home.social

#fluidx3d — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #fluidx3d, aggregated by home.social.

  1. Dr. Moritz Lehmann @[email protected] ·

    Directly found the first issue im #FluidX3D: #OpenCL __attribute__((opencl_unroll_hint(x))) is not supported on AMD's old #GPU driver. Guaranteeing legacy hardware compatibility means testing on legacy hardware. I'm not giving software rot a chance! 🖖🧐
    github.com/ProjectPhysX/FluidX

    #fluidx3d #opencl #gpu
  2. Dr. Moritz Lehmann @[email protected] ·

    Directly found the first issue im #FluidX3D: #OpenCL __attribute__((opencl_unroll_hint(x))) is not supported on AMD's old #GPU driver. Guaranteeing legacy hardware compatibility means testing on legacy hardware. I'm not giving software rot a chance! 🖖🧐
    github.com/ProjectPhysX/FluidX

    #fluidx3d #opencl #gpu
  3. Dr. Moritz Lehmann @[email protected] ·

    Directly found the first issue im #FluidX3D: #OpenCL __attribute__((opencl_unroll_hint(x))) is not supported on AMD's old #GPU driver. Guaranteeing legacy hardware compatibility means testing on legacy hardware. I'm not giving software rot a chance! 🖖🧐
    github.com/ProjectPhysX/FluidX

    #fluidx3d #opencl #gpu
  4. Dr. Moritz Lehmann @[email protected] ·

    Directly found the first issue im #FluidX3D: #OpenCL __attribute__((opencl_unroll_hint(x))) is not supported on AMD's old #GPU driver. Guaranteeing legacy hardware compatibility means testing on legacy hardware. I'm not giving software rot a chance! 🖖🧐
    github.com/ProjectPhysX/FluidX

    #fluidx3d #opencl #gpu
  5. Dr. Moritz Lehmann @[email protected] ·

    Directly found the first issue im #FluidX3D: #OpenCL __attribute__((opencl_unroll_hint(x))) is not supported on AMD's old #GPU driver. Guaranteeing legacy hardware compatibility means testing on legacy hardware. I'm not giving software rot a chance! 🖖🧐
    github.com/ProjectPhysX/FluidX

    #gpu #opencl #fluidx3d
  6. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD v3.7 brings faster Q-criterion isosurface rendering with #OpenCL local memory optimization! 🖖🤠
    github.com/ProjectPhysX/FluidX

    Instead of 32 velocities for each #GPU thread, now an 8x8x8 workgroup loads & reuses 11x11x11 velocities in L1$, a 12x VRAM BW reduction.

    Fascinating insight: Which thread loads which cell from VRAM to L1$, and which thread renders which grid cell within the workgroup, can be very different!
    github.com/ProjectPhysX/FluidX

    PS: plugged X-wing Gif in #GitHub preview 🖖😜

    #fluidx3d #cfd #opencl #gpu #github
  7. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD v3.7 brings faster Q-criterion isosurface rendering with #OpenCL local memory optimization! 🖖🤠
    github.com/ProjectPhysX/FluidX

    Instead of 32 velocities for each #GPU thread, now an 8x8x8 workgroup loads & reuses 11x11x11 velocities in L1$, a 12x VRAM BW reduction.

    Fascinating insight: Which thread loads which cell from VRAM to L1$, and which thread renders which grid cell within the workgroup, can be very different!
    github.com/ProjectPhysX/FluidX

    PS: plugged X-wing Gif in #GitHub preview 🖖😜

    #fluidx3d #cfd #opencl #gpu #github
  8. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD v3.7 brings faster Q-criterion isosurface rendering with #OpenCL local memory optimization! 🖖🤠
    github.com/ProjectPhysX/FluidX

    Instead of 32 velocities for each #GPU thread, now an 8x8x8 workgroup loads & reuses 11x11x11 velocities in L1$, a 12x VRAM BW reduction.

    Fascinating insight: Which thread loads which cell from VRAM to L1$, and which thread renders which grid cell within the workgroup, can be very different!
    github.com/ProjectPhysX/FluidX

    PS: plugged X-wing Gif in #GitHub preview 🖖😜

    #fluidx3d #cfd #opencl #gpu #github
  9. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD v3.7 brings faster Q-criterion isosurface rendering with #OpenCL local memory optimization! 🖖🤠
    github.com/ProjectPhysX/FluidX

    Instead of 32 velocities for each #GPU thread, now an 8x8x8 workgroup loads & reuses 11x11x11 velocities in L1$, a 12x VRAM BW reduction.

