SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Technology Stocks : Qualcomm Moderated Thread - please read rules before posting
QCOM 175.25+0.6%Dec 19 9:30 AM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: waitwatchwander who wrote (196682)11/19/2025 3:52:32 PM
From: Wildbiftek4 Recommendations

Recommended By
JeffreyHF
Lance Bredvold
manning18
ryhack

   of 197011
 
Their new Adreno architecture (similar to but bigger than the Adreno 830/840 found in phone chips) was re-architected for more modern compute heavy GPGPU loads than 7xx and earlier Adrenos.

hothardware.com

In terms of GPGPU workloads, the Adreno X2 has native driver support for WCR (Windows Copilot Runtime), BF16 support, local memory broadcast, and general shuffles, which allows full shuffling between the threads.

On the software side, Qualcomm states it is planning to move to a monthly release cadence, although it didn’t announce when that would begin. As it stands now, the Adreno X2 driver has native support for DX 12.2, OpenCL 3.0 and SYCL, and a Native Vulkan 1.4 driver is coming in Q1 '26. Qualcomm is also working toward full kernel-level anti-cheat compatibility and hopes that by the launch of Snapdragon Elite X2 all major anti-cheat technologies will be natively supported.

I think they didn't see it fit to dedicate excessive resources to driver development prior to this gen because no matter what they did on the driver level, they were limited by the prior gen GPU which is both smaller and less advanced (esp. re. caches):

chipsandcheese.com

They saw it fit to add an additional "cluster cache" to the hierarchy, but the performance of this bolt-on wasn't well optimized in the older architecture. Bandwidth and latency were low compared to other integrated and low end discrete competitors.
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext