NVIDIA GA10B 16SM 918MHz vs 5-Core A18

NVIDIA GA10B 16SM 918MHz
5-Core A18
1024 Shaders
Shared Memory
918MHz
640 Shaders
Shared Memory
1450MHz
Peak Performance
120.32 TOPS
INT4 Tensor Sparse
Peak Performance
1.86 TFLOPS
FP16
FP32
1.88 TFLOPS
FP32
1.86 TFLOPS
FP16
3.76 TFLOPS
FP16
1.86 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
Apple
Chip Designer
NVIDIA
Chip Designer
Apple
Architecture
Ampere
Architecture
Apple Gen 7
Family
Jetson
Family
A Series
Codename
Hercules
GA10B
-
-
Codename
G17P
A18
-
-
Market Segment
Mobile
Market Segment
Mobile
Release Date
12/1/2022
Release Date
9/9/2024
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Form
iGPU
Form
iGPU
Shading Units
1024 Shaders
-
Shading Units
640 Shaders
-
Texture Mapping Units
8 TMUs
Texture Mapping Units
40 TMUs
Render Output Units
16 ROPs
Render Output Units
20 ROPs
Tensor Cores
32 T-Cores
-
-
-
-
Ray-Tracing Cores
5 RT-Cores
Streaming Multiprocessors
8 SMs
-
-
-
-
-
-
-
-
Execution Units
80 EUs
Graphics Processing Clusters
1 GPC
Graphics Processing Clusters
5 GPCs
-
-
-
918MHz
-
-
-
1450MHz
Peak Performance
120.32 TOPS
INT4 Tensor Sparse
Peak Performance
1.86 TFLOPS
FP16
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
FP16
3.76 TFLOPS
15.04 TFLOPS Tensor (FP16 Accumulate)
30.08 TFLOPS Tensor (FP16 Accumulate) Sparse
15.04 TFLOPS Tensor (FP32 Accumulate)
30.08 TFLOPS Tensor (FP32 Accumulate) Sparse
FP16
1.86 TFLOPS
-
-
-
-
FP32
1.88 TFLOPS
-
-
FP32
1.86 TFLOPS
-
-
-
-
-
-
-
-
BF16
-
15.04 TFLOPS Tensor
30.08 TFLOPS Tensor Sparse
-
-
-
-
TF32
7.52 TFLOPS Tensor
15.04 TFLOPS Tensor Sparse
-
-
-
INT4
60.16 TOPS Tensor
120.32 TOPS Tensor Sparse
-
-
-
INT8
-
30.08 TOPS Tensor
60.16 TOPS Tensor Sparse
-
-
-
-
-
-
-
-
-
-
-
-
Pixel Fillrate
14.688 GPixel/s
Pixel Fillrate
29 GPixel/s
-
-
-
-
Texture Fillrate
7.344 GTexel/s
Texture Fillrate
58 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
1
-
-
-
-
Model
NVENC 7
Model
Apple Media Engine 3
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
ProRes
ProRes Raw
Model
NVDEC 5
Model
Apple Media Engine 3
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
AV1
ProRes
ProRes Raw
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