Please Qualcomm and Microsoft, try to have the top end chip in some cheap, well-specced, thermally capable Intel NUC/Mac Mini form factor. I'm writing this on your Windows on ARM Dev Kit 2023 and it fit that bill very well but I'm excited to try a faster chip with better GPU drivers that doesn't break the bank or constrain performance with a low TDP.Reply
>cheap Unfortunately, one of the main issues with Qualcomm and the reason I'm not expecting much from the X Elite, is that their previous Snapdragon PC offerings have been utterly, ridiculously out of touch in terms of pricing.
Every single Snapdragon laptop I've seen has been $2,000+, and that's for a chip that can't even touch the x86 competition in terms of performance, and for a software ecosystem that one would be kind to compare even to a beta. If the X Elite is even close to the competition now, I wouldn't be surprised if it can't be found for less than $2,500, and at that kind of price, a Windows-on-ARM experience is just out of the question, and given Qualcomm's track record, I'd be impressed if it's even possible to get Linux running on it.Reply
And to be clear, it's an utter pity that it has to be that way. I'd love myself a reasonably capable ARM laptop for development and experiments, but with the pricing and Linux support that Qualcomm seems to be set on, I don't see it happening.Reply
That's why I mentioned the WoA Dev Kit, that was £600 with 32GB of RAM and a mac mini form factor. At the time the next cheapest device was a thinkpad x13s for double that. Do it again please, don't make me pay thousands for an unproven platform.Reply
@ Ryan Smith: was there any elaboration as to the P-core/E-core split on these chips? Most rumors still say the X Elite is a 8 P-core & 4 E-core design, with the X Plus dropping down to a 6 P-core & 4 E-core. But it is well known that all cores are the "same" Oryon design. That makes me think the P/E core split is more akin to AMD's strategy with Zen 4/4C. All the cores the same, but perhaps only some can reach certain clockspeeds. At the same time though, Qualcomm is touting those 3.80GHz (or 3.40GHz) all-core turbo speeds - does that really mean all 12 or 10 cores can go that high? Is there perhaps a difference in the L2 cache between them? Or is there really no P/E core split whatsoever?Reply
The cores are the same, but there are two clusters. On the Elite cluster 1 has 8P cores and cluster 2 have 4P cores. On the plus the first cluster is reduced to 6P.Reply
According to Qualcomm, all of the cores are identical. They do not have separate P and E cores, though they do have multiple clusters of cores.
I will put an asterisk in there though, as Qualcomm has not given us a complete deep dive on the architecture yet, and the company does not have a history of being freely forthcoming with technical details. So there could be a catch in there somewhere that makes the CPU clusters somehow different from each other.
And yes, all-core turbo is all-core turbo. All of the CPU cores can go that high, TDP permitting.Reply
Thank you the reply Ryan! That is pretty crazy Qualcomm decided to go with a straight all big core setup, especially given their long history on the smartphone ARM side with big.LITTLE architectures. That does explain how X Elite and X Plus should easily outmatch Apple M3/Ryzen 8040/Core Ultra in multi-thread performance - no matter how you slice it, having 10 or 12 full perf cores is going to beat 4 or 6 or 8 of the competitor's ones. I did notice no single-thread benchmarks, so it will be interesting to see how each individual Oryon core compares to an M3 or Zen 4 or Redwood Cove.Reply
You are confusing Snapdragon X with Ryzen 9000 series Strix Point, AMD’s upcoming monolithic 12-core APU offering. The core configuration on Snapdragon X is purely homogeneous across all measures including feature set and so on. The only difference is binning which allows for higher two core boosting and a higher GPU clock for higher end SKUs.Reply
That's more or less a given. Especially since the X1E-78-100 is the same specs with 12 CPU cores. Qualcomm would be shortchanging themselves by not having a salvage bin.Reply
What I find particularly interesting is the NPU performance and cache size remain the same. It's a monolithic die, is it not? I find it hard to believe the only defects that happen are in the CPU.Reply
>I find it hard to believe the only defects that happen are in the CPU. More likely, the NPU and caches are built with internal redundancy where they have spare elements to compensate for defects.Reply
We don't have a floor plan, but the NPU is thought to not be all that big. It's a dense array of systolic ALUs, but it shouldn't require much die space. So the odds of a defect hitting it, versus the much larger CPU clusters, is relatively low.Reply
It says that the real performance is up to 50% lower than the numbers presented by Qualcomm. In other words, the product hasn't even been launched yet and is already a total failure.Reply
Looks like typical scumbag Qualcomm we love to hate. If it's the truth, other than it will be a flop, every competent true reviewer and not some shill influencer, will rip this product apart. What were they thinking? That they could get away with this? That people will forget their promises? That they make will make those bogus number a reality when it comes out? This is just sad, although I hate Qualcomm as a company, I see them as necessary evil to push efficency on windows machines, now all they do is drive me further into buying apple's Mac with their overpriced memory and storage configs. Reply
You should take the numbers given by Qualcomm with a grain of salt, but you should also be weary of semiaccurate's recent reports.
