature Set K
-
-
-
-
-
-
-
-
-
-
Not a Card
-
-
-
Not a Card
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Change Comparison