    Fascinating insight: Which thread loads which cell from VRAM to L1$, and which thread renders which grid cell within the workgroup, can be very different!
    github.com/ProjectPhysX/FluidX

    PS: plugged X-wing Gif in #GitHub preview 🖖😜

    #fluidx3d #cfd #opencl #gpu #github
  10. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD v3.7 brings faster Q-criterion isosurface rendering with #OpenCL local memory optimization! 🖖🤠
    github.com/ProjectPhysX/FluidX

    Instead of 32 velocities for each #GPU thread, now an 8x8x8 workgroup loads & reuses 11x11x11 velocities in L1$, a 12x VRAM BW reduction.

    Fascinating insight: Which thread loads which cell from VRAM to L1$, and which thread renders which grid cell within the workgroup, can be very different!
    github.com/ProjectPhysX/FluidX

    PS: plugged X-wing Gif in #GitHub preview 🖖😜

    #github #gpu #opencl #cfd #fluidx3d
  11. Dr. Moritz Lehmann @[email protected] ·

    Newest #IntelArc #GPU family member is here, the Panther Lake Arc B390... and it... purrs? 🖖 🥺 🐈‍⬛
    My OpenCL-Benchmark on the B390 measures ~7.4 TFlops FP32 and ~120GB/s memory bandwidth. hw-smi also works with the B390.
    #FluidX3D benchmarks here: github.com/ProjectPhysX/FluidX
    And the #OpenCL infos:
    - Arc B390: opencl.gpuinfo.org/displayrepo
    - Core Ultra X7 358H: opencl.gpuinfo.org/displayrepo

    #intelarc #gpu #fluidx3d #opencl
  12. Dr. Moritz Lehmann @[email protected] ·

    Newest #IntelArc #GPU family member is here, the Panther Lake Arc B390... and it... purrs? 🖖 🥺 🐈‍⬛
    My OpenCL-Benchmark on the B390 measures ~7.4 TFlops FP32 and ~120GB/s memory bandwidth. hw-smi also works with the B390.
    #FluidX3D benchmarks here: github.com/ProjectPhysX/FluidX
    And the #OpenCL infos:
    - Arc B390: opencl.gpuinfo.org/displayrepo
    - Core Ultra X7 358H: opencl.gpuinfo.org/displayrepo

    #intelarc #gpu #fluidx3d #opencl
  13. Dr. Moritz Lehmann @[email protected] ·

    Newest #IntelArc #GPU family member is here, the Panther Lake Arc B390... and it... purrs? 🖖 🥺 🐈‍⬛
    My OpenCL-Benchmark on the B390 measures ~7.4 TFlops FP32 and ~120GB/s memory bandwidth. hw-smi also works with the B390.
    #FluidX3D benchmarks here: github.com/ProjectPhysX/FluidX
    And the #OpenCL infos:
    - Arc B390: opencl.gpuinfo.org/displayrepo
    - Core Ultra X7 358H: opencl.gpuinfo.org/displayrepo

    #intelarc #gpu #fluidx3d #opencl
  14. Dr. Moritz Lehmann @[email protected] ·

    Newest #IntelArc #GPU family member is here, the Panther Lake Arc B390... and it... purrs? 🖖 🥺 🐈‍⬛
    My OpenCL-Benchmark on the B390 measures ~7.4 TFlops FP32 and ~120GB/s memory bandwidth. hw-smi also works with the B390.
    #FluidX3D benchmarks here: github.com/ProjectPhysX/FluidX
    And the #OpenCL infos:
    - Arc B390: opencl.gpuinfo.org/displayrepo
    - Core Ultra X7 358H: opencl.gpuinfo.org/displayrepo

    #intelarc #gpu #fluidx3d #opencl
  15. Dr. Moritz Lehmann @[email protected] ·

    Newest #IntelArc #GPU family member is here, the Panther Lake Arc B390... and it... purrs? 🖖 🥺 🐈‍⬛
    My OpenCL-Benchmark on the B390 measures ~7.4 TFlops FP32 and ~120GB/s memory bandwidth. hw-smi also works with the B390.
    #FluidX3D benchmarks here: github.com/ProjectPhysX/FluidX
    And the #OpenCL infos:
    - Arc B390: opencl.gpuinfo.org/displayrepo
    - Core Ultra X7 358H: opencl.gpuinfo.org/displayrepo