50%, if true, would not only be a total failure, it would be a litigation nightmare. Like way beyond the scope of number fudging that is legally allowed by the feds.Reply
Andrei now does performance analysis for NUVIA. He needs no introduction and his work speaks for itself. I trust the numbers since the conditions are very transparently listed in the bottom notes including OS, memory speed, total platform/device power and so on. In fact, that 23 watt limit for QC’s thin and light reference device is impressive when you realize that also is the maximum power envelope for the display, memory and NVMe under full load.
SemiAccurate cannot give specifics because there are none. I wouldn’t be surprised if Intel is trying to submarine Snapdragon X’s release and Charlie took the bait. His site became trash over the last 3-5 years and this is the tip of the iceberg of the drivel is shovels out these days. He couldn’t even get his web forum with years of subscriber content and discussion back online that his $1.5K/year subscribers wanted—so much for Charlie being tech savvy. Ignore that idiot and his keyboard warrior mind-numbing rants.Reply
Hmm ... well given the TDP numbers from the Qualcomm graph, I'd be suspicious a lot. How can the Ryzen 7940HS reach almost 100W when the official TDP is 35-54W ? Yes I know the PPT is higher but not 100W high, I think the maximum official PPT is 65W. Comparatively the Intel 155H can boost up to 115W yet the benchmark cuts of below 80W ?
So did they measure power at the wall ? Then I wonder why since that is not comparable across devices and has no meaning what so ever when comparing CPUs ... I just don't buy the graphs when there is so much information missing.Reply
There are a few mini-PCs that allow you to manually set the power limits of a 7840HS/7940HS. The total power tends to top out at 90W, with around 40W going to the GPU.Reply
While I value and respect Andrei's expertise and really miss his analysis here, he is now an employee of Qualcomm; and being an employee means that you have to tow the company line, only speak out publicly if authorized to do so, or you get fired and then sued for damages to boot! Employment contracts are full of clauses that are there to prevent any employee from speaking out of turn, especially if you work in R&D. That is not just so at Qualcomm, but is true at pretty much any larger corporation, at least in the US. Reply
I don't believe the supposed launch is just this pathetic copy and paste of suspicious numbers provided by Qualcomm. How horrible... they didn't send any laptops for review?Reply
No, it’s not. Charlie is just salty he isn’t the center of attention in the industry anymore and that he didn’t get a first look at Snapdragon X like the rest of the tech sites did. Some journalists have overinflated egos of themselves and Charlie is among the worst kind of that ilk.Reply
I wonder how good real time encoding quality of AV1 can be on mobile hardware in 2024. I guess if they weren't achieving better quality at a given bitrate than h.265 then they wouldn't include it just to check a box on a feature list, right?Reply
With AV1, it's quite easy to beat HEVC, so I suppose it will be better. In software encoding, SVT-AV1, using the fastest preset, has better compression and speed than x265 and even x264. I can't remember which presets exactly, but I think medium. I'll give it a test and confirm.
