Skip to content

Fix code highlighting on wave intrinsic blog post #127

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
merged 3 commits into from
Jul 21, 2025
Merged

Fix code highlighting on wave intrinsic blog post #127

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
cfc009a
Fix code highlighting
swoods-nv Jul 18, 2025
cd91a39
Remove Apr 4 post from "featured"
swoods-nv Jul 18, 2025
647beb3
Add wave intrinsics post to "featured"
swoods-nv Jul 18, 2025
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
2 changes: 1 addition & 1 deletion _posts/2025-04-04-neural-gfx-in-an-afternoon.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
layout: post
title: "Neural Graphics in an Afternoon"
date: 2025-04-04 17:00:00
categories: [ "blog", "featured" ]
categories: [ "blog" ]
tags: [slang]
featured: true
author: "Shannon Woods, NVIDIA, Slang Working Group Chair"
Expand Down
6 changes: 3 additions & 3 deletions _posts/2025-07-17-ng-wave-intrinsics.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
layout: post
title: "Neural Graphics: Speeding It Up with Wave Intrinsics"
date: 2025-07-17
categories: [ "blog" ]
categories: [ "blog", "featured" ]
tags: [slang]
author: "Shannon Woods, NVIDIA, Slang Working Group Chair"
image: /images/posts/wave-graphic.webp
Expand All @@ -19,7 +19,7 @@ As a quick refresher, these examples implement a 2D Gaussian splatting algorithm

The Python script (`main.py`) driving this process is nearly identical between the two examples, with one key difference: the `balloted-splatting` example uses SlangPy's ability to set a specific call group shape to explicitly match the wavefront size. For example, when kicking off the backward propagation of our loss calculation, we now call

```
```python
module.perPixelLoss.call_group_shape(Shape((WORKGROUP_X, WORKGROUP_Y))).bwds(per_pixel_loss, dispatch_ids, blobs, input_image)
```

Expand All @@ -46,7 +46,7 @@ The `balloted-splatting` example presents a more sophisticated and often more pe

You can see this in action in the new `cullAndApplyBlobs` function, which effectively replaces the `coarseRasterize`, `padBuffer`, `bitonicSort`, and `fineRasterize` sequence from the previous example.

```slang
```hlsl
/*
* cullAndApplyBlobs finds blobs which intersect the current tile and evaluates them in a single pass using
* wave intrinsics.
Expand Down