Mojo Academy · 课时

结合 SIMD 与循环

将内核的核心部分向量化

结合 SIMD 与循环 是 CoddyKit 上的免费 Mojo Academy 课时。这是第 2 节课，共 4 节。你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。这是 Mojo Academy 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 Mojo Academy 课程共包含 4 节课。

本课时的部分内容尚未翻译，以英文显示。

From Scalar to SIMD

To accelerate a kernel, swap the one-at-a-time loop for one that handles a whole pack of values per step with SIMD.

for i in range(n):
    out[i] = a[i] + b[i]

Pick a Width

Choose how many elements fit in one vector. The width is the number of lanes each step processes together.

alias width = 4

Load a Chunk

Grab several elements at once into a SIMD value with a vector load instead of reading them one by one.

var va = a.load[width=width](i)

Compute the Pack

Run the kernel's math on both chunks at once. The whole pack is added element-wise in a single operation.

var vsum = a.load[width=width](i) + b.load[width=width](i)

Store the Pack

Write the full result back with a vector store, covering every lane you just computed in one move.

out.store[width=width](i, vsum)

Step by the Width

The vectorized loop advances by the width, not by one. Each pass covers a full pack of elements.

for i in range(0, n, width):
    pass

Let vectorize Help

Mojo's vectorize helper sweeps a closure across the range in vector steps so you skip the manual bookkeeping.

from algorithm import vectorize

Write the Chunk Closure

You define a small parameterized function that handles one chunk. Mojo calls it with the right width as it sweeps.

fn body[w: Int](i: Int):
    out.store[width=w](i, a.load[width=w](i) + b.load[width=w](i))

Run vectorize

Call vectorize with your closure, the width, and the size. It loops and even handles the leftover tail for you.

vectorize[body, width](n)

Mind the Tail

When n is not a multiple of the width, a few elements remain. vectorize cleans up that tail so nothing is missed.

Same Output, More Speed

The vectorized kernel produces identical results but moves through data in big steps, so it finishes much sooner.

Quick Check

You vectorize a kernel with width 4 but n is 10. What handles the last two elements?

Recap

Vectorize a kernel by loading and storing packs, stepping by the width, and letting vectorize handle the sweep and the tail. 🚀

常见问题解答

「结合 SIMD 与循环」课时是免费的吗？

是的 — 「结合 SIMD 与循环」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 Mojo Academy 课程的其余内容，请升级到 CoddyKit PRO。 Mojo Academy 课程共包含 4 节课。

「结合 SIMD 与循环」这节课中我会学到什么？

将内核的核心部分向量化你通过在浏览器中直接运行的动手代码来练习 Mojo Academy，全天候 AI 导师会在你学习这节课的过程中回答你的问题。

学习 Mojo Academy 需要有经验吗？

无需任何先前经验。CoddyKit 上的 Mojo Academy 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。这是第 2 节课，共 4 节。

「结合 SIMD 与循环」课时需要多长时间？

大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。

我能在这节 Mojo Academy 课中编写并运行代码吗？

能。每节 Mojo Academy 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。

此课程中的所有课时

← 返回 Mojo Academy