[HN Gopher] Raytracing on Intel's Arc B580
       ___________________________________________________________________
        
       Raytracing on Intel's Arc B580
        
       Author : rbanffy
       Score  : 80 points
       Date   : 2025-03-16 12:01 UTC (10 hours ago)
        
 (HTM) web link (chipsandcheese.com)
 (TXT) w3m dump (chipsandcheese.com)
        
       | im_down_w_otp wrote:
       | I love these breakdown writeups so much.
       | 
       | I'm also hoping that Intel puts out an Arc A770 class upgrade in
       | their B-series line-up.
       | 
       | My workstation and my kids' playroom gaming computer both have
       | A770's, and they've been really amazing for the price I paid,
       | $269 and $190. My triple screen racing sim has an RX 7900 GRE
       | ($499), and of the three the GRE has surprisingly been the least
       | consistently stable (e.g. driver timeouts, crashes).
       | 
       | Granted, I came into the new Intel GPU game after they'd gone
       | through 2 solid years of driver quality hell, but I've been
       | really pleased with Intel's uncharacteristic focus and pace of
       | improvement in both the hardware and _especially_ the software. I
       | really hope they keep it up.
        
         | 999900000999 wrote:
         | I have a couple of these too, and I strongly believe Intel is
         | effectively subsidizing these to try to get a foothold in the
         | market.
         | 
         | You get me equivalent of a $500 Nvidia card for around $300 or
         | less. And it makes sense because Intel knows if they can get a
         | foothold in this market they're that much more valuable to
         | shareholders.
         | 
         | Great for gaming, no real downsides imo.
        
           | DeepSeaTortoise wrote:
           | They should drop a $600 card with 128gb of vram. This is just
           | barely possible without losses on every sale.
           | 
           | And then just watch heads explode.
        
             | ryao wrote:
             | At current market pricing on dramexchange, 128GB of 16Gbit
             | GDDR6 chips would cost $499.58. That only leaves $100.42
             | for the PCB, GPU die, miscellaneous parts, manufacturing,
             | packaging, shipping, the store's margin, etcetera. I
             | suspect that they could not do that without taking a loss.
             | 
             | I wonder if they could mix clamshell mode and quadrank to
             | connect 64 memory chips to a GPU. If they connected 128GB
             | of VRAM to a GPU, I would expect then to sell it for $2000,
             | not $600.
        
               | DeepSeaTortoise wrote:
               | Yup, just went with the $3 per GB formula.
               | 
               | GPU should be about $200 at TSMC (400-450mm2).
               | 
               | + about $150 for the pcb, cooler and other stuff, I
               | didn't consider
               | 
               | Times a 1.6 to 1.75 factor if they like actually being
               | profitable (operations, rnd, sales, marketing, ...).
               | 
               | So about $1.5k, I guess.
               | 
               | Multiply that with a .33 "screw the competition" factor
               | and my initial guess is almost spot on.
               | 
               | .
               | 
               | Real problem:
               | 
               | The largest GDDR7 package money can buy right now is 3GB.
               | That's a 1376bit bus right there. GL fitting that to a
               | sub 500mm2 die.
               | 
               | In the future you could put that amount of vram on a
               | 512bit bus, tho.
               | 
               | Also normal DDR is getting really fast atm. 8 channel can
               | already challenge most vram configurations. Maybe it's
               | time soon to switch back to swappable memory.
        
               | rasz wrote:
               | >+ about $150 for the pcb, cooler and other stuff,
               | 
               | Assuming I had access to gerbers I could order replica of
               | 5090 PCB for $65, including shipping. Intel PCB is half
               | that. Again this is for a dude off the street buying 1-5
               | copies, not a bulk order.
        
           | ryao wrote:
           | They are definitely selling them at close to no profit, but
           | they are not anywhere near subsidizing them unless they
           | botched their supply chain so badly that they are overpaying
           | the BOM costs.
        
