Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.#103244

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
michaelgsharp merged 7 commits into from
Jun 20, 2024
Merged

Changed TensorSpan and ReadOnlyTensorSpan layout for better performance. #103244

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
aa617ec
TensorShape
michaelgsharp Jun 10, 2024
c4acef8
fixed TensorShape issue
michaelgsharp Jun 10, 2024
c02fd92
removed extra inline buffer type. Fixed tests. Added large dimension …
michaelgsharp Jun 11, 2024
fb64487
removed typo
michaelgsharp Jun 11, 2024
35dc2cf
adding unsaved files
michaelgsharp Jun 11, 2024
5053a67
changes to use const for stack alloc comparison
michaelgsharp Jun 11, 2024
63bc01d
changes from pr comments
michaelgsharp Jun 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions src/libraries/System.Numerics.Tensors/src/System.Numerics.Tensors.csproj
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
</ItemGroup>

<ItemGroup Condition="'$(TargetFrameworkIdentifier)' == '.NETCoreApp'">
<Compile Include="System\Numerics\Tensors\netcore\TensorShape.cs" />
<Compile Include="System\Numerics\Tensors\netcore\TensorHelpers.cs" />
<Compile Include="System\Numerics\Tensors\netcore\TensorExtensions.cs" />
<Compile Include="System\Numerics\Tensors\netcore\Tensor.Factory.cs" />
Expand Down
129 changes: 51 additions & 78 deletions ...braries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/ReadOnlyTensorSpan.cs
View file
Open in desktop

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/Tensor.Factory.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -153,16 +153,16 @@ public static Tensor<T> CreateUninitialized<T>(scoped ReadOnlySpan<nint> lengths

public static ref readonly TensorSpan<T> FillGaussianNormalDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
{
Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

GaussianDistribution<T>(span, destination._flattenedLength);
GaussianDistribution<T>(span, destination._shape._memoryLength);

return ref destination;
}

public static ref readonly TensorSpan<T> FillUniformDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
{
Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

for (int i = 0; i < span.Length; i++)
span[i] = T.CreateChecked(Random.Shared.NextDouble());
Expand Down
191 changes: 95 additions & 96 deletions ...libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorExtensions.cs
View file
Open in desktop

Large diffs are not rendered by default.

11 changes: 7 additions & 4 deletions src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorHelpers.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -17,7 +17,7 @@ internal static class TensorHelpers
/// <returns>How many boolean values are true.</returns>
public static nint CountTrueElements(scoped in ReadOnlyTensorSpan<bool> filter)
{
Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._flattenedLength);
Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._shape._memoryLength);
nint count = 0;
for (int i = 0; i < filterSpan.Length; i++)
{
Expand DownExpand Up@@ -83,11 +83,14 @@ internal static nint[] GetIntermediateShape(ReadOnlySpan<nint> shape1, int shape
return newShape;
}

internal static bool IsUnderlyingStorageSameSize<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
=> tensor1._shape._memoryLength == tensor2._shape._memoryLength;

internal static bool IsUnderlyingStorageSameSize<T>(Tensor<T> tensor1, Tensor<T> tensor2)
=> tensor1.Lengths.Length == tensor2.Lengths.Length;
=> tensor1._values.Length == tensor2._values.Length;

internal static bool AreLengthsTheSame<T>(ReadOnlyTensorSpan<T> tensor1, ReadOnlyTensorSpan<T> tensor2)
=> tensor1._lengths.SequenceEqual(tensor2._lengths);
internal static bool AreLengthsTheSame<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
=> tensor1.Lengths.SequenceEqual(tensor2.Lengths);

internal static bool AreLengthsTheSame(ReadOnlySpan<nint> lengths1, ReadOnlySpan<nint> lengths2)
=> lengths1.SequenceEqual(lengths2);
Expand Down
64 changes: 64 additions & 0 deletions src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorShape.cs
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,64 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.

using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;

namespace System.Numerics.Tensors
{
internal readonly struct TensorShape

@eiriktsarpaliseiriktsarpalisJun 19, 2024

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could this also be a ref struct?

@tannergoodingtannergoodingJun 19, 2024

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We want to be able to use the same struct as part of Tensor<T> so we can avoid additional allocations for common cases there as well.

{
// Used to determine when we need to allocate a metadata array
public const int MaxInlineArraySize = 5;

// Used to determine when we can stack alloc for indexing vs when we need to allocate
public const int MaxInlineRank = 8;

internal readonly nint[]? _metadata; // 8 bytes

internal readonly nint _memoryLength; // 8 bytes

@eiriktsarpaliseiriktsarpalisJun 19, 2024•
edited
Loading

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Given the layout and size concerns of this change, does the new type require an explicit StructLayoutAttribute annotation? Are we ok with using the default layout? Is there an expectation that the fields will be consumed by unmanaged code.

@tannergoodingtannergoodingJun 19, 2024

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).

@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).

Does Mono behave the same? I think it might respect Sequential for managed types.

@tannergoodingtannergoodingJun 19, 2024

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.

That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).

This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.

@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.

That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).

This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.

Yeah but I've meant that Auto could maybe still be beneficial for Mono.

@tannergoodingtannergoodingJun 19, 2024

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mono should likely consider adjusting their layout algorithm to match the RyuJIT algorithm in that scenario.

There are thousands of structs across the BCL and we are not going to go and annotate every single one of them to be explicitly Auto because they contain some managed field.

internal readonly int _rank; // 4 bytes

private readonly NintBuffer _lengths;
private readonly NintBuffer _strides;

internal TensorShape(nint memoryLength, ReadOnlySpan<nint> lengths, ReadOnlySpan<nint> strides)
{
_memoryLength = memoryLength;
_rank = lengths.Length;
if (lengths.Length > MaxInlineArraySize)
{
_metadata = new nint[lengths.Length + strides.Length];
lengths.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[0], lengths.Length));
strides.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[lengths.Length], strides.Length));
}
else
{
lengths.CopyTo(_lengths);
strides.CopyTo(_strides);
}
}

[InlineArray(MaxInlineArraySize)] // 5x8 bytes (40)
private struct NintBuffer
{
public nint e0;
}

[UnscopedRef]
public ReadOnlySpan<nint> Lengths => (_metadata is null)
? ((ReadOnlySpan<nint>)_lengths).Slice(0, _rank)
: MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank);

[UnscopedRef]
public ReadOnlySpan<nint> Strides => (_metadata is null)
? ((ReadOnlySpan<nint>)_strides).Slice(0, _rank)
: MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank * 2).Slice(_rank);

public nint FlattenedLength => TensorSpanHelpers.CalculateTotalLength(Lengths);

public bool IsEmpty => FlattenedLength == 0;
}
}
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.#103244

