Intel Meteor Lake GPU Offers Anywhere Between GTX 1650 Ti To RTX 3050 Level of Performance

By: Hassan Mujtaba

Intel’s Meteor Lake GPU will drop the need for a discrete graphics chip on entry-level laptops as it will deliver great performance with higher battery times.

Intel Meteor Lake GPU May Offer Up To RTX 3050 Performance At Just 45W, Thin & Light Laptops With Higher Battery Times

As a part of his latest video, Moore’s Law is Dead also shared an alleged AMD Internal presentation for Q4 2022 which compared the graphics performance of its upcoming integrated graphics with a range of NVIDIA discrete solutions. The slides also show the projection of Intel’s Meteor Lake iGPU and put it behind the Phoenix 45W solution though that has changed and the Meteor Lake Xe-LPG GPU is now projected to deliver much better performance.

The slide shows the AMD Radeon 780M GPU featured on Phoenix APUs with 12 RDNA 3 Compute Units at 45W sitting ahead of the NVIDIA GeForce GTX 1650 (50W). The Strix Point APUs have also been shown here which offer faster than NVIDIA GeForce RTX 3050 (35W) performance with RDNA 3+ GPUs configured with 16 Compute Units at 45W.

Image Credits: Moore’s Law is Dead

Initially, the Intel Meteor Lake GPU which features the Xe-LPG Alchemist architecture, the same as the Arc GPUs, was said to end up behind the Phoenix RDNA 3 APU however it looks like the Meteor Lake chip is much more powerful and can deliver performance anywhere between the NVIDIA GTX 1650 Ti and the RTX 3050 at 45W. The Intel Meteor Lake Xe-LPG GPU will feature a new tiled design and incorporate up to 128 Execution Units. The GPU tile will be fabricated on the TSMC 5nm node and early leaks have shown it to be clocking up to 2.1 GHz and delivering over 4 TFLOPs of compute horsepower.

These GPUs will have two configurations, a 64 EU (MTL GT2) and 128 EU (MTL GT3) design. These will also enable enhanced support for DirectX 12 Ultimate & XeSS, features that are only supported by the Alchemist lineup as of right now. Intel will also be using its brand new Adamantine L4 cache starting with Meteor Lake GPUs which will definitely give a nice boost to the GPUs. Overall, having an integrated GPU of this level would mean that laptop manufacturers can enable cheaper designs with far better battery times compared to those with discrete GPUs.

Now we can’t say how well these GPUs will perform in gaming benchmarks since the performance here is only measured within 3DMark Fire Strike and synthetics aren’t the best way to showcase a true gaming scenario. AMD’s RDNA 3 GPUs are offering some great numbers in several AAA titles and they have yet to receive proper driver support so expect more information from Intel about the true capabilities of its Xe-LPG GPUs soon.

Intel’s Meteor Lake chips will be landing soon as they are planned to launch in Q4 2023. Intel has a Vision event happening this month so expect more information during that.

Intel Mobility CPU Lineup:

CPU Family Arrow Lake Meteor Lake Raptor Lake Alder Lake
Process Node (CPU Tile) Intel 20A ‘5nm EUV” Intel 4 ‘7nm EUV’ Intel 7 ’10nm ESF’ Intel 7 ’10nm ESF’
Process Node (GPU Tile) TSMC 3nm TSMC 5nm Intel 7 ’10nm ESF’ Intel 7 ’10nm ESF’
CPU Architecture Hybrid (Four-Core) Hybrid (Triple-Core) Hybrid (Dual-Core) Hybrid (Dual-Core)
P-Core Architecture Lion Cove Redwood Cove Raptor Cove Golden Cove
E-Core Architecture Skymont Crestmont Gracemont Gracemont
Top Configuration TBD 6+8 (H-Series) 6+8 (H-Series)
8+16 (HX-Series)
6+8 (H-Series)
8+8 (HX-Series)
Max Cores / Threads TBD 14/20 14/20 14/20
Planned Lineup H/P/U Series H/P/U Series H/P/U Series H/P/U Series
GPU Architecture Xe2 Battlemage ‘Xe-LPG’
Xe3 Celestial “Xe-LPG”
Xe-LPG ‘Xe-MTL’ Iris Xe (Gen 12) Iris Xe (Gen 12)
GPU Execution Units 192 EUs (1024 Cores)? 128 EUs (1024 Cores) 96 EUs (768 Cores) 96 EUs (768 Cores)
Memory Support TBD DDR5-5600
LPDDR5X – 7400+
Memory Capacity (Max) TBD 96 GB 64 GB 64 GB
Thunderbolt 4 Ports TBD 4 4 4
WiFi Capability TBD WiFi 6E WiFi 6E WiFi 6E
TDP TBD 15-45W 15-55W 15-55W
Launch 2H 2024? 2H 2023 1H 2023 1H 2022

Written by Hassan Mujtaba