NVIDIA GA10B 16SM 625MHz vs Intel Graphics 64EU 1250MHz Full Specs

Summary

1,024 Shaders 625MHz	512 Shaders 1.25GHz
Shared Memory68.3GB/sLPDDR5	Shared Memory83.2GB/s DDR5·LPDDR5·LPDDR4X·DDR4
Peak·FP32·FP16 1.28 TFLOPS	Peak·FP32·FP16 1.28 TFLOPS
Form Factor iGPU	Form Factor iGPU
TDP Shared	TDP Shared

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse FP64 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth

GA10B 16SM 625MHz81.92 TOPSINT4 Tensor Sparse

x32.00

Graphics 64EU 1250MHz2.56 TFLOPSFP16

x1

Show Top Score

Theoretical Performance

Clock Speed625MHz UC·Boost·OC	Clock Speed1250MHz UC·Base·Boost·OC
Peak OPS 81.92 TOPSINT4 Tensor Sparse	Peak OPS 2.56 TFLOPSFP16
Tensor FP16-16 10.24 TFLOPS FP16-16 Tensor Sparse 20.48 TFLOPS Tensor FP16-32 10.24 TFLOPS FP16-32 Tensor Sparse 20.48 TFLOPS	-
Tensor BF16 10.24 TFLOPS BF16 Tensor Sparse 20.48 TFLOPS	-
Tensor TF32 5.12 TFLOPS	Tensor TF32 -
FP32 1.28 TFLOPS	FP32 1.28 TFLOPS
-	FP64 320 GFLOPS
Tensor INT4 40.96 TOPS	Tensor INT4 -
Tensor INT8 20.48 TOPS	-
Pixel Rate 10 GPixel/s	Pixel Rate 20 GPixel/s
Texture Rate 5 GTexel/s	Texture Rate 40 GTexel/s

Core Config

Shaders 1,024 Shaders	Shaders 512 Shaders
TMUs 8 TMUs	TMUs 32 TMUs
ROPs 16 ROPs	ROPs 16 ROPs
Tensor Cores 32 T-Cores	Tensor Cores -
SMs 8 SMs	EUs 64 EUs

Clocks

Base Clock -	Base Clock 300MHz
Boost Clock 625MHz	Boost Clock 1.25GHz

Cache

L2 Cache 2MB shared	L2 Cache 512KB shared
L3 Cache -	L3 Cache 2MB shared

Memory

Shared MemoryLPDDR5	Shared Memory DDR5·LPDDR5·LPDDR4X·DDR4
Memory Bus 128-bit	Memory Bus 128-bit
Memory Speed 4.3GT/s	Memory Speed 5.2GT/s
Memory Bandwidth 68.3GB/s	Memory Bandwidth 83.2GB/s
ECC No	ECC No

Video Output

Multi-Monitor -

Multi-Monitor 4

Encoder

Encoder Model NVENC 7

Encoder Model Quick Sync Video 8

Decoder

Decoder Model NVDEC 5

Decoder Model Quick Sync Video 8

Card

Form Factor iGPU

Form Factor iGPU

Chip

Manufacturer NVIDIA	Manufacturer Intel
Chip Designer NVIDIA	Chip Designer Intel
Architecture Ampere	Architecture Gen 12
Family Jetson	Family Gen 12
Branding	Branding
Codename Hercules	Codename Xe LP
Chip Variant -	Chip Variant GT1
Market Segment Embedded	Market Segment Laptop
Release Date Jan 1, 2023	Release Date Jan 8, 2024

Fabrication

Foundry Samsung	Foundry Intel
Fabrication Node 8N	Fabrication Node Intel 7
Die Size -	Die Size 161mm²
Transistor Count 17 Billion	Transistor Count 11.9 Billion
Transistor Density -	Transistor Density 74 MTr/mm²

Images

No images available

No images available

Used In

CPUs Orin Nano 8GB	CPUs Core 3 100U Core 3 100UL
Laptops -	Laptops Inspiron 14 2-in-1(7440, Early 2024)

Competitors

NVIDIAGA10B 16SM 625MHz vs GPU Apple5-Core A18 Pro NVIDIAGA10B 16SM 625MHz vs GPU Apple8-Core M5-FL NVIDIAGA10B 16SM 625MHz vs GPU Apple9-Core M4-FL Show 12 more

IntelGraphics 64EU 1250MHz vs GPU Apple4-Core A16 IntelGraphics 64EU 1250MHz vs GPU Apple4-Core A18 IntelGraphics 64EU 1250MHz vs GPU Apple4-Core A19 Show 12 more