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

michaelgsharp
merged 7 commits into

from

Jun 20, 2024
 Merged


Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.
#103244
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
aa617ec

TensorShape


michaelgsharp Jun 10, 2024
c4acef8

fixed TensorShape issue


michaelgsharp Jun 10, 2024
c02fd92

removed extra inline buffer type. Fixed tests. Added large dimension …


michaelgsharp Jun 11, 2024
fb64487

removed typo


michaelgsharp Jun 11, 2024
35dc2cf

adding unsaved files


michaelgsharp Jun 11, 2024
5053a67

changes to use const for stack alloc comparison


michaelgsharp Jun 11, 2024
63bc01d

changes from pr comments


michaelgsharp Jun 20, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


1 change: 1 addition & 0 deletions
src/libraries/System.Numerics.Tensors/src/System.Numerics.Tensors.csproj

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
 </ItemGroup>

 <ItemGroup Condition="'$(TargetFrameworkIdentifier)' == '.NETCoreApp'">
 <Compile Include="System\Numerics\Tensors\netcore\TensorShape.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\TensorHelpers.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\TensorExtensions.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\Tensor.Factory.cs" />
Expand Down

129 changes: 51 additions & 78 deletions
...braries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/ReadOnlyTensorSpan.cs

View file


Open in desktop


Large diffs are not rendered by default.


6 changes: 3 additions & 3 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/Tensor.Factory.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -153,16 +153,16 @@ public static Tensor<T> CreateUninitialized<T>(scoped ReadOnlySpan<nint> lengths

 public static ref readonly TensorSpan<T> FillGaussianNormalDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
 {
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

 GaussianDistribution<T>(span, destination._flattenedLength);
 GaussianDistribution<T>(span, destination._shape._memoryLength);

 return ref destination;
 }

 public static ref readonly TensorSpan<T> FillUniformDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
 {
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

 for (int i = 0; i < span.Length; i++)
 span[i] = T.CreateChecked(Random.Shared.NextDouble());
Expand Down

191 changes: 95 additions & 96 deletions
...libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorExtensions.cs

View file


Open in desktop


Large diffs are not rendered by default.


11 changes: 7 additions & 4 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorHelpers.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -17,7 +17,7 @@ internal static class TensorHelpers
 /// <returns>How many boolean values are true.</returns>
 public static nint CountTrueElements(scoped in ReadOnlyTensorSpan<bool> filter)
 {
 Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._flattenedLength);
 Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._shape._memoryLength);
 nint count = 0;
 for (int i = 0; i < filterSpan.Length; i++)
 {
Expand DownExpand Up@@ -83,11 +83,14 @@ internal static nint[] GetIntermediateShape(ReadOnlySpan<nint> shape1, int shape
 return newShape;
 }

 internal static bool IsUnderlyingStorageSameSize<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
 => tensor1._shape._memoryLength == tensor2._shape._memoryLength;

 internal static bool IsUnderlyingStorageSameSize<T>(Tensor<T> tensor1, Tensor<T> tensor2)
=> tensor1.Lengths.Length == tensor2.Lengths.Length;
 => tensor1._values.Length == tensor2._values.Length;

 internal static bool AreLengthsTheSame<T>(ReadOnlyTensorSpan<T> tensor1, ReadOnlyTensorSpan<T> tensor2)
 => tensor1._lengths.SequenceEqual(tensor2._lengths);
 internal static bool AreLengthsTheSame<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
 => tensor1.Lengths.SequenceEqual(tensor2.Lengths);

 internal static bool AreLengthsTheSame(ReadOnlySpan<nint> lengths1, ReadOnlySpan<nint> lengths2)
 => lengths1.SequenceEqual(lengths2);
Expand Down

64 changes: 64 additions & 0 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorShape.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,64 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.

using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;

namespace System.Numerics.Tensors
{
 internal readonly struct TensorShape
@eiriktsarpaliseiriktsarpalisJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could this also be a ref struct?
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We want to be able to use the same struct as part of Tensor<T> so we can avoid additional allocations for common cases there as well.
 {
 // Used to determine when we need to allocate a metadata array
 public const int MaxInlineArraySize = 5;

 // Used to determine when we can stack alloc for indexing vs when we need to allocate
 public const int MaxInlineRank = 8;

 internal readonly nint[]? _metadata; // 8 bytes

 internal readonly nint _memoryLength; // 8 bytes
@eiriktsarpaliseiriktsarpalisJun 19, 2024•

edited

Loading

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Given the layout and size concerns of this change, does the new type require an explicit StructLayoutAttribute annotation? Are we ok with using the default layout? Is there an expectation that the fields will be consumed by unmanaged code.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).
@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).
Does Mono behave the same? I think it might respect Sequential for managed types.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.
That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).
This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.
@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.
That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).
This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.
Yeah but I've meant that Auto could maybe still be beneficial for Mono.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mono should likely consider adjusting their layout algorithm to match the RyuJIT algorithm in that scenario.
There are thousands of structs across the BCL and we are not going to go and annotate every single one of them to be explicitly Auto because they contain some managed field.
 internal readonly int _rank; // 4 bytes

 private readonly NintBuffer _lengths;
 private readonly NintBuffer _strides;

 internal TensorShape(nint memoryLength, ReadOnlySpan<nint> lengths, ReadOnlySpan<nint> strides)
 {
 _memoryLength = memoryLength;
 _rank = lengths.Length;
 if (lengths.Length > MaxInlineArraySize)
 {
 _metadata = new nint[lengths.Length + strides.Length];
 lengths.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[0], lengths.Length));
 strides.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[lengths.Length], strides.Length));
 }
 else
 {
 lengths.CopyTo(_lengths);
 strides.CopyTo(_strides);
 }
 }

 [InlineArray(MaxInlineArraySize)] // 5x8 bytes (40)
 private struct NintBuffer
 {
 public nint e0;
 }

 [UnscopedRef]
 public ReadOnlySpan<nint> Lengths => (_metadata is null)
 ? ((ReadOnlySpan<nint>)_lengths).Slice(0, _rank)
 : MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank);

 [UnscopedRef]
 public ReadOnlySpan<nint> Strides => (_metadata is null)
 ? ((ReadOnlySpan<nint>)_strides).Slice(0, _rank)
 : MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank * 2).Slice(_rank);

 public nint FlattenedLength => TensorSpanHelpers.CalculateTotalLength(Lengths);

 public bool IsEmpty => FlattenedLength == 0;
 }
}
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.#103244

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

michaelgsharp
merged 7 commits into

from

Jun 20, 2024
 Merged


Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.
#103244
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
aa617ec