What would be nice to see is VVC encoding and decoding, playback having been widely enabled of late by FFmpeg's new decoder.Reply
A big question will be what cost systems these will be in. Will they have lower margins on the chip than AMD and Intel as ARM SoCs typically do, or will they try to move up in the world? The Plus still looks like plenty of performance, could have a lot of appeal if it brings similar perf/watt to M3 in much lower cost systems Reply
Very curious what happened with the LPDDR5 frequency. Supplier change? Some esoteric reference clock was set too high? Picking a non-JEDEC-standard # isn’t bad or even very interesting, but it certainly makes you curious of the engineering why.
//
Still feels weird to tease a CPU this early with so much first-party specific data, but little on the technical side. Like, surely, if QC knows all this, then popular details about the uArch or GPU config or cache would be set in stone.
I also don’t love the names. Are all the Elite versions seriously going to use obscure product codes to differentiate? 😭 So Elite X 84, Elite X 80, etc.?
No Elite Xa, Elite Xb, etc?
Whatever happened to those 3.2K Geekbench 6.2 1T results? Are those gone forever now? I don’t seen them mentioned anymore. Reply
"Whatever happened to those 3.2K Geekbench 6.2 1T results? Are those gone forever now? I don’t seen them mentioned anymore. "
The current guidance from Qualcomm for GB 6.2 ST performance is to expect a high TDP (config A) system to score between 2850 and 2900. The previous guidance in October was 2939-2979.Reply
Ahh, you're thinking about the Geekbench Linux results.
The high TDP systems running Linux score a bit higher than the Windows systems, due to a combination of OS differences and the fact that (at the time) there was no speed management for the fans - so they were locked at 100%. We observed a demo system scoring 3236, and there had apparently been runs that were faster.
I think Snapdragon X in any way or form has high probability of flopping it's because of the graphics driver support for decades and decades of many applications especially gaming just wouldn't be there and they have to continuously update them every time and an important game is released. Also what about all the really important rendering applications there is a very high barrier to entry in the pc space.Reply
Qualcomm's ego and desire to be seen as a direct Intel/Apple competitor is wasting a perfectly viable core. This should be an Alder Lake-N competitor. It could easily win the sub-$500 market and the education market with half the core count on TSMC 6nm.Reply
Mediatek mid and low range are cheap, but their top end is pricey. The only phones I could find have comparable prices between Mediatek Dimensity 9300 and Snapdragon 8 Gen3.Reply
If there's anything to that story, Qualcomm will have some explaining to do. This doesn't look good, and they better get out in front of this now! Reply
Thanks Ryan! Well, at least Qualcomm is consistent, even if it's consistent in deflecting criticism. I hope they realize that it's in their own best interest to get even pre-production laptops in the hands of outside reviewers like yourself ASAP. Reply
If Qualcomm can release a perfect low wattage CPU that makes a Windows based fanless laptop like that of the Apple’s MacBook Air M3: I will buy it! Reply
Geekbench just posted results for a Dell Inspiron with a Snapdragon X Elite SoC; they are considerably lower than the figures QC showed https://browser.geekbench.com/v6/cpu/5889224 . Of course, both Windows on ARM and the firmware used are likely still not ready to ship releases, but then, what is QC running on their samples that got much better numbers, and why didn't Dell (a Tier 1 OEM) have access to those? QC isn't helping their case here. Reply
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
50 Comments
Back to Article
CampGareth - Wednesday, April 24, 2024 - link
Please Qualcomm and Microsoft, try to have the top end chip in some cheap, well-specced, thermally capable Intel NUC/Mac Mini form factor. I'm writing this on your Windows on ARM Dev Kit 2023 and it fit that bill very well but I'm excited to try a faster chip with better GPU drivers that doesn't break the bank or constrain performance with a low TDP. ReplyDolda2000 - Wednesday, April 24, 2024 - link
>cheapUnfortunately, one of the main issues with Qualcomm and the reason I'm not expecting much from the X Elite, is that their previous Snapdragon PC offerings have been utterly, ridiculously out of touch in terms of pricing.
