NVIDIA GA10B 16SM 625MHz vs ARM Mali-G78 MP20 848MHz

NVIDIA GA10B 16SM 625MHz
ARM Mali-G78 MP20 848MHz
1024 Shaders
Shared Memory
625MHz
640 Shaders
Shared Memory
848MHz
Peak Performance
81.92 TOPS
INT4 Tensor Sparse
Peak Performance
2.17 TFLOPS
FP16
FP32
1.28 TFLOPS
FP32
1.09 TFLOPS
FP16
2.56 TFLOPS
FP16
2.17 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%
Manufacturer
NVIDIA
Manufacturer
ARM
Chip Designer
NVIDIA
Chip Designer
ARM
Architecture
Ampere
Architecture
Valhall 2
Family
Jetson
Family
Series 8
Codename
Hercules
GA10B
-
-
Codename
-
Tensor
-
-
Market Segment
Mobile
Market Segment
Mobile
Release Date
1/1/2023
Release Date
10/19/2021
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Form
iGPU
Form
iGPU
Shading Units
1024 Shaders
-
Shading Units
640 Shaders
-
Texture Mapping Units
8 TMUs
Texture Mapping Units
80 TMUs
Render Output Units
16 ROPs
Render Output Units
40 ROPs
Tensor Cores
32 T-Cores
-
-
-
-
-
-
Streaming Multiprocessors
8 SMs
-
-
-
-
-
-
-
-
Execution Units
20 EUs
Graphics Processing Clusters
1 GPC
Graphics Processing Clusters
20 GPCs
-
-
-
625MHz
-
-
-
848MHz
Peak Performance
81.92 TOPS
INT4 Tensor Sparse
Peak Performance
2.17 TFLOPS
FP16
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
FP16
2.56 TFLOPS
10.24 TFLOPS Tensor (FP16 Accumulate)
20.48 TFLOPS Tensor (FP16 Accumulate) Sparse
10.24 TFLOPS Tensor (FP32 Accumulate)
20.48 TFLOPS Tensor (FP32 Accumulate) Sparse
FP16
2.17 TFLOPS
-
-
-
-
FP32
1.28 TFLOPS
-
-
FP32
1.09 TFLOPS
-
-
-
-
-
-
-
-
BF16
-
10.24 TFLOPS Tensor
20.48 TFLOPS Tensor Sparse
-
-
-
-
TF32
5.12 TFLOPS Tensor
10.24 TFLOPS Tensor Sparse
-
-
-
INT4
40.96 TOPS Tensor
81.92 TOPS Tensor Sparse
-
-
-
INT8
-
20.48 TOPS Tensor
40.96 TOPS Tensor Sparse
-
-
-
-
-
-
-
-
-
-
-
-
Pixel Fillrate
10 GPixel/s
Pixel Fillrate
33.92 GPixel/s
-
-
-
-
Texture Fillrate
5 GTexel/s
Texture Fillrate
67.84 GTexel/s
-
-
-
-
L1
64KB/SM Tex
192KB/SM
-
-
L1
-
-
-
Unknown
L2
2MB Shared
L2
Unknown
-
-
-
-
-
-
Shared Memory
-
-
Shared Memory
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
TDP
Shared
TDP
Shared
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
Max Resolution
Unknown
Max Resolution
3840x2160
Max Resolution Refresh Rate
-
Max Resolution Refresh Rate
60Hz
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
Model
BigOcean
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
Codec
-
-
-
JPEG
-
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
Model
NVDEC 5
Model
BigOcean
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
Codec
-
-
-
JPEG
-
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
Direct X
12
Direct 3D
12_2
Direct X
12
Direct 3D
12_1
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
OpenGL
3.2
OpenCL
2.0
Vulkan
1.2
Shader Model
6.7
CUDA
8.7
-
-
PureVideo HD
VP11
VDPAU
Feature Set K
-
-
-
-
-
-
-
-
-
-
Not a Card
-
-
-
Not a Card
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Change Comparison