TensorShape


michaelgsharp Jun 10, 2024
c4acef8

fixed TensorShape issue


michaelgsharp Jun 10, 2024
c02fd92

removed extra inline buffer type. Fixed tests. Added large dimension …


michaelgsharp Jun 11, 2024
fb64487

removed typo


michaelgsharp Jun 11, 2024
35dc2cf

adding unsaved files


michaelgsharp Jun 11, 2024
5053a67

changes to use const for stack alloc comparison


michaelgsharp Jun 11, 2024
63bc01d

changes from pr comments


michaelgsharp Jun 20, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


1 change: 1 addition & 0 deletions
src/libraries/System.Numerics.Tensors/src/System.Numerics.Tensors.csproj

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
 </ItemGroup>

 <ItemGroup Condition="'$(TargetFrameworkIdentifier)' == '.NETCoreApp'">
 <Compile Include="System\Numerics\Tensors\netcore\TensorShape.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\TensorHelpers.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\TensorExtensions.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\Tensor.Factory.cs" />
Expand Down

129 changes: 51 additions & 78 deletions
...braries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/ReadOnlyTensorSpan.cs

View file


Open in desktop


Large diffs are not rendered by default.


6 changes: 3 additions & 3 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/Tensor.Factory.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -153,16 +153,16 @@ public static Tensor<T> CreateUninitialized<T>(scoped ReadOnlySpan<nint> lengths

 public static ref readonly TensorSpan<T> FillGaussianNormalDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
 {
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

 GaussianDistribution<T>(span, destination._flattenedLength);
 GaussianDistribution<T>(span, destination._shape._memoryLength);

 return ref destination;
 }

 public static ref readonly TensorSpan<T> FillUniformDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
 {
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

 for (int i = 0; i < span.Length; i++)
 span[i] = T.CreateChecked(Random.Shared.NextDouble());
Expand Down

191 changes: 95 additions & 96 deletions
...libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorExtensions.cs

View file


Open in desktop


Large diffs are not rendered by default.


11 changes: 7 additions & 4 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorHelpers.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -17,7 +17,7 @@ internal static class TensorHelpers
 /// <returns>How many boolean values are true.</returns>
 public static nint CountTrueElements(scoped in ReadOnlyTensorSpan<bool> filter)
 {
 Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._flattenedLength);
 Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._shape._memoryLength);
 nint count = 0;
 for (int i = 0; i < filterSpan.Length; i++)
 {
Expand DownExpand Up@@ -83,11 +83,14 @@ internal static nint[] GetIntermediateShape(ReadOnlySpan<nint> shape1, int shape
 return newShape;
 }

 internal static bool IsUnderlyingStorageSameSize<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
 => tensor1._shape._memoryLength == tensor2._shape._memoryLength;

 internal static bool IsUnderlyingStorageSameSize<T>(Tensor<T> tensor1, Tensor<T> tensor2)
=> tensor1.Lengths.Length == tensor2.Lengths.Length;
 => tensor1._values.Length == tensor2._values.Length;

 internal static bool AreLengthsTheSame<T>(ReadOnlyTensorSpan<T> tensor1, ReadOnlyTensorSpan<T> tensor2)
 => tensor1._lengths.SequenceEqual(tensor2._lengths);
 internal static bool AreLengthsTheSame<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
 => tensor1.Lengths.SequenceEqual(tensor2.Lengths);

 internal static bool AreLengthsTheSame(ReadOnlySpan<nint> lengths1, ReadOnlySpan<nint> lengths2)
 => lengths1.SequenceEqual(lengths2);
Expand Down

64 changes: 64 additions & 0 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorShape.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,64 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.

using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;

namespace System.Numerics.Tensors
{
 internal readonly struct TensorShape
@eiriktsarpaliseiriktsarpalisJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could this also be a ref struct?
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We want to be able to use the same struct as part of Tensor<T> so we can avoid additional allocations for common cases there as well.
 {
 // Used to determine when we need to allocate a metadata array
 public const int MaxInlineArraySize = 5;

 // Used to determine when we can stack alloc for indexing vs when we need to allocate
 public const int MaxInlineRank = 8;

 internal readonly nint[]? _metadata; // 8 bytes

 internal readonly nint _memoryLength; // 8 bytes
@eiriktsarpaliseiriktsarpalisJun 19, 2024•

edited

Loading

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Given the layout and size concerns of this change, does the new type require an explicit StructLayoutAttribute annotation? Are we ok with using the default layout? Is there an expectation that the fields will be consumed by unmanaged code.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).
@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).
Does Mono behave the same? I think it might respect Sequential for managed types.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.
That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).
This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.
@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.
That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).
This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.
Yeah but I've meant that Auto could maybe still be beneficial for Mono.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mono should likely consider adjusting their layout algorithm to match the RyuJIT algorithm in that scenario.
There are thousands of structs across the BCL and we are not going to go and annotate every single one of them to be explicitly Auto because they contain some managed field.
 internal readonly int _rank; // 4 bytes

 private readonly NintBuffer _lengths;
 private readonly NintBuffer _strides;

 internal TensorShape(nint memoryLength, ReadOnlySpan<nint> lengths, ReadOnlySpan<nint> strides)
 {
 _memoryLength = memoryLength;
 _rank = lengths.Length;
 if (lengths.Length > MaxInlineArraySize)
 {
 _metadata = new nint[lengths.Length + strides.Length];
 lengths.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[0], lengths.Length));
 strides.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[lengths.Length], strides.Length));
 }
 else
 {
 lengths.CopyTo(_lengths);
 strides.CopyTo(_strides);
 }
 }

 [InlineArray(MaxInlineArraySize)] // 5x8 bytes (40)
 private struct NintBuffer
 {
 public nint e0;
 }

 [UnscopedRef]
 public ReadOnlySpan<nint> Lengths => (_metadata is null)
 ? ((ReadOnlySpan<nint>)_lengths).Slice(0, _rank)
 : MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank);

 [UnscopedRef]
 public ReadOnlySpan<nint> Strides => (_metadata is null)
 ? ((ReadOnlySpan<nint>)_strides).Slice(0, _rank)
 : MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank * 2).Slice(_rank);

 public nint FlattenedLength => TensorSpanHelpers.CalculateTotalLength(Lengths);

 public bool IsEmpty => FlattenedLength == 0;
 }
}
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.#103244

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

michaelgsharp
merged 7 commits into

from

Jun 20, 2024
 Merged


Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.
#103244
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
aa617ec

TensorShape


michaelgsharp Jun 10, 2024
c4acef8

fixed TensorShape issue


michaelgsharp Jun 10, 2024
c02fd92

removed extra inline buffer type. Fixed tests. Added large dimension …


michaelgsharp Jun 11, 2024
fb64487

removed typo


michaelgsharp Jun 11, 2024
35dc2cf

adding unsaved files


michaelgsharp Jun 11, 2024
5053a67

changes to use const for stack alloc comparison


michaelgsharp Jun 11, 2024
63bc01d

changes from pr comments


michaelgsharp Jun 20, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


1 change: 1 addition & 0 deletions
src/libraries/System.Numerics.Tensors/src/System.Numerics.Tensors.csproj

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
 </ItemGroup>

 <ItemGroup Condition="'$(TargetFrameworkIdentifier)' == '.NETCoreApp'">
 <Compile Include="System\Numerics\Tensors\netcore\TensorShape.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\TensorHelpers.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\TensorExtensions.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\Tensor.Factory.cs" />
Expand Down

129 changes: 51 additions & 78 deletions
...braries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/ReadOnlyTensorSpan.cs

View file


Open in desktop


Large diffs are not rendered by default.