Every single Snapdragon laptop I've seen has been $2,000+, and that's for a chip that can't even touch the x86 competition in terms of performance, and for a software ecosystem that one would be kind to compare even to a beta. If the X Elite is even close to the competition now, I wouldn't be surprised if it can't be found for less than $2,500, and at that kind of price, a Windows-on-ARM experience is just out of the question, and given Qualcomm's track record, I'd be impressed if it's even possible to get Linux running on it. Reply
Dolda2000 - Wednesday, April 24, 2024 - link
And to be clear, it's an utter pity that it has to be that way. I'd love myself a reasonably capable ARM laptop for development and experiments, but with the pricing and Linux support that Qualcomm seems to be set on, I don't see it happening. ReplyCampGareth - Wednesday, April 24, 2024 - link
That's why I mentioned the WoA Dev Kit, that was £600 with 32GB of RAM and a mac mini form factor. At the time the next cheapest device was a thinkpad x13s for double that. Do it again please, don't make me pay thousands for an unproven platform. ReplyAlistair - Sunday, April 28, 2024 - link
yeap give me a dev kit with 32GB/1TB for $800 USD or so Replynandnandnand - Wednesday, April 24, 2024 - link
That's the appropriate level of skepticism. Maybe the 10-core model will do better. ReplyNextGen_Gamer - Wednesday, April 24, 2024 - link
@ Ryan Smith: was there any elaboration as to the P-core/E-core split on these chips? Most rumors still say the X Elite is a 8 P-core & 4 E-core design, with the X Plus dropping down to a 6 P-core & 4 E-core. But it is well known that all cores are the "same" Oryon design. That makes me think the P/E core split is more akin to AMD's strategy with Zen 4/4C. All the cores the same, but perhaps only some can reach certain clockspeeds. At the same time though, Qualcomm is touting those 3.80GHz (or 3.40GHz) all-core turbo speeds - does that really mean all 12 or 10 cores can go that high? Is there perhaps a difference in the L2 cache between them? Or is there really no P/E core split whatsoever? Replyhigh3r - Wednesday, April 24, 2024 - link
Afaik, all cores are P cores in both Elite and Plus. 4 cores likely at lower frequency. Replydudedud - Wednesday, April 24, 2024 - link
The cores are the same, but there are two clusters. On the Elite cluster 1 has 8P cores and cluster 2 have 4P cores. On the plus the first cluster is reduced to 6P. ReplyRyan Smith - Wednesday, April 24, 2024 - link
According to Qualcomm, all of the cores are identical. They do not have separate P and E cores, though they do have multiple clusters of cores.I will put an asterisk in there though, as Qualcomm has not given us a complete deep dive on the architecture yet, and the company does not have a history of being freely forthcoming with technical details. So there could be a catch in there somewhere that makes the CPU clusters somehow different from each other.
And yes, all-core turbo is all-core turbo. All of the CPU cores can go that high, TDP permitting. Reply
NextGen_Gamer - Thursday, April 25, 2024 - link
Thank you the reply Ryan! That is pretty crazy Qualcomm decided to go with a straight all big core setup, especially given their long history on the smartphone ARM side with big.LITTLE architectures. That does explain how X Elite and X Plus should easily outmatch Apple M3/Ryzen 8040/Core Ultra in multi-thread performance - no matter how you slice it, having 10 or 12 full perf cores is going to beat 4 or 6 or 8 of the competitor's ones. I did notice no single-thread benchmarks, so it will be interesting to see how each individual Oryon core compares to an M3 or Zen 4 or Redwood Cove. ReplyHifihedgehog - Thursday, April 25, 2024 - link
You are confusing Snapdragon X with Ryzen 9000 series Strix Point, AMD’s upcoming monolithic 12-core APU offering. The core configuration on Snapdragon X is purely homogeneous across all measures including feature set and so on. The only difference is binning which allows for higher two core boosting and a higher GPU clock for higher end SKUs. Replymeacupla - Wednesday, April 24, 2024 - link
I wonder if the X Plus an X Elite with 1 or 2 cores that didn't pass QC. ReplyRyan Smith - Wednesday, April 24, 2024 - link
That's more or less a given. Especially since the X1E-78-100 is the same specs with 12 CPU cores. Qualcomm would be shortchanging themselves by not having a salvage bin. Replymeacupla - Wednesday, April 24, 2024 - link
What I find particularly interesting is the NPU performance and cache size remain the same.It's a monolithic die, is it not?
