EnGenius ECS2512FP. 8-port 2.5G Cloud Switch review
Deepcool CG560 chassis review
Fractal Design Torrent Black RGB TG review
Core i9 12900K DDR4 3600 vs DDR5 5200 performance review
Corsair H150i Elite LCD review
Seasonic Syncro Q704 chassis + Connect PSU review
Fractal Design Ion+ 2 Platinum 860W PSU Review
Crucial P5 Plus PCIe 4.0 M.2 NVMe review
Fractal Design Lumen S28 RGB review (LCS)
WD Red SN700 NVMe SSD review
AMD makes Super Resolution officially open source, four new games get support
Following the recent AMD FidelityFX Super Resolution (FSR) announcement, AMD is today making the source code for its powerful spatial upscaling technology broadly available to game developers via GPUOpen.
FSR is also now available for developers in two of the most popular game engines:
- Unity: A special preview beta branch of Unity 2021.2 HDRP.
- Unreal Engine: A patch that can be applied to v4.26 of Unreal Engine.
FSR is an open-source solution with broad API support, making it easy for developers to integrate the technology into new and existing titles, and is supported on more than 100 AMD processors with Radeon graphics and AMD GPUs, as well as competitor GPUs. FSR is designed to boost framerates by up to 2.4x at 4K in “Performance” mode in select titles while delivering a high-quality, high-resolution gaming experience.
Additionally, several new titles are adding FSR support in the next few weeks, bringing the total number of FSR-supported games to 12 since the feature was launched just a few weeks ago, with more expected in the coming months:
- Arcadegeddon (July 16)
- Necromunda: Hired Gun (July 16)
- Resident Evil Village (next week)
- Edge of Eternity (this month)
For more information on FSR please visit GPUOpen
AMD makes now offers a 4700S CPU, the IC and PC version of the Xbox Series X SOC (with the GPU disabled) - 06/28/2021 09:32 AM
Here's an interesting one, AMD made its “4700S” processor official, 5this is the Xbox Series X SOC. The 4700S has its GPU disabled, despite the fact that it includes the same RDNA2 GPU from 12TF...
AMD makes Radeon RX 500X series offical: OEM rebrands - 04/11/2018 09:54 PM
On its website AMD has now released official information on the Radeon RX 500X series. Little is new about is, and it seems to be OEM rebranding with the Radeon RX 500 series. As we discussed yesterd...
AMD makes profit again - 04/16/2010 10:04 AM
AMD announced a first quarter profit of $257 million, or 35 cents per share, on revenue of $1.57 billion. This compared to a loss of $416 million, or 66 cents per share, on revenue of $1.18 billion in...
Horus-Anhur
Senior Member
Posts: 1584
Joined: 2013-02-05
Senior Member
Posts: 1584
Joined: 2013-02-05
#5929686 Posted on: 07/16/2021 02:41 PM
You are, probably, confusing it with nVidia.
amd is hated in the open source community.
You are, probably, confusing it with nVidia.
kanenas
Senior Member
Posts: 317
Joined: 2019-07-07
Senior Member
Posts: 317
Joined: 2019-07-07
#5929719 Posted on: 07/16/2021 05:02 PM
amd is hated in the open source community.
6155
AMD Van Gogh APU With Zen 2 CPU & RDNA 2 GPU Cores, Over 2 TFLOPs Horsepower
6156
amd is hated in the open source community.
6155
AMD Van Gogh APU With Zen 2 CPU & RDNA 2 GPU Cores, Over 2 TFLOPs Horsepower
6156
cucaulay malkin
Senior Member
Posts: 3017
Joined: 2020-08-03
Senior Member
Posts: 3017
Joined: 2020-08-03
#5929729 Posted on: 07/16/2021 05:37 PM
If you read the code, the process takes place very early in the pipeline, it even utilizes FP16 on GPUs supporting it for better graphics etc.
how ? in what way ?
If you read the code, the process takes place very early in the pipeline, it even utilizes FP16 on GPUs supporting it for better graphics etc.
how ? in what way ?
Denial
Senior Member
Posts: 13565
Joined: 2004-05-16
Senior Member
Posts: 13565
Joined: 2004-05-16
#5929735 Posted on: 07/16/2021 05:51 PM
It's an optimized Lanczos-2 with edge-guided interpolation. It makes use of FP16 when supported for additional performance.
Heavily modifed lanczos-2. Is not the same thing.
It's an optimized Lanczos-2 with edge-guided interpolation. It makes use of FP16 when supported for additional performance.
Click here to post a comment for this news story on the message forum.
Senior Member
Posts: 6203
Joined: 2012-11-10
amd is hated in the open source community.
Sure, some hate AMD in the open-source community, but most don't.
What for? GPU or CPU related?
If for CPU - PSP code, then yes.
If for GPU, I don't see why.
i am genuinely curious, can you elaborate, please?
It's mostly just a bunch of princesses who are picky and not getting everything they expected. Or they get a lemon of a GPU (most likely user error - I don't believe any computer hardware is ever truly DOA when new) and swear vengeance or whatever.
There are also those who want better compute support, but, most of such users go to Nvidia. Nvidia's negatives with open-source hardly matter at all when compute performance is your #1 priority, and Nvidia is still overall the better option for compute.