6 changes: 3 additions & 3 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/Tensor.Factory.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -153,16 +153,16 @@ public static Tensor<T> CreateUninitialized<T>(scoped ReadOnlySpan<nint> lengths

 public static ref readonly TensorSpan<T> FillGaussianNormalDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
 {
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

 GaussianDistribution<T>(span, destination._flattenedLength);
 GaussianDistribution<T>(span, destination._shape._memoryLength);

 return ref destination;
 }

 public static ref readonly TensorSpan<T> FillUniformDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
 {
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

 for (int i = 0; i < span.Length; i++)
 span[i] = T.CreateChecked(Random.Shared.NextDouble());
Expand Down

191 changes: 95 additions & 96 deletions
...libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorExtensions.cs

View file


Open in desktop


Large diffs are not rendered by default.


11 changes: 7 additions & 4 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorHelpers.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -17,7 +17,7 @@ internal static class TensorHelpers
 /// <returns>How many boolean values are true.</returns>
 public static nint CountTrueElements(scoped in ReadOnlyTensorSpan<bool> filter)
 {
 Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._flattenedLength);
 Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._shape._memoryLength);
 nint count = 0;
 for (int i = 0; i < filterSpan.Length; i++)
 {
Expand DownExpand Up@@ -83,11 +83,14 @@ internal static nint[] GetIntermediateShape(ReadOnlySpan<nint> shape1, int shape
 return newShape;
 }

 internal static bool IsUnderlyingStorageSameSize<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
 => tensor1._shape._memoryLength == tensor2._shape._memoryLength;

 internal static bool IsUnderlyingStorageSameSize<T>(Tensor<T> tensor1, Tensor<T> tensor2)
=> tensor1.Lengths.Length == tensor2.Lengths.Length;
 => tensor1._values.Length == tensor2._values.Length;

 internal static bool AreLengthsTheSame<T>(ReadOnlyTensorSpan<T> tensor1, ReadOnlyTensorSpan<T> tensor2)
 => tensor1._lengths.SequenceEqual(tensor2._lengths);
 internal static bool AreLengthsTheSame<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
 => tensor1.Lengths.SequenceEqual(tensor2.Lengths);

 internal static bool AreLengthsTheSame(ReadOnlySpan<nint> lengths1, ReadOnlySpan<nint> lengths2)
 => lengths1.SequenceEqual(lengths2);
Expand Down

64 changes: 64 additions & 0 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorShape.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,64 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.

using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;

namespace System.Numerics.Tensors
{
 internal readonly struct TensorShape
@eiriktsarpaliseiriktsarpalisJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could this also be a ref struct?
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We want to be able to use the same struct as part of Tensor<T> so we can avoid additional allocations for common cases there as well.
 {
 // Used to determine when we need to allocate a metadata array
 public const int MaxInlineArraySize = 5;

 // Used to determine when we can stack alloc for indexing vs when we need to allocate
 public const int MaxInlineRank = 8;

 internal readonly nint[]? _metadata; // 8 bytes

 internal readonly nint _memoryLength; // 8 bytes
@eiriktsarpaliseiriktsarpalisJun 19, 2024•

edited

Loading

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Given the layout and size concerns of this change, does the new type require an explicit StructLayoutAttribute annotation? Are we ok with using the default layout? Is there an expectation that the fields will be consumed by unmanaged code.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).
@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).
Does Mono behave the same? I think it might respect Sequential for managed types.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.
That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).
This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.
@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.
That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).
This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.
Yeah but I've meant that Auto could maybe still be beneficial for Mono.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mono should likely consider adjusting their layout algorithm to match the RyuJIT algorithm in that scenario.
There are thousands of structs across the BCL and we are not going to go and annotate every single one of them to be explicitly Auto because they contain some managed field.
 internal readonly int _rank; // 4 bytes

 private readonly NintBuffer _lengths;
 private readonly NintBuffer _strides;

 internal TensorShape(nint memoryLength, ReadOnlySpan<nint> lengths, ReadOnlySpan<nint> strides)
 {
 _memoryLength = memoryLength;
 _rank = lengths.Length;
 if (lengths.Length > MaxInlineArraySize)
 {
 _metadata = new nint[lengths.Length + strides.Length];
 lengths.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[0], lengths.Length));
 strides.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[lengths.Length], strides.Length));
 }
 else
 {
 lengths.CopyTo(_lengths);
 strides.CopyTo(_strides);
 }
 }

 [InlineArray(MaxInlineArraySize)] // 5x8 bytes (40)
 private struct NintBuffer
 {
 public nint e0;
 }

 [UnscopedRef]
 public ReadOnlySpan<nint> Lengths => (_metadata is null)
 ? ((ReadOnlySpan<nint>)_lengths).Slice(0, _rank)
 : MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank);

 [UnscopedRef]
 public ReadOnlySpan<nint> Strides => (_metadata is null)
 ? ((ReadOnlySpan<nint>)_strides).Slice(0, _rank)
 : MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank * 2).Slice(_rank);

 public nint FlattenedLength => TensorSpanHelpers.CalculateTotalLength(Lengths);

 public bool IsEmpty => FlattenedLength == 0;
 }
}
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.#103244

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

michaelgsharp
merged 7 commits into

from

Jun 20, 2024
 Merged


Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.
#103244
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
aa617ec

TensorShape


michaelgsharp Jun 10, 2024
c4acef8

fixed TensorShape issue


michaelgsharp Jun 10, 2024
c02fd92

removed extra inline buffer type. Fixed tests. Added large dimension …


michaelgsharp Jun 11, 2024
fb64487

removed typo


michaelgsharp Jun 11, 2024
35dc2cf

adding unsaved files


michaelgsharp Jun 11, 2024
5053a67

changes to use const for stack alloc comparison


michaelgsharp Jun 11, 2024
63bc01d

changes from pr comments


michaelgsharp Jun 20, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


1 change: 1 addition & 0 deletions
src/libraries/System.Numerics.Tensors/src/System.Numerics.Tensors.csproj

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
 </ItemGroup>

 <ItemGroup Condition="'$(TargetFrameworkIdentifier)' == '.NETCoreApp'">
 <Compile Include="System\Numerics\Tensors\netcore\TensorShape.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\TensorHelpers.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\TensorExtensions.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\Tensor.Factory.cs" />
Expand Down

129 changes: 51 additions & 78 deletions
...braries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/ReadOnlyTensorSpan.cs

View file


Open in desktop


Large diffs are not rendered by default.