             | 999900000999 wrote:
             | R&D isn't free.
             | 
             | Even selling at cost is a subsidy.
             | 
             | I'm proud to support them. Intel is also selling their
             | lunar lake chips fairly cheaply too. Let's all hope they
             | make it through this rough patch. I can't imagine a world
             | where we only have one x86 manufacturer.
        
               | hypothesis wrote:
               | > I can't imagine a world where we only have one x86
               | manufacturer.
               | 
               | Does it even matter? Some people won't notice even if
               | there are zero x86 manufacturers.
               | 
               | In fact I would say lots of people have not bought x86
               | CPU in while, between Mac, RPi and risc-v boards...
        
               | 999900000999 wrote:
               | X86 is still needed for a lot of software. The emulation
               | just isn't there yet.
        
               | hypothesis wrote:
               | That would be news to people on mac with Rosetta Stone /
               | Crossover.
        
               | 999900000999 wrote:
               | A lot of server code and specialized software won't work.
               | 
               | Competition is always good
        
               | ryao wrote:
               | R&D is a sunk cost that is largely paid by their iGPUs.
               | Selling at cost is not a subsidy and that is not relevant
               | here since they should be making money off every sale. I
               | tried estimating their costs a few months ago and found
               | that they had room for up to a 10% margin on these, even
               | after giving retailers a 10% margin. If they are not
               | making money from these, it would be their fault for not
               | building enough to leverage economics of scale.
        
               | 999900000999 wrote:
               | https://slickdeals.net/f/17910114-acer-arc-a770-16gb-gpu-
               | w-f...
               | 
               | > Acer Arc A770 16gb GPU w/Free Game & Shipping $229.99
               | $229.99 $399.99 at Newegg
               | 
               | Sure that margin is holding when they had to mark the
               | first generation down to get them off the shelves. It
               | would truly surprise me if they've made a significant
               | profit off these cards.
        
         | throwaway48476 wrote:
         | They won't make a B770 or C770 because they lose money on every
         | card they sell. The prices are low because otherwise they would
         | sell 0 and they already paid for the silicon. The intel
         | graphics division is run by fools who won't give their cards a
         | USP in the SR-IOV feature home labers have been asking for for
         | years. Doing what AMD and Nvidia do but worse is not a
         | profitable strategy. There's a 50% the whole division gets
         | fired in the next year though.
        
           | gruez wrote:
           | >The intel graphics division is run by fools who won't give
           | their cards a USP in the SR-IOV feature home labers have been
           | asking for for years.
           | 
           | Intel are "fools" for not adding a feature that maybe a few
           | thousand people care about?
        
             | throwaway48476 wrote:
             | A few thousand people is a lot more than the number of
             | gamers who'd buy an Intel GPU at market price. If they
             | don't raise their ASP into the black they're going to ax
             | the whole division.
             | 
             | For reference the B580 die is nearly the size of the 4070
             | but sells for a third the price.
        
           | freddi333 wrote:
           | SR-IOV doesn't sell consumer cards, are you expecting Intel
           | to produce an expensive XEON equivalent of Arc? I'd expect
           | them to attempt capturing some LLM market share by loading up
           | the cards with RAM rather than expending effort on niche
           | features.
        
             | throwaway48476 wrote:
             | SR-IOV would sell more cards than Intel would be able to
             | sell if they charged market rate for their GPUs. Same goes
             | for not selling a local LLM high VRAM variant. Intel is
             | just allergic to competing by offering a USP.
             | 
             | AMD Ryzen CPUs have ECC enabled but not officially
             | supported. Intel still locks away the feature.
        
       | sergiotapia wrote:
       | Was raytracing a psyop by Nvidia to lock out amd? Games today
       | don't look that much nicer than 10 years ago and demand crazy
       | hardware. Is raytracing a solution looking for a problem?
       | 
       | https://x.com/NikTekOfficial/status/1837628834528522586
        
         | im_down_w_otp wrote:
         | I've kind of wondered about this a bit too. The respective
         | visual quality side of it that is. Especially in a context
         | where you're actually playing a game. You're not just sitting
         | there staring at side by side still frames looking for minor
         | differences.
         | 
         | What I have assumed given then trend, but could be completely
         | wrong about, is that the raytracing version of the world might
         | be easier on the software & game dev side to get great visual
         | results without the overhead of meticulous engineering, use,
         | and composition of different lighting systems, shader effects,
         | etc.
        
