News Intel GPUs - Battlemage officially announced, evidently not cancelled

Page 187 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Aapje

Golden Member
Mar 21, 2022
1,470
2,034
106
We need to wait for benchmarks but it's a seriously impressive uplift. And also seems like they vastly improved perf/W and Ray-Tracing performance.

It's relatively easy to get a big boost, when they were so far away from the state of the art. And they have to make a big jump to be able to get to a situation where they can actually earn money with it, within a reasonable time frame.

Let's see if they can pull it off, by releasing on time and getting to a decent level with regards to performance/mm2 and performance/watt.
 

Ghostsonplanets

Senior member
Mar 1, 2024
569
963
96
The more I read about Xe², the more I think Intel has finally gotten high performance graphics right and shed a lot of decisions/ways of doing things that were legacy from the Xe LP integrated base. Xe² adds native 64-bit support, hardware indirect execution, change to SIMD16, no more lockstep XVE but rather a single, fat XVE, increased performance of the fixed function units. Probably also fix the memory controller issues too.

While also vastly increasing perf/W and absolute performance. I actually expect to be some cases where Xe² BMG irrealistically outclasses Xe¹ ACM due to fixing so much things.

TAP demo of LNL BMG iGP running F1 2024 on High XeSS 1080p Performance with RT Shadows enabled at >60+ FPS was really exciting.
 

gdansk

Platinum Member
Feb 8, 2011
2,500
3,401
136
It is looking good though and that's irrespective of Alchemist being ... not good.
 

DavidC1

Senior member
Dec 29, 2023
433
618
96
Ha, looks like Intel is doing the underhype, overdeliver. Xe2 now sounds good.

Nice to see suspicions of compatibility and performance issues possibly due to being flaws in design being confirmed. SIMD16 in architecture mentioned straightup for improving compatibility is awesome. Meaning driver development will become faster, because they don't need to write code to explicitly support every game.
 

DavidC1

Senior member
Dec 29, 2023
433
618
96
The Xe-cores in Xe2 have been improved for higher performance, better utilisation, and greater compatibility with games. That last point is particularly important, going off Intel's previous form.
These changes take various forms, though I'm told it's not only improvements to the software stack, but changes to the silicon itself to make it gel more easily with modern games.

There's hardware support for commonly used commands, such as execute indirect, which causes headaches and slows performance on Alchemist. Another command, Fast Clear, is now supported in the Xe2 hardware, rather than having to be emulated in software as it was on Alchemist.
Another is execute indirect support baked into the hardware, via the Command Front End, which is a command used commonly in game engines, including Unreal Engine 5. This was previously emulated in software on Alchemist, which led to slowdown
The Xe2 architecture's Render Slice includes improvements to deliver 3x mesh shading performance, 3x vertex fetch throughput, and 2x throughput for sampling without filtering. Bandwidth requirements should be lower, and commands are more in line with what games often use.
-Ray Tracing Unit width increases from 2 traversal pipelines to 3.
 
Last edited:

KompuKare

Golden Member
Jul 28, 2009
1,089
1,146
136
Ha, looks like Intel is doing the underhype, overdeliver. Xe2 now sounds good.

Nice to see suspicions of compatibility and performance issues possibly due to being flaws in design being confirmed. SIMD16 in architecture mentioned straightup for improving compatibility is awesome. Meaning driver development will become faster, because they don't need to write code to explicitly support every game.
Yet at release time, weren't the driver team thrown under the bus by the hardware team!?

That Intel were going to have an enormous task sorting out their drivers after decades of neglect was a given. Handicapping the driver team because of hardware faults and potentially having wasted the driver teams time as hardware kept promising that X or Y would work at release? That must have been tough.

The part-time Intel watchers here and elsewhere have long suspected that Intel is large enough for plenty of internal politics - and when the driver team was to blame stories came out I suspected the hardware team of playing deflection politics!
 

blckgrffn

Diamond Member
May 1, 2003
9,206
3,196
136
www.teamjuchems.com
Yet at release time, weren't the driver team thrown under the bus by the hardware team!?

That Intel were going to have an enormous task sorting out their drivers after decades of neglect was a given. Handicapping the driver team because of hardware faults and potentially having wasted the driver teams time as hardware kept promising that X or Y would work at release? That must have been tough.

The part-time Intel watchers here and elsewhere have long suspected that Intel is large enough for plenty of internal politics - and when the driver team was to blame stories came out I suspected the hardware team of playing deflection politics!