6 changes: 3 additions & 3 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/Tensor.Factory.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -153,16 +153,16 @@ public static Tensor<T> CreateUninitialized<T>(scoped ReadOnlySpan<nint> lengths

 public static ref readonly TensorSpan<T> FillGaussianNormalDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
 {
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

 GaussianDistribution<T>(span, destination._flattenedLength);
 GaussianDistribution<T>(span, destination._shape._memoryLength);

 return ref destination;
 }

 public static ref readonly TensorSpan<T> FillUniformDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
 {
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

 for (int i = 0; i < span.Length; i++)
 span[i] = T.CreateChecked(Random.Shared.NextDouble());
Expand Down

191 changes: 95 additions & 96 deletions
...libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorExtensions.cs

View file


Open in desktop


Large diffs are not rendered by default.


11 changes: 7 additions & 4 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorHelpers.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -17,7 +17,7 @@ internal static class TensorHelpers
 /// <returns>How many boolean values are true.</returns>
 public static nint CountTrueElements(scoped in ReadOnlyTensorSpan<bool> filter)
 {
 Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._flattenedLength);
 Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._shape._memoryLength);
 nint count = 0;
 for (int i = 0; i < filterSpan.Length; i++)
 {
Expand DownExpand Up@@ -83,11 +83,14 @@ internal static nint[] GetIntermediateShape(ReadOnlySpan<nint> shape1, int shape
 return newShape;
 }

 internal static bool IsUnderlyingStorageSameSize<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
 => tensor1._shape._memoryLength == tensor2._shape._memoryLength;

 internal static bool IsUnderlyingStorageSameSize<T>(Tensor<T> tensor1, Tensor<T> tensor2)
=> tensor1.Lengths.Length == tensor2.Lengths.Length;
 => tensor1._values.Length == tensor2._values.Length;

 internal static bool AreLengthsTheSame<T>(ReadOnlyTensorSpan<T> tensor1, ReadOnlyTensorSpan<T> tensor2)
 => tensor1._lengths.SequenceEqual(tensor2._lengths);
 internal static bool AreLengthsTheSame<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
 => tensor1.Lengths.SequenceEqual(tensor2.Lengths);

 internal static bool AreLengthsTheSame(ReadOnlySpan<nint> lengths1, ReadOnlySpan<nint> lengths2)
 => lengths1.SequenceEqual(lengths2);
Expand Down

64 changes: 64 additions & 0 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorShape.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,64 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.

using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;

namespace System.Numerics.Tensors
{
 internal readonly struct TensorShape
@eiriktsarpaliseiriktsarpalisJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could this also be a ref struct?
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We want to be able to use the same struct as part of Tensor<T> so we can avoid additional allocations for common cases there as well.
 {
 // Used to determine when we need to allocate a metadata array
 public const int MaxInlineArraySize = 5;

 // Used to determine when we can stack alloc for indexing vs when we need to allocate
 public const int MaxInlineRank = 8;

 internal readonly nint[]? _metadata; // 8 bytes

 internal readonly nint _memoryLength; // 8 bytes
@eiriktsarpaliseiriktsarpalisJun 19, 2024•

edited

Loading

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Given the layout and size concerns of this change, does the new type require an explicit StructLayoutAttribute annotation? Are we ok with using the default layout? Is there an expectation that the fields will be consumed by unmanaged code.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).
@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).
Does Mono behave the same? I think it might respect Sequential for managed types.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.
That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).
This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.
@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.
That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).
This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.
Yeah but I've meant that Auto could maybe still be beneficial for Mono.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mono should likely consider adjusting their layout algorithm to match the RyuJIT algorithm in that scenario.
There are thousands of structs across the BCL and we are not going to go and annotate every single one of them to be explicitly Auto because they contain some managed field.
 internal readonly int _rank; // 4 bytes

 private readonly NintBuffer _lengths;
 private readonly NintBuffer _strides;

 internal TensorShape(nint memoryLength, ReadOnlySpan<nint> lengths, ReadOnlySpan<nint> strides)
 {
 _memoryLength = memoryLength;
 _rank = lengths.Length;
 if (lengths.Length > MaxInlineArraySize)
 {
 _metadata = new nint[lengths.Length + strides.Length];
 lengths.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[0], lengths.Length));
 strides.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[lengths.Length], strides.Length));
 }
 else
 {
 lengths.CopyTo(_lengths);
 strides.CopyTo(_strides);
 }
 }

 [InlineArray(MaxInlineArraySize)] // 5x8 bytes (40)
 private struct NintBuffer
 {
 public nint e0;
 }

 [UnscopedRef]
 public ReadOnlySpan<nint> Lengths => (_metadata is null)
 ? ((ReadOnlySpan<nint>)_lengths).Slice(0, _rank)
 : MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank);

 [UnscopedRef]
 public ReadOnlySpan<nint> Strides => (_metadata is null)
 ? ((ReadOnlySpan<nint>)_strides).Slice(0, _rank)
 : MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank * 2).Slice(_rank);

 public nint FlattenedLength => TensorSpanHelpers.CalculateTotalLength(Lengths);

 public bool IsEmpty => FlattenedLength == 0;
 }
}
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.#103244

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

michaelgsharp
merged 7 commits into

from

Jun 20, 2024
 Merged


Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.
#103244
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
aa617ec

TensorShape


michaelgsharp Jun 10, 2024
c4acef8

fixed TensorShape issue


michaelgsharp Jun 10, 2024
c02fd92

removed extra inline buffer type. Fixed tests. Added large dimension …


michaelgsharp Jun 11, 2024
fb64487

removed typo


michaelgsharp Jun 11, 2024
35dc2cf

adding unsaved files


michaelgsharp Jun 11, 2024
5053a67

changes to use const for stack alloc comparison


michaelgsharp Jun 11, 2024
63bc01d

changes from pr comments


michaelgsharp Jun 20, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


1 change: 1 addition & 0 deletions
src/libraries/System.Numerics.Tensors/src/System.Numerics.Tensors.csproj

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
 </ItemGroup>

 <ItemGroup Condition="'$(TargetFrameworkIdentifier)' == '.NETCoreApp'">
 <Compile Include="System\Numerics\Tensors\netcore\TensorShape.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\TensorHelpers.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\TensorExtensions.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\Tensor.Factory.cs" />
Expand Down

129 changes: 51 additions & 78 deletions
...braries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/ReadOnlyTensorSpan.cs

View file


Open in desktop


Large diffs are not rendered by default.