           | gmueckl wrote:
           | When path tracing works, it is much, much, MUCH simpler and
           | vastly saner algorithm than those stacks of 40+ complicated
           | rasterization hacks in current rasterization based renderers
           | that barely manage to capture crude approxinations of the
           | first indirect light bounces. Rasterization as a rendering
           | model for realistic lighting has outlived its usefulness. It
           | overstayed because optimizing ray-triangle intersection tests
           | for path tracing in hardware is a hard problem that took some
           | 15 o 20 years of research to even get to the first generation
           | RTX hardware.
        
             | gruez wrote:
             | >When path tracing works, it is much, much, MUCH simpler
             | and vastly saner algorithm than those stacks of 40+
             | complicated rasterization hacks in current rasterization
             | based renderers that barely manage to capture crude
             | approxinations of the first indirect light bounces.
             | 
             | It's ironic that you harp about "hacks" that are used in
             | rasterization, when raytracing is so computationally
             | intensive that you need layers upon layers of performance
             | hacks to get decent performance. The raytraced results
             | needs to be denoised because not enough rays are used. The
             | output of that needs to be supersampled (because you need
             | to render at low resolution to get acceptable performance),
             | and then on top of all of that you need to hallu^W
             | extrapolate frames to hit high frame rates.
        
               | 1W6MIC49CYX9GAP wrote:
               | Meanwhile raserization is fundamentally incapable of
               | producing the same image.
        
               | cubefox wrote:
               | And you still need rasterization for ray traced games
               | (even "fully" path traced games like Cyberpunk 2077)
               | because the ray tracing sample count is too low to result
               | in an acceptable image even after denoising. So the
               | primary visibility rendering is done via rasterization
               | (which has all the fine texture and geometry detail
               | without shading), and the ray traced (and denoised)
               | shading is layerd on top.
               | 
               | You can see the purely ray traced part in this image from
               | the post: https://substack-post-
               | media.s3.amazonaws.com/public/images/8...
               | 
               | This combination of techniques is actually pretty smart:
               | Combine the powers of the rasterization and ray tracing
               | algorithms to achieve the best quality/speed combination.
               | 
               | The rendering implementation in software like Blender can
               | afford to be primitive in comparison: It's not for real-
               | time animation, so they don't make use of rasterization
               | at all and do not even use denoising. That's why
               | rendering a simple scene takes seconds in Blender to
               | converge but only milliseconds in modern games.
        
             | juunpp wrote:
             | This doesn't hold at all. Path tracing doesn't "just work",
             | it is computational infeasible. It needs acceleration
             | structures, ray traversal scheduling, denoisers, upscalers,
             | and a million other hacks to work any close to real-time.
        
           | kmeisthax wrote:
           | For the vast majority of scenes in games, the best balance of
           | performance and quality is precomputed visibility, lighting
           | and reflections in static levels with hand-made model LoDs.
           | The old Quake/Half-Life bsp/vis/rad combo. This is unwieldy
           | for large streaming levels (e.g. open world games) and breaks
           | down completely for highly dynamic scenes. You wouldn't want
           | to build Minecraft in Source Engine[0].
           | 
           | However, that's not what's driving raytracing.
           | 
           | The vast majority of game development is "content pipeline" -
           | i.e. churning out lots of _stuff_ - and engine and graphics
           | tech is built around removing roadblocks to that content
           | pipeline, rather than presenting the graphics card with an
           | efficient set of draw commands. e.g. LoDs demand artists
           | spend extra time building the same model multiple times;
           | precomputed lighting demands the level designer wait longer
           | between iterations. That goes against the content pipeline.
           | 
           | Raytracing is Nvidia promising game and engine developers
           | that they can just forget about lighting and delegate that
           | entirely to the GPU at run time, at the cost of running like
           | garbage on anything that isn't Nvidia. It's entirely
           | impractical[1] to fully raytrace a game at runtime, but that
           | doesn't matter if people are paying $$$ for roided out space
           | heater graphics cards just for slightly nicer lighting.
           | 
           | [0] That one scene in _The Stanley Parable_ notwithstanding
           | 
           | [1] Unless you happen to have a game that takes place
           | entirely in a hall of mirrors
        
