Skip to content

Pre-duplicate kernel values in ResizeKernelMap for faster FMA convolution #1515

New issue
New issue
Open
grepdemos/ImageSharp
#3
#2793
Open
Pre-duplicate kernel values in ResizeKernelMap for faster FMA convolution#1515
grepdemos/ImageSharp
#3
#2793
Labels
area:performanceup-for-grabs
Milestone
 
Future
@antonfirsov

Description

@antonfirsov
antonfirsov
opened on Jan 21, 2021
Member

As @saucecontrol pointed out in his comment, we can get rid of VPERMS in the following code:

ImageSharp/src/ImageSharp/Processing/Processors/Transforms/Resize/ResizeKernel.cs

Lines 104 to 112 in e2211c3

result256_0 = Fma.MultiplyAdd(
Unsafe.As<Vector4, Vector256<float>>(ref rowStartRef),
Avx2.PermuteVar8x32(Vector256.CreateScalarUnsafe(*(double*)bufferStart).AsSingle(), mask),
result256_0);
result256_1 = Fma.MultiplyAdd(
Unsafe.As<Vector4, Vector256<float>>(ref Unsafe.Add(ref rowStartRef, 2)),
Avx2.PermuteVar8x32(Vector256.CreateScalarUnsafe(*(double*)(bufferStart + 2)).AsSingle(), mask),
result256_1);

If FMA is detected we should allocate 4x buffer and to the duplication in ResizeKernelMap.Calculate, which should be much cheaper than doing it in every convolution:

ImageSharp/src/ImageSharp/Processing/Processors/Transforms/Resize/ResizeKernelMap.cs

Lines 115 to 120 in e2211c3

public static ResizeKernelMap Calculate<TResampler>(
in TResampler sampler,
int destinationSize,
int sourceSize,
MemoryAllocator memoryAllocator)
where TResampler : struct, IResampler

Activity

antonfirsov
added
needs triage
area:performance
and removed
needs triage
on Jan 21, 2021
antonfirsov
added this to the Future milestone on Jan 21, 2021
antonfirsov
added
up-for-grabs
on Jan 21, 2021
antonfirsov
changed the title [-]Pre-duplicate kernels in ResizeKernelMap for faster FMA convolution[/-] [+]Pre-duplicate kernel values in ResizeKernelMap for faster FMA convolution[/+] on Jan 21, 2021
antonfirsov
mentioned this on Jan 28, 2021
JimBobSquarePants
linked a pull request that will close this issue on Aug 15, 2024
lizard-boy
linked a pull request that will close this issue on Nov 1, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    area:performanceup-for-grabs

    Type

    No type

    Projects

    No projects

    Milestone

    Relationships

    None yet

      Development

      Participants

      @antonfirsov

      Issue actions
        Pre-duplicate kernel values in ResizeKernelMap for faster FMA convolution · Issue #1515 · SixLabors/ImageSharp