6 changes: 3 additions & 3 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/Tensor.Factory.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -153,16 +153,16 @@ public static Tensor<T> CreateUninitialized<T>(scoped ReadOnlySpan<nint> lengths

 public static ref readonly TensorSpan<T> FillGaussianNormalDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
 {
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

 GaussianDistribution<T>(span, destination._flattenedLength);
 GaussianDistribution<T>(span, destination._shape._memoryLength);

 return ref destination;
 }

 public static ref readonly TensorSpan<T> FillUniformDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
 {
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

 for (int i = 0; i < span.Length; i++)
 span[i] = T.CreateChecked(Random.Shared.NextDouble());
Expand Down

191 changes: 95 additions & 96 deletions
...libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorExtensions.cs

View file


Open in desktop


Large diffs are not rendered by default.


11 changes: 7 additions & 4 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorHelpers.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -17,7 +17,7 @@ internal static class TensorHelpers
 /// <returns>How many boolean values are true.</returns>
 public static nint CountTrueElements(scoped in ReadOnlyTensorSpan<bool> filter)
 {
 Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._flattenedLength);
 Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._shape._memoryLength);
 nint count = 0;
 for (int i = 0; i < filterSpan.Length; i++)
 {
Expand DownExpand Up@@ -83,11 +83,14 @@ internal static nint[] GetIntermediateShape(ReadOnlySpan<nint> shape1, int shape
 return newShape;
 }

 internal static bool IsUnderlyingStorageSameSize<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
 => tensor1._shape._memoryLength == tensor2._shape._memoryLength;

 internal static bool IsUnderlyingStorageSameSize<T>(Tensor<T> tensor1, Tensor<T> tensor2)
=> tensor1.Lengths.Length == tensor2.Lengths.Length;
 => tensor1._values.Length == tensor2._values.Length;

 internal static bool AreLengthsTheSame<T>(ReadOnlyTensorSpan<T> tensor1, ReadOnlyTensorSpan<T> tensor2)
 => tensor1._lengths.SequenceEqual(tensor2._lengths);
 internal static bool AreLengthsTheSame<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
 => tensor1.Lengths.SequenceEqual(tensor2.Lengths);

 internal static bool AreLengthsTheSame(ReadOnlySpan<nint> lengths1, ReadOnlySpan<nint> lengths2)
 => lengths1.SequenceEqual(lengths2);
Expand Down

64 changes: 64 additions & 0 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorShape.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,64 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.

using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;

namespace System.Numerics.Tensors
{
 internal readonly struct TensorShape
@eiriktsarpaliseiriktsarpalisJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could this also be a ref struct?
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We want to be able to use the same struct as part of Tensor<T> so we can avoid additional allocations for common cases there as well.
 {
 // Used to determine when we need to allocate a metadata array
 public const int MaxInlineArraySize = 5;

 // Used to determine when we can stack alloc for indexing vs when we need to allocate
 public const int MaxInlineRank = 8;

 internal readonly nint[]? _metadata; // 8 bytes

 internal readonly nint _memoryLength; // 8 bytes
@eiriktsarpaliseiriktsarpalisJun 19, 2024•

edited

Loading

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Given the layout and size concerns of this change, does the new type require an explicit StructLayoutAttribute annotation? Are we ok with using the default layout? Is there an expectation that the fields will be consumed by unmanaged code.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).
@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).
Does Mono behave the same? I think it might respect Sequential for managed types.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.
That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).
This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.
@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.
That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).
This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.
Yeah but I've meant that Auto could maybe still be beneficial for Mono.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mono should likely consider adjusting their layout algorithm to match the RyuJIT algorithm in that scenario.
There are thousands of structs across the BCL and we are not going to go and annotate every single one of them to be explicitly Auto because they contain some managed field.
 internal readonly int _rank; // 4 bytes

 private readonly NintBuffer _lengths;
 private readonly NintBuffer _strides;

 internal TensorShape(nint memoryLength, ReadOnlySpan<nint> lengths, ReadOnlySpan<nint> strides)
 {
 _memoryLength = memoryLength;
 _rank = lengths.Length;
 if (lengths.Length > MaxInlineArraySize)
 {
 _metadata = new nint[lengths.Length + strides.Length];
 lengths.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[0], lengths.Length));
 strides.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[lengths.Length], strides.Length));
 }
 else
 {
 lengths.CopyTo(_lengths);
 strides.CopyTo(_strides);
 }
 }

 [InlineArray(MaxInlineArraySize)] // 5x8 bytes (40)
 private struct NintBuffer
 {
 public nint e0;
 }

 [UnscopedRef]
 public ReadOnlySpan<nint> Lengths => (_metadata is null)
 ? ((ReadOnlySpan<nint>)_lengths).Slice(0, _rank)
 : MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank);

 [UnscopedRef]
 public ReadOnlySpan<nint> Strides => (_metadata is null)
 ? ((ReadOnlySpan<nint>)_strides).Slice(0, _rank)
 : MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank * 2).Slice(_rank);

 public nint FlattenedLength => TensorSpanHelpers.CalculateTotalLength(Lengths);

 public bool IsEmpty => FlattenedLength == 0;
 }
}
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.#103244

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

michaelgsharp
merged 7 commits into

from

Jun 20, 2024
 Merged


Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.
#103244
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
aa617ec

TensorShape


michaelgsharp Jun 10, 2024
c4acef8

fixed TensorShape issue


michaelgsharp Jun 10, 2024
c02fd92

removed extra inline buffer type. Fixed tests. Added large dimension …


michaelgsharp Jun 11, 2024
fb64487

removed typo


michaelgsharp Jun 11, 2024
35dc2cf

adding unsaved files


michaelgsharp Jun 11, 2024
5053a67

changes to use const for stack alloc comparison


michaelgsharp Jun 11, 2024
63bc01d

changes from pr comments


michaelgsharp Jun 20, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


1 change: 1 addition & 0 deletions
src/libraries/System.Numerics.Tensors/src/System.Numerics.Tensors.csproj

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
 </ItemGroup>

 <ItemGroup Condition="'$(TargetFrameworkIdentifier)' == '.NETCoreApp'">
 <Compile Include="System\Numerics\Tensors\netcore\TensorShape.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\TensorHelpers.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\TensorExtensions.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\Tensor.Factory.cs" />
Expand Down

129 changes: 51 additions & 78 deletions
...braries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/ReadOnlyTensorSpan.cs

View file


Open in desktop


Large diffs are not rendered by default.