             | corysama wrote:
             | Yep. I worked on the engine of a PS3/360 AAA game long ago.
             | We spent a long of time building a pipeline for precomputed
             | lighting. But, in the end the game was 95% fully
             | dynamically lit.
             | 
             | For the artists, being able to wiggle lights around all
             | over in real time was an immeasurable productivity boost
             | over even just 10s of seconds between baked lighting
             | iterations. They had a selection of options at their
             | fingertips and used dynamic lighting almost all the time.
             | 
             | But, that came with a lot of restrictions and limitations
             | that make the game look dated by today's standards.
        
           | juunpp wrote:
           | Except that it isn't like that at all. All you get from the
           | driver in terms of ray tracing is the acceleration structure
           | and ray traversal. Then you have denoisers and upscalers
           | provided as third-party software. But games still ship with
           | thousands of materials, and it is up to the developer to
           | manage lights, shaders, etc, and use the hardware and driver
           | primitives intelligently to get the best bang for the buck.
           | Plus, given that primary rays are a waste of time/compute,
           | you're still stuck with G-buffer passes and rasterization
           | anyway. So now you have two problems instead of one.
        
         | Clemolomo wrote:
         | It's a transition happening.
         | 
         | Research and progress is necessary, Ray tracing is a clear
         | advancement.
         | 
         | AMD could just easily skip it if they want to reduce costs, we
         | could just not by the gpus. Non of it is happening.
         | 
         | It does look better and it would be a lot easier if we would
         | only do ray tracing
        
         | keyringlight wrote:
         | I think there's two ways of looking at it. Firstly that raster
         | has more or less plateaued, there haven't been any great
         | advances in a long time and it's not like AMD or any other
         | company have offered an alternative path or vision for where
         | they see 3d graphics going. The last thing a company like
         | nvidia wants is to be a generic good which is easy to compete
         | with or simple to compare against. Nvidia was also making use
         | of their strength/long term investment in ML to drive DLSS
         | 
         | Secondly, nvidia are a company that want to sell stuff for a
         | high asking price, and once a certain tech gets good enough
         | that becomes more difficult. If the 20 series was just a
         | incremental improvement from the 10, and so on then I expect
         | sales would have plateaued especially if game requirements
         | don't move much.
        
           | sergiotapia wrote:
           | I don't believe we have reached a raster ceiling. More and
           | more it seems like groups are cahoots to push rtx and ray
           | tracing. We are left to speculate why devs are doing this.
           | nvidiabux? easier time to add marketing keywords? who
           | knows... i'm not a game dev.
           | 
           | https://www.youtube.com/watch?v=NxjhtkzuH9M
        
             | gruez wrote:
             | There's no need for implications of deals between nvidia
             | and game developers in smoke filled rooms. It's pretty
             | straightforward: raytracing means less work for developers,
             | because they don't have to manually place lights to make
             | things look "right". Plus, they can harp about how it looks
             | "realistic". It's not any different than the explosion of
             | electron apps (and similar technologies making apps using
             | html/js), which might be fast to develop, but are bloated
             | and feel non-native. But it's not like there's an electron
             | corp, giving out "electronbux" to push app developers to
             | use electron.
        
             | phatfish wrote:
             | Raster quality is limited by how much effort engine
             | developers are willing to put into finding computationally
             | cheap approximations of how light/materials behave. But it
             | feels like the easy wins are already taken?
        