I find it hard to believe the only defects that happen are in the CPU. Reply
Dolda2000 - Wednesday, April 24, 2024 - link
>I find it hard to believe the only defects that happen are in the CPU.More likely, the NPU and caches are built with internal redundancy where they have spare elements to compensate for defects. Reply
Ryan Smith - Wednesday, April 24, 2024 - link
We don't have a floor plan, but the NPU is thought to not be all that big. It's a dense array of systolic ALUs, but it shouldn't require much die space. So the odds of a defect hitting it, versus the much larger CPU clusters, is relatively low. Replymeacupla - Thursday, April 25, 2024 - link
Ah, I see. That is very interesting info, much appreciated. Replyhigh3r - Wednesday, April 24, 2024 - link
https://www.semiaccurate.com/2024/04/24/qualcomm-i... ReplyTerry_Craig - Wednesday, April 24, 2024 - link
It says that the real performance is up to 50% lower than the numbers presented by Qualcomm. In other words, the product hasn't even been launched yet and is already a total failure. ReplyEliadbu - Wednesday, April 24, 2024 - link
Looks like typical scumbag Qualcomm we love to hate. If it's the truth, other than it will be a flop, every competent true reviewer and not some shill influencer, will rip this product apart. What were they thinking? That they could get away with this? That people will forget their promises? That they make will make those bogus number a reality when it comes out? This is just sad, although I hate Qualcomm as a company, I see them as necessary evil to push efficency on windows machines, now all they do is drive me further into buying apple's Mac with their overpriced memory and storage configs. Replymeacupla - Wednesday, April 24, 2024 - link
You should take the numbers given by Qualcomm with a grain of salt, but you should also be weary of semiaccurate's recent reports.50%, if true, would not only be a total failure, it would be a litigation nightmare. Like way beyond the scope of number fudging that is legally allowed by the feds. Reply
Hifihedgehog - Thursday, April 25, 2024 - link
Andrei now does performance analysis for NUVIA. He needs no introduction and his work speaks for itself. I trust the numbers since the conditions are very transparently listed in the bottom notes including OS, memory speed, total platform/device power and so on. In fact, that 23 watt limit for QC’s thin and light reference device is impressive when you realize that also is the maximum power envelope for the display, memory and NVMe under full load.SemiAccurate cannot give specifics because there are none. I wouldn’t be surprised if Intel is trying to submarine Snapdragon X’s release and Charlie took the bait. His site became trash over the last 3-5 years and this is the tip of the iceberg of the drivel is shovels out these days. He couldn’t even get his web forum with years of subscriber content and discussion back online that his $1.5K/year subscribers wanted—so much for Charlie being tech savvy. Ignore that idiot and his keyboard warrior mind-numbing rants. Reply
haplo602 - Thursday, April 25, 2024 - link
Hmm ... well given the TDP numbers from the Qualcomm graph, I'd be suspicious a lot. How can the Ryzen 7940HS reach almost 100W when the official TDP is 35-54W ? Yes I know the PPT is higher but not 100W high, I think the maximum official PPT is 65W. Comparatively the Intel 155H can boost up to 115W yet the benchmark cuts of below 80W ?So did they measure power at the wall ? Then I wonder why since that is not comparable across devices and has no meaning what so ever when comparing CPUs ... I just don't buy the graphs when there is so much information missing. Reply
meacupla - Thursday, April 25, 2024 - link
There are a few mini-PCs that allow you to manually set the power limits of a 7840HS/7940HS.The total power tends to top out at 90W, with around 40W going to the GPU. Reply
eastcoast_pete - Thursday, April 25, 2024 - link