6 changes: 3 additions & 3 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/Tensor.Factory.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -153,16 +153,16 @@ public static Tensor<T> CreateUninitialized<T>(scoped ReadOnlySpan<nint> lengths

 public static ref readonly TensorSpan<T> FillGaussianNormalDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
 {
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

 GaussianDistribution<T>(span, destination._flattenedLength);
 GaussianDistribution<T>(span, destination._shape._memoryLength);

 return ref destination;
 }

 public static ref readonly TensorSpan<T> FillUniformDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
 {
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

 for (int i = 0; i < span.Length; i++)
 span[i] = T.CreateChecked(Random.Shared.NextDouble());
Expand Down

191 changes: 95 additions & 96 deletions
...libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorExtensions.cs

View file


Open in desktop


Large diffs are not rendered by default.


11 changes: 7 additions & 4 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorHelpers.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -17,7 +17,7 @@ internal static class TensorHelpers
 /// <returns>How many boolean values are true.</returns>
 public static nint CountTrueElements(scoped in ReadOnlyTensorSpan<bool> filter)
 {
 Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._flattenedLength);
 Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._shape._memoryLength);
 nint count = 0;
 for (int i = 0; i < filterSpan.Length; i++)
 {
Expand DownExpand Up@@ -83,11 +83,14 @@ internal static nint[] GetIntermediateShape(ReadOnlySpan<nint> shape1, int shape
 return newShape;
 }

 internal static bool IsUnderlyingStorageSameSize<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
 => tensor1._shape._memoryLength == tensor2._shape._memoryLength;

 internal static bool IsUnderlyingStorageSameSize<T>(Tensor<T> tensor1, Tensor<T> tensor2)
=> tensor1.Lengths.Length == tensor2.Lengths.Length;
 => tensor1._values.Length == tensor2._values.Length;

 internal static bool AreLengthsTheSame<T>(ReadOnlyTensorSpan<T> tensor1, ReadOnlyTensorSpan<T> tensor2)
 => tensor1._lengths.SequenceEqual(tensor2._lengths);
 internal static bool AreLengthsTheSame<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
 => tensor1.Lengths.SequenceEqual(tensor2.Lengths);

 internal static bool AreLengthsTheSame(ReadOnlySpan<nint> lengths1, ReadOnlySpan<nint> lengths2)
 => lengths1.SequenceEqual(lengths2);
Expand Down

64 changes: 64 additions & 0 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorShape.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,64 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.

using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;

namespace System.Numerics.Tensors
{
 internal readonly struct TensorShape
@eiriktsarpaliseiriktsarpalisJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could this also be a ref struct?
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We want to be able to use the same struct as part of Tensor<T> so we can avoid additional allocations for common cases there as well.
 {
 // Used to determine when we need to allocate a metadata array
 public const int MaxInlineArraySize = 5;

 // Used to determine when we can stack alloc for indexing vs when we need to allocate
 public const int MaxInlineRank = 8;

 internal readonly nint[]? _metadata; // 8 bytes

 internal readonly nint _memoryLength; // 8 bytes
@eiriktsarpaliseiriktsarpalisJun 19, 2024•

edited

Loading

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Given the layout and size concerns of this change, does the new type require an explicit StructLayoutAttribute annotation? Are we ok with using the default layout? Is there an expectation that the fields will be consumed by unmanaged code.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).
@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).
Does Mono behave the same? I think it might respect Sequential for managed types.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.
That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).
This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.
@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.
That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).
This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.
Yeah but I've meant that Auto could maybe still be beneficial for Mono.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mono should likely consider adjusting their layout algorithm to match the RyuJIT algorithm in that scenario.
There are thousands of structs across the BCL and we are not going to go and annotate every single one of them to be explicitly Auto because they contain some managed field.
 internal readonly int _rank; // 4 bytes

 private readonly NintBuffer _lengths;
 private readonly NintBuffer _strides;

 internal TensorShape(nint memoryLength, ReadOnlySpan<nint> lengths, ReadOnlySpan<nint> strides)
 {
 _memoryLength = memoryLength;
 _rank = lengths.Length;
 if (lengths.Length > MaxInlineArraySize)
 {
 _metadata = new nint[lengths.Length + strides.Length];
 lengths.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[0], lengths.Length));
 strides.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[lengths.Length], strides.Length));
 }
 else
 {
 lengths.CopyTo(_lengths);
 strides.CopyTo(_strides);
 }
 }

 [InlineArray(MaxInlineArraySize)] // 5x8 bytes (40)
 private struct NintBuffer
 {
 public nint e0;
 }

 [UnscopedRef]
 public ReadOnlySpan<nint> Lengths => (_metadata is null)
 ? ((ReadOnlySpan<nint>)_lengths).Slice(0, _rank)
 : MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank);

 [UnscopedRef]
 public ReadOnlySpan<nint> Strides => (_metadata is null)
 ? ((ReadOnlySpan<nint>)_strides).Slice(0, _rank)
 : MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank * 2).Slice(_rank);

 public nint FlattenedLength => TensorSpanHelpers.CalculateTotalLength(Lengths);

 public bool IsEmpty => FlattenedLength == 0;
 }
}
Loading

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.#103244

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

michaelgsharp
merged 7 commits into

from

Jun 20, 2024
 Merged


Changed TensorSpan and ReadOnlyTensorSpan layout for better performance.
#103244
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


7 commits


Select commit
Hold shift + click to select a range
aa617ec

TensorShape


michaelgsharp Jun 10, 2024
c4acef8

fixed TensorShape issue


michaelgsharp Jun 10, 2024
c02fd92

removed extra inline buffer type. Fixed tests. Added large dimension …


michaelgsharp Jun 11, 2024
fb64487

removed typo


michaelgsharp Jun 11, 2024
35dc2cf

adding unsaved files


michaelgsharp Jun 11, 2024
5053a67

changes to use const for stack alloc comparison


michaelgsharp Jun 11, 2024
63bc01d

changes from pr comments


michaelgsharp Jun 20, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


1 change: 1 addition & 0 deletions
src/libraries/System.Numerics.Tensors/src/System.Numerics.Tensors.csproj

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -16,6 +16,7 @@
 </ItemGroup>

 <ItemGroup Condition="'$(TargetFrameworkIdentifier)' == '.NETCoreApp'">
 <Compile Include="System\Numerics\Tensors\netcore\TensorShape.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\TensorHelpers.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\TensorExtensions.cs" />
 <Compile Include="System\Numerics\Tensors\netcore\Tensor.Factory.cs" />
Expand Down

129 changes: 51 additions & 78 deletions
...braries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/ReadOnlyTensorSpan.cs

View file


Open in desktop


Large diffs are not rendered by default.


