Intel Graphics 80EU 1450MHz vs NVIDIA GA10B 32SM Full Specs

Summary

640 Shaders 1.45GHz	2,048 Shaders 1.3GHz
Shared Memory83.2GB/s DDR5·DDR4	Shared Memory204.8GB/sLPDDR5
Peak·FP32·FP16 1.86 TFLOPS	Peak·FP32·FP16 5.33 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

Graphics 80EU 1450MHz3.71 TFLOPSFP16

x1

GA10B 32SM340.8 TOPSINT4 Tensor Sparse

x91.81

Show Top Score

Theoretical Performance

Clock Speed1450MHz UC·Boost·OC	Clock Speed1300MHz UC·Boost·OC
Peak OPS 3.71 TFLOPSFP16	Peak OPS 340.8 TOPSINT4 Tensor Sparse
-	Tensor FP16-16 42.6 TFLOPS FP16-16 Tensor Sparse 85.2 TFLOPS Tensor FP16-32 42.6 TFLOPS FP16-32 Tensor Sparse 85.2 TFLOPS
-	Tensor BF16 42.6 TFLOPS BF16 Tensor Sparse 85.2 TFLOPS
Tensor TF32 -	Tensor TF32 21.3 TFLOPS
FP32 1.86 TFLOPS	FP32 5.33 TFLOPS
FP64 464 GFLOPS	-
Tensor INT4 -	Tensor INT4 170.4 TOPS
-	Tensor INT8 85.2 TOPS
Pixel Rate 29 GPixel/s	Pixel Rate 41.6 GPixel/s
Texture Rate 58 GTexel/s	Texture Rate 20.8 GTexel/s

Core Config

Shaders 640 Shaders	Shaders 2,048 Shaders
TMUs 40 TMUs	TMUs 16 TMUs
ROPs 20 ROPs	ROPs 32 ROPs
Tensor Cores -	Tensor Cores 64 T-Cores
EUs 80 EUs	SMs 16 SMs

Clocks

Boost Clock 1.45GHz

Boost Clock 1.3GHz

Cache

L2 Cache 896KB shared	L2 Cache 4.1MB shared
L3 Cache 3MB shared	L3 Cache -

Memory

Shared Memory DDR5·DDR4	Shared MemoryLPDDR5
Memory Bus 128-bit	Memory Bus 256-bit
Memory Speed 5.2GT/s	Memory Speed 6.4GT/s
Memory Bandwidth 83.2GB/s	Memory Bandwidth 204.8GB/s
ECC No	ECC No

Video Output

Multi-Monitor 4

Multi-Monitor -

Encoder

Encoder Model Quick Sync Video 8

Encoder Model NVENC 7

Decoder

Decoder Model Quick Sync Video 8

Decoder Model NVDEC 5

Card

Form Factor iGPU

Form Factor iGPU

Chip

Manufacturer Intel	Manufacturer NVIDIA
Chip Designer Intel	Chip Designer NVIDIA
Architecture Gen 12	Architecture Ampere
Family Gen 12	Family Jetson
Branding	Branding
Codename Xe LP	Codename Hercules
Chip Variant GT1	Chip Variant -
Market Segment Laptop	Market Segment Embedded
Release Date Jan 8, 2024	Release Date Jan 1, 2021

Fabrication

Foundry Intel	Foundry Samsung
Fabrication Node Intel 7	Fabrication Node 8N
Die Size 208mm²	Die Size -
Transistor Count 15.2 Billion	Transistor Count 17 Billion
Transistor Density 73 MTr/mm²	Transistor Density -

Images

No images available

No images available

Used In

CPUs Core 5 120HL

CPUs AGX Orin 64GB

Competitors

IntelGraphics 80EU 1450MHz vs GPU AMDRadeon 860M 3000MHz IntelGraphics 80EU 1450MHz vs GPU Apple5-Core A19 Pro IntelGraphics 80EU 1450MHz vs GPU Apple5-Core A19 Show 12 more

NVIDIAGA10B 32SM vs GPU Apple16-Core M5 Pro NVIDIAGA10B 32SM vs GPU Apple20-Core M5 Pro NVIDIAGA10B 32SM vs GPU IntelArc B370 2400MHz Show 10 more