While I value and respect Andrei's expertise and really miss his analysis here, he is now an employee of Qualcomm; and being an employee means that you have to tow the company line, only speak out publicly if authorized to do so, or you get fired and then sued for damages to boot! Employment contracts are full of clauses that are there to prevent any employee from speaking out of turn, especially if you work in R&D. That is not just so at Qualcomm, but is true at pretty much any larger corporation, at least in the US. Replyeastcoast_pete - Thursday, April 25, 2024 - link
Didn't see your post, I just put that also in my post here. Definitely something worth reading, and for Qualcomm to respond to! ReplyTerry_Craig - Wednesday, April 24, 2024 - link
I don't believe the supposed launch is just this pathetic copy and paste of suspicious numbers provided by Qualcomm. How horrible... they didn't send any laptops for review? Replykn00tcn - Wednesday, April 24, 2024 - link
nowhere did anyone state this is a launch,it's a product brief about a couple months before launchthe very first sentence even says "preparing for mid-year" Reply
Terry_Craig - Wednesday, April 24, 2024 - link
This is a big circus tent set up by Qualcomm clowns. ReplyHifihedgehog - Thursday, April 25, 2024 - link
No, it’s not. Charlie is just salty he isn’t the center of attention in the industry anymore and that he didn’t get a first look at Snapdragon X like the rest of the tech sites did. Some journalists have overinflated egos of themselves and Charlie is among the worst kind of that ilk. Replygarblah - Wednesday, April 24, 2024 - link
I wonder how good real time encoding quality of AV1 can be on mobile hardware in 2024. I guess if they weren't achieving better quality at a given bitrate than h.265 then they wouldn't include it just to check a box on a feature list, right? ReplyGeoffreyA - Thursday, April 25, 2024 - link
With AV1, it's quite easy to beat HEVC, so I suppose it will be better. In software encoding, SVT-AV1, using the fastest preset, has better compression and speed than x265 and even x264. I can't remember which presets exactly, but I think medium. I'll give it a test and confirm.What would be nice to see is VVC encoding and decoding, playback having been widely enabled of late by FFmpeg's new decoder. Reply
tipoo - Wednesday, April 24, 2024 - link
A big question will be what cost systems these will be in. Will they have lower margins on the chip than AMD and Intel as ARM SoCs typically do, or will they try to move up in the world? The Plus still looks like plenty of performance, could have a lot of appeal if it brings similar perf/watt to M3 in much lower cost systems Replyikjadoon - Wednesday, April 24, 2024 - link
Very curious what happened with the LPDDR5 frequency. Supplier change? Some esoteric reference clock was set too high? Picking a non-JEDEC-standard # isn’t bad or even very interesting, but it certainly makes you curious of the engineering why.//
Still feels weird to tease a CPU this early with so much first-party specific data, but little on the technical side. Like, surely, if QC knows all this, then popular details about the uArch or GPU config or cache would be set in stone.
I also don’t love the names. Are all the Elite versions seriously going to use obscure product codes to differentiate? 😭 So Elite X 84, Elite X 80, etc.?
No Elite Xa, Elite Xb, etc?
Whatever happened to those 3.2K Geekbench 6.2 1T results? Are those gone forever now? I don’t seen them mentioned anymore. Reply
Ryan Smith - Wednesday, April 24, 2024 - link
"Whatever happened to those 3.2K Geekbench 6.2 1T results? Are those gone forever now? I don’t seen them mentioned anymore. "The current guidance from Qualcomm for GB 6.2 ST performance is to expect a high TDP (config A) system to score between 2850 and 2900. The previous guidance in October was 2939-2979. Reply
ikjadoon - Wednesday, April 24, 2024 - link
Ah, interesting, right. So there has been a small drop off.//
I was actually remembering these Qualcomm benchmarks from also October 2023:
Geekbench 6.2 1T
Qualcomm "Oryon" (no SXE name): 3,227
Intel i9-13980HX: 3,192
Apple M2 Max: 2,841
https://www.pcworld.com/article/2112907/qualcomm-s...