6 changes: 3 additions & 3 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/Tensor.Factory.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -153,16 +153,16 @@ public static Tensor<T> CreateUninitialized<T>(scoped ReadOnlySpan<nint> lengths

 public static ref readonly TensorSpan<T> FillGaussianNormalDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
 {
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

 GaussianDistribution<T>(span, destination._flattenedLength);
 GaussianDistribution<T>(span, destination._shape._memoryLength);

 return ref destination;
 }

 public static ref readonly TensorSpan<T> FillUniformDistribution<T>(in TensorSpan<T> destination) where T : IFloatingPoint<T>
 {
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._flattenedLength);
 Span<T> span = MemoryMarshal.CreateSpan<T>(ref destination._reference, (int)destination._shape._memoryLength);

 for (int i = 0; i < span.Length; i++)
 span[i] = T.CreateChecked(Random.Shared.NextDouble());
Expand Down

191 changes: 95 additions & 96 deletions
...libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorExtensions.cs

View file


Open in desktop


Large diffs are not rendered by default.


11 changes: 7 additions & 4 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorHelpers.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -17,7 +17,7 @@ internal static class TensorHelpers
 /// <returns>How many boolean values are true.</returns>
 public static nint CountTrueElements(scoped in ReadOnlyTensorSpan<bool> filter)
 {
 Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._flattenedLength);
 Span<bool> filterSpan = MemoryMarshal.CreateSpan(ref filter._reference, (int)filter._shape._memoryLength);
 nint count = 0;
 for (int i = 0; i < filterSpan.Length; i++)
 {
Expand DownExpand Up@@ -83,11 +83,14 @@ internal static nint[] GetIntermediateShape(ReadOnlySpan<nint> shape1, int shape
 return newShape;
 }

 internal static bool IsUnderlyingStorageSameSize<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
 => tensor1._shape._memoryLength == tensor2._shape._memoryLength;

 internal static bool IsUnderlyingStorageSameSize<T>(Tensor<T> tensor1, Tensor<T> tensor2)
=> tensor1.Lengths.Length == tensor2.Lengths.Length;
 => tensor1._values.Length == tensor2._values.Length;

 internal static bool AreLengthsTheSame<T>(ReadOnlyTensorSpan<T> tensor1, ReadOnlyTensorSpan<T> tensor2)
 => tensor1._lengths.SequenceEqual(tensor2._lengths);
 internal static bool AreLengthsTheSame<T>(scoped in ReadOnlyTensorSpan<T> tensor1, scoped in ReadOnlyTensorSpan<T> tensor2)
 => tensor1.Lengths.SequenceEqual(tensor2.Lengths);

 internal static bool AreLengthsTheSame(ReadOnlySpan<nint> lengths1, ReadOnlySpan<nint> lengths2)
 => lengths1.SequenceEqual(lengths2);
Expand Down

64 changes: 64 additions & 0 deletions
src/libraries/System.Numerics.Tensors/src/System/Numerics/Tensors/netcore/TensorShape.cs

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,64 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.

using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;

namespace System.Numerics.Tensors
{
 internal readonly struct TensorShape
@eiriktsarpaliseiriktsarpalisJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could this also be a ref struct?
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We want to be able to use the same struct as part of Tensor<T> so we can avoid additional allocations for common cases there as well.
 {
 // Used to determine when we need to allocate a metadata array
 public const int MaxInlineArraySize = 5;

 // Used to determine when we can stack alloc for indexing vs when we need to allocate
 public const int MaxInlineRank = 8;

 internal readonly nint[]? _metadata; // 8 bytes

 internal readonly nint _memoryLength; // 8 bytes
@eiriktsarpaliseiriktsarpalisJun 19, 2024•

edited

Loading

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Given the layout and size concerns of this change, does the new type require an explicit StructLayoutAttribute annotation? Are we ok with using the default layout? Is there an expectation that the fields will be consumed by unmanaged code.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).
@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This struct contains a managed field (nint[]? _metadata) and as such is not blittable and will never have StructLayout respected, the runtime will treat it as Auto regardless (you can technically mark it as LayoutKind.Explicit and that would be respected, but that's a de-optimization and would cause many other issues).
Does Mono behave the same? I think it might respect Sequential for managed types.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.
That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).
This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.
@MichalPetrykaMichalPetrykaJun 19, 2024

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Mono behave the same? I think it might respect Sequential for managed types.
That doesn't really matter. RyuJIT doesn't and so code cannot depend on the managed side being sequential, that is part of why we must use InlineArray (rather than declaring n-sequential fields).
This is likewise an internal struct, so it can't be used by developers in interop scenarios. Due to it being a struct containing a managed field, it likewise couldn't be used in interop without marshalling and so there is zero benefit to changing the layout from its default.
Yeah but I've meant that Auto could maybe still be beneficial for Mono.
@tannergoodingtannergoodingJun 19, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mono should likely consider adjusting their layout algorithm to match the RyuJIT algorithm in that scenario.
There are thousands of structs across the BCL and we are not going to go and annotate every single one of them to be explicitly Auto because they contain some managed field.
 internal readonly int _rank; // 4 bytes

 private readonly NintBuffer _lengths;
 private readonly NintBuffer _strides;

 internal TensorShape(nint memoryLength, ReadOnlySpan<nint> lengths, ReadOnlySpan<nint> strides)
 {
 _memoryLength = memoryLength;
 _rank = lengths.Length;
 if (lengths.Length > MaxInlineArraySize)
 {
 _metadata = new nint[lengths.Length + strides.Length];
 lengths.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[0], lengths.Length));
 strides.CopyTo(MemoryMarshal.CreateSpan(ref _metadata[lengths.Length], strides.Length));
 }
 else
 {
 lengths.CopyTo(_lengths);
 strides.CopyTo(_strides);
 }
 }

 [InlineArray(MaxInlineArraySize)] // 5x8 bytes (40)
 private struct NintBuffer
 {
 public nint e0;
 }

 [UnscopedRef]
 public ReadOnlySpan<nint> Lengths => (_metadata is null)
 ? ((ReadOnlySpan<nint>)_lengths).Slice(0, _rank)
 : MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank);

 [UnscopedRef]
 public ReadOnlySpan<nint> Strides => (_metadata is null)
 ? ((ReadOnlySpan<nint>)_strides).Slice(0, _rank)
 : MemoryMarshal.CreateReadOnlySpan(ref MemoryMarshal.GetArrayDataReference(_metadata), _rank * 2).Slice(_rank);

 public nint FlattenedLength => TensorSpanHelpers.CalculateTotalLength(Lengths);

 public bool IsEmpty => FlattenedLength == 0;
 }
}
Loading