Qualcomm Adreno 642L vs NVIDIA GA10B 8SM
Qualcomm Adreno 642L
NVIDIA GA10B 8SM
|
512 Shaders
Shared Memory
550MHz
|
512 Shaders
Shared Memory
625MHz
|
|
Peak Performance
1.13 TFLOPS
FP16
|
Peak Performance
40.96 TOPS
INT4 Tensor Sparse
|
|
FP32
0.56 TFLOPS
|
FP32
0.64 TFLOPS
|
|
FP16
1.13 TFLOPS
|
FP16
1.28 TFLOPS
|
|
Form Factor
iGPU
-
|
Form Factor
iGPU
-
|
|
TDP
5W
|
TDP
Shared
|
|
-
-
-
-
-
|
-
-
-
-
-
|
|
GB6 OpenCL N/A
0%
|
|
|
GB6 Metal N/A
0%
|
GB6 Metal 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
Qualcomm
|
Manufacturer
NVIDIA
|
|
Chip Designer
Qualcomm
|
Chip Designer
NVIDIA
|
|
Architecture
Adreno 600
|
Architecture
Ampere
|
|
Family
Adreno 600
|
Family
Jetson
|
|
-
-
-
-
-
|
Codename
Hercules
GA10B
-
-
|
|
Market Segment
Mobile
|
Market Segment
Mobile
|
|
Release Date
5/19/2021
|
Release Date
1/1/2023
|
|
-
-
-
|
-
-
-
|
|
-
-
-
|
-
-
-
|
|
-
-
-
|
-
-
-
|
|
-
-
|
-
-
|
|
-
-
-
|
-
-
-
|
|
Form
iGPU
|
Form
iGPU
|
|
Shading Units
512 Shaders
-
|
Shading Units
512 Shaders
-
|
|
Texture Mapping Units
16 TMUs
|
Texture Mapping Units
4 TMUs
|
|
Render Output Units
8 ROPs
|
Render Output Units
8 ROPs
|
|
-
-
|
Tensor Cores
16 T-Cores
|
|
-
-
|
-
-
|
|
-
-
|
Streaming Multiprocessors
4 SMs
|
|
-
-
|
-
-
|
|
Execution Units
4 EUs
|
-
-
|
|
-
-
|
Graphics Processing Clusters
1 GPC
|
|
-
-
490MHz Base
550MHz
|
-
-
-
625MHz
|
|
Peak Performance
1.13 TFLOPS
FP16
|
Peak Performance
40.96 TOPS
INT4 Tensor Sparse
|
|
-
-
-
|
-
-
-
|
|
-
-
-
-
-
-
|
-
-
-
-
-
-
|
|
FP16
1.13 TFLOPS
-
-
-
-
|
FP16
1.28 TFLOPS
5.12 TFLOPS Tensor (FP16 Accumulate)
10.24 TFLOPS Tensor (FP16 Accumulate) Sparse
5.12 TFLOPS Tensor (FP32 Accumulate)
10.24 TFLOPS Tensor (FP32 Accumulate) Sparse
|
|
FP32
0.56 TFLOPS
-
-
|
FP32
0.64 TFLOPS
-
-
|
|
FP64
0.14 TFLOPS
-
|
-
-
-
|
|
-
-
-
-
|
BF16
-
5.12 TFLOPS Tensor
10.24 TFLOPS Tensor Sparse
|
|
-
-
-
|
TF32
2.56 TFLOPS Tensor
5.12 TFLOPS Tensor Sparse
|
|
-
-
-
|
INT4
20.48 TOPS Tensor
40.96 TOPS Tensor Sparse
|
|
-
-
-
-
|
INT8
-
10.24 TOPS Tensor
20.48 TOPS Tensor Sparse
|
|
INT32
0.28 TOPS
|
-
-
|
|
-
-
|
-
-
|
|
Pixel Fillrate
4.4 GPixel/s
|
Pixel Fillrate
5 GPixel/s
|
|
-
-
|
-
-
|
|
Texture Fillrate
8.8 GTexel/s
|
Texture Fillrate
2.5 GTexel/s
|
|
-
-
|
-
-
|
|
L1
2KB/SM Tex
-
-
-
|
L1
64KB/SM Tex
192KB/SM
-
-
|
|
L2
128KB Shared
|
L2
1MB Shared
|
|
L3
1024MB Shared
-
|
-
-
-
|
|
Shared Memory
-
-
|
Shared Memory
-
-
|
|
-
|
-
|
|
-
-
-
-
-
-
|
-
-
-
-
-
-
|
|
-
-
-
-
-
-
-
-
-
|
-
-
-
-
-
-
-
-
-
|
|
TDP
5W
|
TDP
Shared
|
|
-
-
|
-
-
|
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
|
|
Max Resolution
1920x1200
|
Max Resolution
Unknown
|
|
Max Resolution Refresh Rate
144Hz
|
Max Resolution Refresh Rate
-
|
|
Variable Refresh Rate
-
-
-
|
Variable Refresh Rate
G-Sync
FreeSync
-
|
|
Display Stream Compression (DSC)
Not Supported
|
Display Stream Compression (DSC)
Not Supported
|
|
Multi Monitor Support
1
|
Multi Monitor Support
Unknown
|
|
-
-
|
-
-
|
|
Model
Hexagon 770
|
Model
NVENC 7
|
|
Codec
-
-
MPEG-4
-
VC-1
VP8
VP9
H.263
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
|
Model
Hexagon 770
|
Model
NVDEC 5
|
|
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
|
Direct X
12
Direct 3D
12_1
|
Direct X
12
Direct 3D
12_2
|
|
OpenGL
3.2
OpenCL
2.0
Vulkan
1.1
|
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
-
-
-
|
|
-
-
-
-
-
-
-
-
|
-
-
-
-
-
-
-
-
|
|
-
-
-
-
-
-
|
-
-
-
-
-
-
|
|
-
-
-
-
|
-
-
-
-
|
|
-
-
-
-
-
-
|
-
-
-
-
-
-
|
Copy Link