It's not a major regression, but I do wonder where the 3.2K number came from, if it was also released around the Oct 2023 timeframe. Reply
Ryan Smith - Wednesday, April 24, 2024 - link
Ahh, you're thinking about the Geekbench Linux results.The high TDP systems running Linux score a bit higher than the Windows systems, due to a combination of OS differences and the fact that (at the time) there was no speed management for the fans - so they were locked at 100%. We observed a demo system scoring 3236, and there had apparently been runs that were faster.
https://www.anandtech.com/show/21112/qualcomm-snap... Reply
trivik12 - Wednesday, April 24, 2024 - link
I am looking forward to independent reviews on laptops with these chips but its annoying around trickled info that is coming out. Replysnakeeater3301 - Wednesday, April 24, 2024 - link
I think Snapdragon X in any way or form has high probability of flopping it's because of the graphics driver support for decades and decades of many applications especially gaming just wouldn't be there and they have to continuously update them every time and an important game is released. Also what about all the really important rendering applications there is a very high barrier to entry in the pc space. Replydigiguy - Saturday, April 27, 2024 - link
there are tons of ultrabook users who don't game or do any rendering Replyfelixbrault - Thursday, April 25, 2024 - link
Abysmal single-thread performance confirmed. In speedometer 3.0 (mostly single threaded performance) my Iphone 14 Pro max get 25.2 of score. Replylmcd - Thursday, April 25, 2024 - link
Qualcomm's ego and desire to be seen as a direct Intel/Apple competitor is wasting a perfectly viable core. This should be an Alder Lake-N competitor. It could easily win the sub-$500 market and the education market with half the core count on TSMC 6nm. Replynandnandnand - Friday, April 26, 2024 - link
If we believe Qualc, It's competitive with Phoenix and Meteor Lake, if not Strix Point (other than the big boy 45 TOPS NPU).If you want cheap Windows on ARM, MediaTek has to come to the rescue. ARM's CEO said the exclusivity deal is ending this year. Reply
meacupla - Friday, April 26, 2024 - link
Mediatek mid and low range are cheap, but their top end is pricey.The only phones I could find have comparable prices between Mediatek Dimensity 9300 and Snapdragon 8 Gen3. Reply
eastcoast_pete - Thursday, April 25, 2024 - link
Would love to hear any comments from Qualcomm about this article in Semiaccurate https://www.semiaccurate.com/2024/04/24/qualcomm-i...If there's anything to that story, Qualcomm will have some explaining to do. This doesn't look good, and they better get out in front of this now! Reply
Ryan Smith - Friday, April 26, 2024 - link
"Would love to hear any comments from Qualcomm about this article in Semiaccurate "Qualcomm's official response is as follows:
"We stand behind our performance claims and are excited for consumers to get their hands on Snapdragon X Elite and X Plus devices soon.” Reply
eastcoast_pete - Friday, April 26, 2024 - link
Thanks Ryan! Well, at least Qualcomm is consistent, even if it's consistent in deflecting criticism. I hope they realize that it's in their own best interest to get even pre-production laptops in the hands of outside reviewers like yourself ASAP. ReplyHarry_Wild - Monday, April 29, 2024 - link
If Qualcomm can release a perfect low wattage CPU that makes a Windows based fanless laptop like that of the Apple’s MacBook Air M3: I will buy it! Replyeastcoast_pete - Monday, April 29, 2024 - link
Geekbench just posted results for a Dell Inspiron with a Snapdragon X Elite SoC; they are considerably lower than the figures QC showed https://browser.geekbench.com/v6/cpu/5889224. Of course, both Windows on ARM and the firmware used are likely still not ready to ship releases, but then, what is QC running on their samples that got much better numbers, and why didn't Dell (a Tier 1 OEM) have access to those? QC isn't helping their case here. Reply