         | ThatPlayer wrote:
         | I don't think it's just about looks. The advantage of ray
         | tracing is the real time lighting done rather than the static
         | baked maps. One of the features I feel that was lost with
         | modern game lighting is dynamic environments. But as long as
         | the game isn't only ray tracing, these types of interactions
         | will stay disabled for the game. Teardown and The Finals are
         | examples of a dynamic environment game with raytraced lighting.
         | 
         | Another example is when was the last time you've seen a game
         | with a mirror that wasn't broken?
        
           | gruez wrote:
           | Hitman, GTA, both of which use a non-raytraced
           | implementation. More to the point, lack of mirrors doesn't
           | impact the gameplay. It's something that's trotted out as a
           | nice gimmick, 99% of the time it's not there, and you don't
           | really notice that it's missing.
        
             | ThatPlayer wrote:
             | GTA V's implementation did not work in their cars. Rear
             | view and side view mirrors in cars are noticeably low
             | quality and missing other cars while driving, which is
             | pretty big for gameplay purposes.
             | 
             | Working mirrors are limited to less complex scenes in GTA.
             | Hitman too I believe.
        
             | keyringlight wrote:
             | Hitman is an example that contradicts your point about
             | gameplay, guards will see you in mirrors and act
             | appropriately. They'll be doing that for gameplay with a
             | non-graphical method, but you need to show it to the player
             | graphically for them to appreciate the senses available
        
               | gruez wrote:
               | >Hitman is an example that contradicts your point about
               | gameplay, guards will see you in mirrors and act
               | appropriately.
               | 
               | See:
               | 
               | >It's something that's trotted out as a nice gimmick, 99%
               | of the time it's not there, and you don't really notice
               | that it's missing.
               | 
               | Yeah, it's a nice detail for the 1% of time that you're
               | in a bathroom or whatever, but it's not like the
               | immersion takes a hit when it's missing. Moreover because
               | the game is third person, you can't even accurately judge
               | whether you'll be spotted through a mirror or not.
        
         | davikr wrote:
         | lol, go play Cyberpunk 2077 with pathtracing and compare it to
         | raster before you call it a gimmick.
        
           | sergiotapia wrote:
           | i own an rtx 4090 and yes cyberpunk looks amazing with
           | raytracing - but worth the $2000k and nvidia monopoly over
           | the tech? a big resounding no (for me).
        
         | TiredOfLife wrote:
         | Here is a good video by Digital Foundry looking at Metro Exodus
         | Enhanced edition with devtools. Where they show what raytracing
         | is and how it differs from regular lighting.
         | 
         | https://youtu.be/NbpZCSf4_Yk
         | 
         | simplified tldr: with raytracing you build the environment,
         | designate which parts (like sun, lamps) emit light and you are
         | done. With regular an artist has to spend hours to days adding
         | many fake lightsources to get same result.
        
         | washadjeffmad wrote:
         | If you think of either crypto or gaming and not accelerated
         | compute for advanced modeling and simulation when you hear
         | Nvidia, you won't have sufficient perspective to answer this
         | question.
         | 
         | What does RTX do, what does it replace, and what does it
         | enable, for whom? Repeat for Physx, etc. Give yourself a bonus
         | point if you've ever heard of Nvidia Omniverse before right
         | now.
        
         | berkut wrote:
         | Not if you want better fidelity: the VFX industry for film
         | moved from rasterisation to raytracing / pathtracing (on CPU
         | initially, and a lot of final frame rendering is still done on
         | CPU due to memory requirements even today, although lookdev is
         | often done on GPU if the shaders / light transport algorithms
         | can be matched between GPU/CPU codepaths) due to the higher
         | fidelity possible starting back in around 2012/2013.
         | 
         | It required discarding a lot of "tricks" that had been learnt
         | with rasterisation to speed things up over the years, and made
         | things slower in some cases, but meant everything could use
         | raytracing to compute visibility / occlusion, rather than
         | having shadow maps, irradiance caches, pointcloud SSS caches,
         | which simplified workflows greatly and allowed high-fidelity
         | light transport simulations of things like volume scattering in
         | difficult mediums like water/glass and hair (i.e. TRRT lobes),
         | where rasterisation is very difficult to get the medium
         | transitions and LT correct.
        
