Give me a break. Valve did it just fine even without vendor drivers:They perhaps naively trusted Qualcomm when they said they would support Linux. One can only hope the situation will be better for the next generation of SD.
Give me a break. Valve did it just fine even without vendor drivers:They perhaps naively trusted Qualcomm when they said they would support Linux. One can only hope the situation will be better for the next generation of SD.
Give me a break. Valve did it just fine even without vendor drivers:
Steam Frame Using Mesa's Turnip Vulkan Open-Source Driver - Phoronix
www.phoronix.com
Eh, it creeps in a few places. https://www.unrealengine.com/en-US/...-in-unreal-engine-4-a-peek-behind-the-curtainMost games aren't particularly SIMD-heavy.
As far as I understand 8 gen 3 was last soc supported by Turnip, all adreno 8xx soc don't have Turnip support.Give me a break. Valve did it just fine even without vendor drivers:
Steam Frame Using Mesa's Turnip Vulkan Open-Source Driver - Phoronix
www.phoronix.com
This leads to https://github.com/intel/projects/intel-ispc-in-unreal-engine-4-a-peek-behind-the-curtain which ends in 404. Do you have it archived somewhere?Eh, it creeps in a few places. https://www.unrealengine.com/en-US/...-in-unreal-engine-4-a-peek-behind-the-curtain
Bah, sorry, that used to be a working blog post! But ISPC is certainly still used in Unreal Engine (as you can verify yourself if you check the source), and will generate SIMD code for a range of architectures.This leads to https://github.com/intel/projects/intel-ispc-in-unreal-engine-4-a-peek-behind-the-curtain which ends in 404. Do you have it archived somewhere?![]()
Yeah, but who cares about a laptop that does proper suspend/resume /sValve did Linux without vendor drivers for the GPU. Now do the ISP, the codec blocks, power management, wifi/modem, device enumeration, etc, etc
My point is that it isn't some vendor conspiracy as the trolls on this board seem to think. Qualcomm is actually excellent at b2b customer support:Valve did Linux without vendor drivers for the GPU. Now do the ISP, the codec blocks, power management, wifi/modem, device enumeration, etc, etc
I also suspect, by the way, that Valve is using Halium, and therefore cribbing heavily from what is available for phones. This is not common or desired practice for desktop Linux, as it inherits a bunch of dependencies on out-of-tree, out-of-distro-repos Android bits.
Compared to Lunar Lake (288V), the 12-core variants of X2E are ~30% faster in Single Thread depending on the benchmark. What do we expect Panther Lake to be compared to Lunar Lake, ~10% faster in ST? So X2E would be 20% faster than Panther Lake in 1T workloads. Panther Lake will close the gap considerably in terms of nT workloads, at least with it's bigger compute die that has 4p+8e+4lp cores, which is probably what the 12-core X2E chips will go up against.Didn't see the computerbase.de benchmarks listed here:
![]()
Snapdragon X2 Elite im Benchmark: Alle drei SoCs im Vergleich mit Apple, AMD und Intel
Nach Benchmarks mit dem Snapdragon X2 Elite Extreme konnte ComputerBase jetzt die Ableger X2E-88-100 und X2E-80-100 bei 22 Watt TDP testen.www.computerbase.de
Qualcomm's reference designs tend to always perform better than actual laptops, but still relatively impressive
www.semiaccurate.com
Oh Qualcomm wasted a S class CPU team what a surprise![]()
A Deep Dive Into The Qualcomm Snapdragon X2 Elite Workings
Qualcomm talked about the power use of the X2 in a roundabout way, please welcome the new INPP metric.www.semiaccurate.com
Mighty impressive figures given the performance uplift between the two.
It should be new die, codename Mahua: different than X2 Elite. It is supposed to have 6+6 CPU config; not sure due to conflict with X2 Elite (6+6) & 128-bit memory bus. The X2P-64 comes with 4+6? configuration. iGPU should cut off 1 WGP net 3.5TF. The only thing not cut is NPU: still remains 80 TOPS which is expected.Is this something new?
Qualcomm is claiming some wild gains. 3.1x faster MT performance than competitors at the same power (!)
Same as last gen, where we had Purwa (Plus) and Hamoa (Elite).Is this something new?
Qualcomm is claiming some wild gains. 3.1x faster MT performance than competitors at the same power (!)
The iGPU is weak.That hexa core part has no small cores? NOW this is wild, damn Qualcomm, if compatibility wouldn't be an issue, it could destroy Intel and AMD big time.
Is there a market for budget with less battery life? I don’t quite get it unless OEMs can really open up a price gap with the Elites. A bigger price gap than with the X1s.That hexa core part has no small cores? NOW this is wild, damn Qualcomm, if compatibility wouldn't be an issue, it could destroy Intel and AMD big time.
Don't forget: mini PCs. Those little things could be a good way to sell the X1 Plus without E Cores. Of course for laptops won't be but for Mini PCs it might be another story.Is there a market for budget with less battery life? I don’t quite get it unless OEMs can really open up a price gap with the Elites. A bigger price gap than with the X1s.
SYCL support was already mentioned in one of their slides, now they have stated a timeline.George: And in terms of API, what will you support for the X2 GPU?
Eric: Obviously we’ll have DirectX 12.2 and all the DirectX versions behind that, so we’ll be fully compatible there. But we also plan to introduce native Vulkan 1.4 support. There’s a version of that which Windows supplies, but we’ll be supplying a native version that is the same codebase as we use for our other products. We’ll also be introducing native OpenCL 3.0 support, also as used by our other products. And then in the first quarter of 2026 we’d like to introduce SYCL support, and SYCL is a higher-end compute-focused API and shading language for a GPU. It’s an open standard, other companies support it, and it helps us attack some of the GPGPU use-cases that exist on Windows for Snapdragon.
