Announcement

Collapse
No announcement yet.

Mesa's RADV Radeon Vulkan Driver Continues Outperforming AMDVLK For RDNA2 Linux Gaming

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • M@GOid
    replied
    Originally posted by skeevy420 View Post

    I about shit myself when I saw a 6700 for under $500 day before. As long as that trend stays I'm gonna be buying a new GPU by year's end. I'm waiting to see what the 7000 series brings...which would be an ironic buy for me since my first modern AMD GPU was a rebranded 7000 HD series (R7 260x). I feel like I'll be coming full circle.

    Reading about the 7000 series bringing in extra circuits for FSR3 and potential machine learning has peaked my interests some.
    I did shit myself when I came home from work. After I installed the new GPU my motherboard decided to play a prank on me ("haha, I will not start :-P"). Thank God it was only a memory stick problem, because of high humidity (cleaned it and is now working).

    Apart from the obscene jump in gaming performance from my rumble RX550, the hardware video decoding is a sight to behold: in Firefox, AV1 codec 4k60 videos now play with minimal (~5%) CPU utilization. Although I'm noticing some hiccups in some VP9 videos. Hopefully those will be corrected soon on a new Firefox release or on the GPU driver side.

    Leave a comment:


  • skeevy420
    replied
    Originally posted by bridgman View Post
    What we are doing is taking the (multi-OS but primarily developed for Windows) closed source driver and periodically sanitizing a snapshot of the code required for a Linux build. The shader compiler code is different from the closed source version but is based on the same back end we use for open source graphics drivers and the ROCm stack.
    Because of that I've always wondered if AMDVLK (and Pro) would run console ports better. I assume the consoles use AMDVLK Pro or something very close to it.

    Not games designed with cross play or crossplatform in mind, but actual console games that moved to PC a year or more later. About the only modern ones that I have are FFVIIR and Death Stranding. I might experiment with that this weekend.

    Leave a comment:


  • skeevy420
    replied
    Originally posted by M@GOid View Post
    Nice to see that my new RX 6600 will be mostly trouble free the moment I plug it in the afternoon. After 2 agonizing years, I finally managed to grab a new GPU for a reasonable price.
    I about shit myself when I saw a 6700 for under $500 day before. As long as that trend stays I'm gonna be buying a new GPU by year's end. I'm waiting to see what the 7000 series brings...which would be an ironic buy for me since my first modern AMD GPU was a rebranded 7000 HD series (R7 260x). I feel like I'll be coming full circle.

    Reading about the 7000 series bringing in extra circuits for FSR3 and potential machine learning has peaked my interests some.

    Leave a comment:


  • mahurinj
    replied
    Originally posted by bridgman View Post

    As far as I know we are not and have never developed a separate open source Vulkan driver - if we had it would look a lot like RADV although it probably would not have ACO yet.

    What we are doing is taking the (multi-OS but primarily developed for Windows) closed source driver and periodically sanitizing a snapshot of the code required for a Linux build. The shader compiler code is different from the closed source version but is based on the same back end we use for open source graphics drivers and the ROCm stack.
    Aaahhh I see okay that makes more sense thank you

    Leave a comment:


  • bridgman
    replied
    Originally posted by mahurinj View Post
    Is there a reason for AMD to continue developing a separate open source driver rather than just contributing to the RADV driver and blessing that as the official supported version?
    As far as I know we are not and have never developed a separate open source Vulkan driver - if we had it would look a lot like RADV although it probably would not have ACO yet.

    What we are doing is taking the (multi-OS but primarily developed for Windows) closed source driver and periodically sanitizing a snapshot of the code required for a Linux build. The shader compiler code is different from the closed source version but is based on the same back end we use for open source graphics drivers and the ROCm stack.
    Last edited by bridgman; 28 June 2022, 09:20 PM.

    Leave a comment:


  • tildearrow
    replied
    But with AMDVLK using the LLVM AMDGPU shader compiler rather than their in-house proprietary shader compiler
    Imagine AMDVLK with ACO...

    Leave a comment:


  • M@GOid
    replied
    Originally posted by dimko View Post

    Aamen. Albeit i was lucky, in between covid years i managed to grab 5700XT at MSRP.
    Got mine in a flash sale. After a couple hours they where gone.

    Leave a comment:


  • dimko
    replied
    Originally posted by M@GOid View Post
    Nice to see that my new RX 6600 will be mostly trouble free the moment I plug it in the afternoon. After 2 agonizing years, I finally managed to grab a new GPU for a reasonable price.
    Aamen. Albeit i was lucky, in between covid years i managed to grab 5700XT at MSRP.

    Leave a comment:


  • mahurinj
    replied
    Is there a reason for AMD to continue developing a separate open source driver rather than just contributing to the RADV driver and blessing that as the official supported version?

    Leave a comment:


  • M@GOid
    replied
    Nice to see that my new RX 6600 will be mostly trouble free the moment I plug it in the afternoon. After 2 agonizing years, I finally managed to grab a new GPU for a reasonable price.

    Leave a comment:

Working...
X