    #opencl #fluidx3d #gpu #intelarc
  16. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD has reached ⭐ 5000 Stargazers on #GitHub! 🖖🥳
    Grid refinement update is still in development, I haven't forgotten... ⬜◻️◽▫️
    github.com/ProjectPhysX/FluidX

    #fluidx3d #cfd #github
  17. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD has reached ⭐ 5000 Stargazers on #GitHub! 🖖🥳
    Grid refinement update is still in development, I haven't forgotten... ⬜◻️◽▫️
    github.com/ProjectPhysX/FluidX

    #fluidx3d #cfd #github
  18. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD has reached ⭐ 5000 Stargazers on #GitHub! 🖖🥳
    Grid refinement update is still in development, I haven't forgotten... ⬜◻️◽▫️
    github.com/ProjectPhysX/FluidX

    #fluidx3d #cfd #github
  19. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD has reached ⭐ 5000 Stargazers on #GitHub! 🖖🥳
    Grid refinement update is still in development, I haven't forgotten... ⬜◻️◽▫️
    github.com/ProjectPhysX/FluidX

    #fluidx3d #cfd #github
  20. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD has reached ⭐ 5000 Stargazers on #GitHub! 🖖🥳
    Grid refinement update is still in development, I haven't forgotten... ⬜◻️◽▫️
    github.com/ProjectPhysX/FluidX

    #github #cfd #fluidx3d
  21. Dr. Moritz Lehmann @[email protected] ·

    Finally Intel #GPU support on Linux too. Watch all the metrics go brrr in multi-GPU #FluidX3D #CFD workload! Will #opensource soon™️

    Hardening against the myriads of broken counters in all those bugged APIs was a long shot. 🖖🫠

    ____________ | Windows | #Linux |
    CPU / RAM | ✅️️WinAPI | ✅️️/proc |
    #Nvidia GPU | ✅️️NVML | ✅️️NVML |
    #Intel GPU | ✅IGCL | ✅SYSMAN |
    #AMD GPU | ✅️️️️ADLX | ✅️️️️AMDSMI |

    #gpu #fluidx3d #cfd #opensource #linux #nvidia
  22. Dr. Moritz Lehmann @[email protected] ·

    Finally Intel #GPU support on Linux too. Watch all the metrics go brrr in multi-GPU #FluidX3D #CFD workload! Will #opensource soon™️

    Hardening against the myriads of broken counters in all those bugged APIs was a long shot. 🖖🫠

    ____________ | Windows | #Linux |
    CPU / RAM | ✅️️WinAPI | ✅️️/proc |
    #Nvidia GPU | ✅️️NVML | ✅️️NVML |
    #Intel GPU | ✅IGCL | ✅SYSMAN |
    #AMD GPU | ✅️️️️ADLX | ✅️️️️AMDSMI |

    #gpu #fluidx3d #cfd #opensource #linux #nvidia
  23. Dr. Moritz Lehmann @[email protected] ·

    Finally Intel #GPU support on Linux too. Watch all the metrics go brrr in multi-GPU #FluidX3D #CFD workload! Will #opensource soon™️

    Hardening against the myriads of broken counters in all those bugged APIs was a long shot. 🖖🫠

    ____________ | Windows | #Linux |
    CPU / RAM | ✅️️WinAPI | ✅️️/proc |
    #Nvidia GPU | ✅️️NVML | ✅️️NVML |
    #Intel GPU | ✅IGCL | ✅SYSMAN |
    #AMD GPU | ✅️️️️ADLX | ✅️️️️AMDSMI |

    #gpu #fluidx3d #cfd #opensource #linux #nvidia
  24. Dr. Moritz Lehmann @[email protected] ·

    Finally Intel #GPU support on Linux too. Watch all the metrics go brrr in multi-GPU #FluidX3D #CFD workload! Will #opensource soon™️

    Hardening against the myriads of broken counters in all those bugged APIs was a long shot. 🖖🫠

    ____________ | Windows | #Linux |
    CPU / RAM | ✅️️WinAPI | ✅️️/proc |
    #Nvidia GPU | ✅️️NVML | ✅️️NVML |
    #Intel GPU | ✅IGCL | ✅SYSMAN |
    #AMD GPU | ✅️️️️ADLX | ✅️️️️AMDSMI |

