Intel’s tGPU Delays Mass Production to Late 2023 for Meteor Lake CPUs Using TSMC’s 3nm Node

Intel's tGPU For Meteor Lake CPUs That Utilizes TSMC's 3nm Node Has Mass Production Delayed To Late 2023 1
Written by admin

in a report published by TrendForceWe’re getting our second confirmation that Intel’s tGPU for 14th Gen Meteor Lake CPUs, which is expected to use TSMC’s 3nm process node, has been delayed until late 2023 for mass production.

Intel’s 3nm tGPU Mass Production Delay Holds TSMC, 14th Gen Meteor Lake Postponed to Late 2023?

It was previously rumored that Intel could push its 14th Gen Meteor Lake CPUs to late 2023, and it looks like we’re getting similar reports from Trendforce sources close to Taiwanese chipmaker TSMC. Intel is reportedly planning mass production of the tGPU (Tiled GPU) initially featured in 14th Gen Meteor Lake CPUs starting in the second half of 2022. This was later delayed to the first half of 2023 due to product design and process. validation issues, but now we may be looking at even more lag.

According to TrendForce research, Intel plans to outsource the tGPU chipset in Meteor Lake to TSMC for production. Mass production of this product was originally scheduled for 2H22 but was later delayed to 1H23 due to product design and process validation issues. Recently, the product’s mass production schedule has been delayed to the end of 2023 for some reason, overnight completely canceling the 3nm production capacity reserved in 2023 with only a marginal amount of wafer input for engineering verification.

However, the development status of Intel’s own Intel 4 process and accompanying outsourcing are still important potential growth factors for TSMC. If Intel 4 fails to mass-produce as planned, Intel can strongly support growth in 2024 by outsourcing compute boxes to TSMC. However, if the Intel process goes smoothly, there is a possibility that the company chooses to manufacture the relevant products itself and cancels it. TSMC’s orders.

via TrendForce

According to the latest data, TSMC may not start mass production on Intel’s 3nm tGPU until the end of 2023. Similar things were said in a report by Digitimes last month. Intel CEO Pat Gelsinger he visited TSMC Fixing the outsourcing plan with the Taiwanese chipmaker, of course. Since Intel is a large 3nm customer, a delay could potentially hurt TSMC and slow it down. While there are other big vendors for 3nm like Apple, AMD, and Qualcomm, their products aren’t expected to start production until 2024.

It is also emphasized that if Intel’s own “Intel 4” compute node may experience some problems and cannot produce a suitable volume for Meteor Lake CPUs, Chipzilla may reconsider outsourcing other IPs such as Compte Tile to TSMC. This could help TSMC drive revenue even further, but according to Intel’s latest claims, it seems like progress is being made in the on-premises process nodes and showing good results, but we’ll see as we head into 2023.

With Raptor Lake in the second half of this year and Meteor Lake in 2023, we develop the Alder Lake leadership and exemplify how our innovative design decisions can drive leadership performance even before we re-establish best-in-class transistor technology.

And in 2023, we’ll be delivering the first decomposed CPU built on Intel 4, Meteor Lake, which shows it’s doing well in both our and our customers’ labs.

Yes. Maybe while we’re fast past five nodes, Intel 7 complete, bulk shipments, five nodes, four years, we said Intel 7, 35 million units, you can go and smash one. I’m sure our competitors shed tears over this, okay. Intel 4, okay, we said, hey, Meteor Lake looks good at this point.

Intel CEO Pat Gelsinger (Q2 2022 Earnings Call)

The tGPU will be one of the main components of 14th Gen Meteor Lake CPUs with Arc graphics architecture to put Intel on par with AMD’s and Apple’s embedded GPU solutions. platform details recently leaked For Meteor Lake CPUs, it confirmed that consumer launch is expected in the second half of 2023.

Intel Mobility CPU Series:

CPU Family Meteor Lake Raptor Lake Kizilagac Lake
Compute Node Intel 4 ‘7nm EUV’ Intel 7 ’10nm ESF’ Intel 7 ’10nm ESF’
CPU Architecture Hybrid (Triple Core) Hybrid (Dual Core) Hybrid (Dual Core)
P-Core Architecture Sequoia Cove Raptor Cove put gold
E-Core Architecture Crestmont gracemont gracemont
Best Configuration 6+8 (H-Series) 6+8 (H-Series) 6+8 (H-Series)
Max Cores/Threads 14/20 14/20 14/20
Scheduled Squad H/P/U Series H/P/U Series H/P/U Series
GPU Architecture Xe2 Battlemage ‘Xe-LPG’ Iris Xe (Gen 12) Iris Xe (Gen 12)
GPU Execution Units 128 EU (1024 Cores) 96 EU (768 Cores) 96 EU (768 Cores)
Memory Support DDR5-5600
LPDDR5X – 7400+
Memory Capacity (Max) 96GB 64GB 64GB
Thunderbolt 4 Port 4 2 2
WiFi Capability Wi-Fi 6E Wi-Fi 6E Wi-Fi 6E
TDP 15-45W 15-45W 15-45W
Start 2H 2023 1H 2023 1H 2022

About the author


Leave a Comment