         | shmerl wrote:
         | If suggested usage means upscaling, it's a dubious trade off.
         | That's why I'm not using it in Cyberpunk 2077, at least with
         | RDNA 3 on Linux, since I don't want to use upscaling.
         | 
         | Not sure how much RDNA 4 and on will improve it.
        
       | achierius wrote:
       | It feels like just yesterday that Chips and Cheese started
       | publishing (*checked and they started up in 2020 -- so not that
       | long ago after all!), and now they've really become a mainstay in
       | my silicon newsletter stack, up there with
       | Semianalysis/Semiengineering/etc.
       | 
       | > Intel uses a software-managed scoreboard to handle dependencies
       | for long latency instructions.
       | 
       | Interesting! I've seen this in compute accelerators before, but
       | both AMD and Nvidia manage their long-latency dependency tracking
       | in hardware so it's interesting to see a major GPU vendor taking
       | this approach. Looking more into it, it looks like the interface
       | their `send`/`sendc` instruction exposes is basically the same
       | interface that the PE would use to talk to the NOC: rather than
       | having some high-level e.g. load instruction that hardware then
       | translates to "send a read-request to the dcache, and when it
       | comes back increment this scoreboard slot", the ISA lets/makes
       | the compiler state that all directly. Good for fine control of
       | the hardware, bad if the compiler isn't able to make inferences
       | that the hardware would (e.g. based on runtime data), but then
       | good again if you really want to minimize area and so wouldn't
       | have that fancy logic in the pipeline anyways.
        
       | rayiner wrote:
       | This is so cool! I think this is a video of CyberPunk 2077 with
       | path tracing on versus off:
       | https://www.youtube.com/watch?v=89-RgetbUi0. It sees like a real,
       | next-generation advance in graphics quality that we haven't seem
       | in awhile.
        
         | vinkelhake wrote:
         | Just a heads up - it looks like the "Path Tracing Off" shots
         | have ray tracing disabled as well. In the shots starting at
         | 1:22 (the car and then the plaza), it looks like they just have
         | the base screenspace reflections enabled. Path tracing makes a
         | difference (sometimes big, sometimes small) for diffuse
         | lighting in the game. The kind of reflection seen in those
         | scenes can be had by enabling "normal" ray tracing in the game,
         | which is playable on more systems.
        
       | api wrote:
       | Intel Arc could be Intel's comeback if they play it right. AMD's
       | got the hardware to disrupt nVidia but their software sucks and
       | they have a bad reputation for that. Apple's high-end M chips are
       | good but also expensive like nVidia (and sold only with a high-
       | end Mac) and don't quite have the RAM bandwidth.
        
         | blagie wrote:
         | Intel is close. Good history with software.
         | 
         | If they started shipping GPUs with more RAM, I think they'd be
         | in a strong position. The traditional disruption is to eat the
         | low-end and move up.
         | 
         | Silly as it may sound, but a Battlemage where one can just plug
         | in DIMMs, with some high total limit for RAM, would be the
         | ultimate for developers who just want to test / debug LLMs
         | locally.
        
           | userbinator wrote:
           | _Silly as it may sound, but a Battlemage where one can just
           | plug in DIMMs, with some high total limit for RAM, would be
           | the ultimate for developers who just want to test / debug
           | LLMs locally._
           | 
           | Reminds me of this old satire video:
           | https://www.youtube.com/watch?v=s13iFPSyKdQ
        
           | throwaway48476 wrote:
           | Intel is run by fools. I don't see them coming back. They
           | just don't have the willingness to compete and offer products
           | with USPs. Intel today is just MBAs and the cheapest
           | outsourced labor the MBAs can find.
        
       ___________________________________________________________________
       (page generated 2025-03-16 23:01 UTC)