    #intel #gpu #fluidx3d #cfd #opensource #linux
  25. Dr. Moritz Lehmann @[email protected] ·

    Finally Intel #GPU support on Linux too. Watch all the metrics go brrr in multi-GPU #FluidX3D #CFD workload! Will #opensource soon™️

    Hardening against the myriads of broken counters in all those bugged APIs was a long shot. 🖖🫠

    ____________ | Windows | #Linux |
    CPU / RAM | ✅️️WinAPI | ✅️️/proc |
    #Nvidia GPU | ✅️️NVML | ✅️️NVML |
    #Intel GPU | ✅IGCL | ✅SYSMAN |
    #AMD GPU | ✅️️️️ADLX | ✅️️️️AMDSMI |

    #amd #intel #nvidia #linux #opensource #cfd
  26. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD v3.6 is out! This release accumulates a number of small improvements over the last months. Most notably, better interactive graphics support on #macOS with XQuartz. Have fun! 🖖😎🌊🍏
    github.com/ProjectPhysX/FluidX

    #fluidx3d #cfd #macos
  27. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD v3.6 is out! This release accumulates a number of small improvements over the last months. Most notably, better interactive graphics support on #macOS with XQuartz. Have fun! 🖖😎🌊🍏
    github.com/ProjectPhysX/FluidX

    #fluidx3d #cfd #macos
  28. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD v3.6 is out! This release accumulates a number of small improvements over the last months. Most notably, better interactive graphics support on #macOS with XQuartz. Have fun! 🖖😎🌊🍏
    github.com/ProjectPhysX/FluidX

    #fluidx3d #cfd #macos
  29. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD v3.6 is out! This release accumulates a number of small improvements over the last months. Most notably, better interactive graphics support on #macOS with XQuartz. Have fun! 🖖😎🌊🍏
    github.com/ProjectPhysX/FluidX

    #fluidx3d #cfd #macos
  30. Dr. Moritz Lehmann @[email protected] ·

    #FluidX3D #CFD v3.6 is out! This release accumulates a number of small improvements over the last months. Most notably, better interactive graphics support on #macOS with XQuartz. Have fun! 🖖😎🌊🍏
    github.com/ProjectPhysX/FluidX

    #macos #cfd #fluidx3d
  31. Dr. Moritz Lehmann @[email protected] ·

    Finally, the bars for #Intel hardware in the #FluidX3D #mermaid gantt performance chart are BLUE, as nature intended it.
    github.com/ProjectPhysX/FluidX

    #intel #fluidx3d #mermaid
  32. Dr. Moritz Lehmann @[email protected] ·

    Finally, the bars for #Intel hardware in the #FluidX3D #mermaid gantt performance chart are BLUE, as nature intended it.
    github.com/ProjectPhysX/FluidX

    #intel #fluidx3d #mermaid
  33. Dr. Moritz Lehmann @[email protected] ·

    Finally, the bars for #Intel hardware in the #FluidX3D #mermaid gantt performance chart are BLUE, as nature intended it.
    github.com/ProjectPhysX/FluidX

    #intel #fluidx3d #mermaid
  34. Dr. Moritz Lehmann @[email protected] ·

    Finally, the bars for #Intel hardware in the #FluidX3D #mermaid gantt performance chart are BLUE, as nature intended it.
    github.com/ProjectPhysX/FluidX

    #intel #fluidx3d #mermaid
  35. Dr. Moritz Lehmann @[email protected] ·

    Finally, the bars for #Intel hardware in the #FluidX3D #mermaid gantt performance chart are BLUE, as nature intended it.
    github.com/ProjectPhysX/FluidX

    #mermaid #fluidx3d #intel
  36. Dr. Moritz Lehmann @[email protected] ·

    Some experimentation with ```mermaid ...``` charts in #GitHub #markdown. Turns out you can hack the formatting on the quadrantChart to turn it into an xy-scatter plot with individual point size/coloring/labeling.🖖🧐
    First plot is datasheet memory bandwidth vs. FP32 TFlops/s, second plot is #FluidX3D performance vs. bandwidth, for lots of #GPU​/​#CPU hardware.

    #github #markdown #fluidx3d #gpu #cpu
  37. Dr. Moritz Lehmann @[email protected] ·

    Some experimentation with ```mermaid ...``` charts in #GitHub #markdown. Turns out you can hack the formatting on the quadrantChart to turn it into an xy-scatter plot with individual point size/coloring/labeling.🖖🧐
    First plot is datasheet memory bandwidth vs. FP32 TFlops/s, second plot is #FluidX3D performance vs. bandwidth, for lots of #GPU​/​#CPU hardware.