The number of tasks that were essentially being run on software that was emulating hardware in the driver was interesting bits. I wish we knew how that compared to the strategies of the other two GPU makers so we could judge if this was abnormal or par for the course. I've heard nvidia is OK leaving more to software in their drivers while AMD took a more aggressive hardware approach but I don't know what that actually means compared to the decisions Intel made in the past and are making now.
 
  • Like
Reactions: Tlh97 and KompuKare
Jun 4, 2024
116
146
71
Ha, looks like Intel is doing the underhype, overdeliver. Xe2 now sounds good.

Nice to see suspicions of compatibility and performance issues possibly due to being flaws in design being confirmed. SIMD16 in architecture mentioned straightup for improving compatibility is awesome. Meaning driver development will become faster, because they don't need to write code to explicitly support every game.
I hope that’s what’s happening across their entire product portfolio. Under promised over deliver consistently. They have to do this to regain confidence.
 
  • Like
Reactions: igor_kavinski

Ghostsonplanets

Senior member
Mar 1, 2024
569
963
96
-Ray Tracing Unit width triples from 2 traversal pipelines to 3.
- "Back in the day we were DX compliant, which turns out to not quite be enough. You need to be similar to the dominant architecture. And that's the direction that we're heading with Xe."

Interesting quote. I'm not sure how much TAP is driving Intel Graphics, but he does seems to be heading them into the right direction.

Xe LP kinda seemed like an amalgamation of Intel GPU IP + some Vega esque design thinking (Not surprising given Raja). But turns out that the Xe LP/Gen12 foundation block for Alchemist was terrible for HPG and software work.

Battlemage seems a much simpler thing and aligned to others IHV designs. While also correcting a lot of Alchemist flaws. Good stuff all around.

It's also good that Intel is fast tracking new graphics IP for their Mobile line-up with Lunar and Panther Lake instead of reusing Alchemist LPG for years.
 

Ghostsonplanets

Senior member
Mar 1, 2024
569
963
96
Sounds like we will see SIMD32 for Xe3.
SIMD32, alongside Gen13 new uArch, would certainly explain why PTL U is only 32 XVE.

IMO the plan is probably to match the previous generation peak performance in the U series but using much less area to do so. And the H series gets a wider GPU to keep up the 2x gains gen on gen while also creeping up into the Nvidia xx50 performance.
 
Jul 27, 2020
18,213
11,919
116
I've heard nvidia is OK leaving more to software in their drivers
Sounds about right since their GPUs are more CPU-limited due to greater driver overhead. It also says something about their expectation that someone buying their GPUs would not pair them with slow CPUs.
 

DAPUNISHER

Super Moderator CPU Forum Mod and Elite Member
Super Moderator
Aug 22, 2001
28,887
21,774
146
When reviewers are showing Battle Mage running faster and looking better than the AMD APUs with some light ray tracing loads and XeSS, it is going to seriously move the needle. AMD has been coasting for far too long with APUs. They won't be able to get away with the 6yrs+ of Vega anymore. Real competition is finally here from the looks of it.

Best part is, it should trigger a price war with AMD in every space except high end cards. Nvidia has basically abandoned the space. Where Nvidia is concerned: The RTX 3050 may be the last time they get away with a crap offering in the lower price range. Where it has consistently outsold the competition on name and feature set, despite poor price to performance. Intel B series ray tracing and XeSS may turn out to be the combo breaker.
 

ToTTenTranz

Member
Feb 4, 2021
110
165
86
AMD has been coasting for far too long with APUs. They won't be able to get away with the 6yrs+ of Vega anymore. Real competition is finally here from the looks of it.

The decision to forego LLC completely in Strix Point's iGPU seems to have been a terrible one. Strix Halo can still be very interesting, but Point seems meh for everyone but those making proper use of 12 cores.
 

GodisanAtheist

Diamond Member
Nov 16, 2006
7,074
7,503
136
The decision to forego LLC completely in Strix Point's iGPU seems to have been a terrible one. Strix Halo can still be very interesting, but Point seems meh for everyone but those making proper use of 12 cores.

-I've always been perplexed by AMD's unwillingness to add IC to their APUs. Figure it would have an outsized effect in the most bandwidth constrained scenarios.

Guess we'll start seeing IC after AMD's apu's get squeezed by Intel.