    #github #markdown #fluidx3d #gpu #cpu
  38. Dr. Moritz Lehmann @[email protected] ·

    Some experimentation with ```mermaid ...``` charts in #GitHub #markdown. Turns out you can hack the formatting on the quadrantChart to turn it into an xy-scatter plot with individual point size/coloring/labeling.🖖🧐
    First plot is datasheet memory bandwidth vs. FP32 TFlops/s, second plot is #FluidX3D performance vs. bandwidth, for lots of #GPU​/​#CPU hardware.

    #github #markdown #fluidx3d #gpu #cpu
  39. Dr. Moritz Lehmann @[email protected] ·

    Some experimentation with ```mermaid ...``` charts in #GitHub #markdown. Turns out you can hack the formatting on the quadrantChart to turn it into an xy-scatter plot with individual point size/coloring/labeling.🖖🧐
    First plot is datasheet memory bandwidth vs. FP32 TFlops/s, second plot is #FluidX3D performance vs. bandwidth, for lots of #GPU​/​#CPU hardware.

    #github #markdown #fluidx3d #gpu #cpu
  40. Dr. Moritz Lehmann @[email protected] ·

    Some experimentation with ```mermaid ...``` charts in #GitHub #markdown. Turns out you can hack the formatting on the quadrantChart to turn it into an xy-scatter plot with individual point size/coloring/labeling.🖖🧐
    First plot is datasheet memory bandwidth vs. FP32 TFlops/s, second plot is #FluidX3D performance vs. bandwidth, for lots of #GPU​/​#CPU hardware.

    #cpu #gpu #fluidx3d #markdown #github
  41. Dr. Moritz Lehmann @[email protected] ·

    Here's me demoing #Intel Arc Pro B60 #GPU workstations at #SC25 in St. Louis, runnig SolidWorks and #FluidX3D! 🖖😎
    youtube.com/watch?v=Z8yxiyXTi7I

    #intel #gpu #sc25 #fluidx3d
  42. Dr. Moritz Lehmann @[email protected] ·

    Here's me demoing #Intel Arc Pro B60 #GPU workstations at #SC25 in St. Louis, runnig SolidWorks and #FluidX3D! 🖖😎
    youtube.com/watch?v=Z8yxiyXTi7I

    #intel #gpu #sc25 #fluidx3d
  43. Dr. Moritz Lehmann @[email protected] ·

    Here's me demoing #Intel Arc Pro B60 #GPU workstations at #SC25 in St. Louis, runnig SolidWorks and #FluidX3D! 🖖😎
    youtube.com/watch?v=Z8yxiyXTi7I

    #intel #gpu #sc25 #fluidx3d
  44. Dr. Moritz Lehmann @[email protected] ·

    Here's me demoing #Intel Arc Pro B60 #GPU workstations at #SC25 in St. Louis, runnig SolidWorks and #FluidX3D! 🖖😎
    youtube.com/watch?v=Z8yxiyXTi7I

    #intel #gpu #sc25 #fluidx3d
  45. Dr. Moritz Lehmann @[email protected] ·

    Here's me demoing #Intel Arc Pro B60 #GPU workstations at #SC25 in St. Louis, runnig SolidWorks and #FluidX3D! 🖖😎
    youtube.com/watch?v=Z8yxiyXTi7I

    #fluidx3d #sc25 #gpu #intel
  46. Dr. Moritz Lehmann @[email protected] ·

    Making progress on >top secret #FluidX3D update< but still a long way to go 🖖🧐

    #fluidx3d
  47. Dr. Moritz Lehmann @[email protected] ·

    Making progress on >top secret #FluidX3D update< but still a long way to go 🖖🧐

    #fluidx3d
  48. Dr. Moritz Lehmann @[email protected] ·

    Making progress on >top secret #FluidX3D update< but still a long way to go 🖖🧐

    #fluidx3d
  49. Dr. Moritz Lehmann @[email protected] ·

    Making progress on >top secret #FluidX3D update< but still a long way to go 🖖🧐

    #fluidx3d
  50. Dr. Moritz Lehmann @[email protected] ·

    Making progress on >top secret #FluidX3D update< but still a long way to go 🖖🧐

    #fluidx3d