Bring back WebGPU (#7063)

* Start from andredaprato:webgpu-clean

* Fix infs

* inf wgsl function is not needed

* Emulated ulong for threefry, more tests passing

* Randomness tests passing

* Update model export to support new changes in webgpu, efficientnet export works again

* Simplify shift emulation in wgsl

* Delete test file

* Fix bigger than u32 u32 literal

* Why was skip copies added here?

* Python3.12 for webgpu tests

* Fix model export syntax error

* Get test ops passing with some skips

* Fix lint

* Much simpler shift

* Run more tests

* Timestamp queries are not supported in CI, so skip search tests

* All fancy indexing passing

* r is ctx

* Run more dtype tests by using is_dtype_supported

* Cleanup ulong shift rendering

* UPat -> Pat, UOps -> Ops

* Pat -> UPat

* Refactor render_ushift if-else

* Pattern to avoid ulong mul

* Remove vals_dtype

* is_nan trick + rewrite, test_isnan passing

* Rewrite a * select(1, nan, gate) -> select(a, nan, gate)

* No arg, just op

* Support char, uchar, short, ushort

* Run test_index_mnis now that we have uint8

* Fix pyling

* Save 3 lines by using base Compiler

* No more long emulation

* Remove fixup_binops

* No more external_local_bufx wgsl specific cstyle modif, use base extra_pm

* Simpler, faster copyin/out

* Skip some new tests that use long

* Fix typo

* copyout touchup

* Save lines by using render_cast

* WebGL is not supported in core, delete it from is_dtype_supported

* More narrow test skips for some unary tests

* TernaryOps, UnaryOps -> Ops

* TinyGrad supports WebGPU

* StableDiffusion demo: f16tof32 gpu is a lib, update UI

* Packed load/store, no more scale_size, no core tinygrad changes

* Rename copyin, copyout

* Device -> dev

* Fix lint

* Pattern matcher rule for packed load/store

* Refactor

* Shorter packed load/store

* this should fix lint

* Fix mypy

* SD compile script working

* New SD webgpu UI

* New default prompt

* New SD weights

* Fix title when webgpu not available

* Run symbolic tests, simplify is_nan, use round_up

* Show step time on UI

* Bump minimum wgpu version to v0.19

* Fix latent

---------

Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>

test/web/test_webgpu.js

@@ -0,0 +1,65 @@
+const puppeteer = require("puppeteer");
+const { spawn } = require("child_process");
+const res = spawn("python", ["-m", "http.server", "8000"], { shell: true });
+
+async function timeout(time) {
+  return new Promise((resolve) => setTimeout(resolve, time));
+}
+
+function cleanup(err) {
+  console.log("cleaning up");
+  res.kill();
+  if (err != null) {
+    console.error(err);
+    process.exit(1);
+  }
+  process.exit(0);
+}
+
+async function waitForText(selector, text) {
+  let n = 0;
+  let ready = false;
+  while (n < 30) {
+    const res = await (await selector.getProperty("textContent")).jsonValue();
+    console.log(`waiting for text ${text} got ${res}`);
+    if (res == text) {
+      ready = true;
+      break;
+    }
+    await timeout(1000);
+    n += 1;
+  }
+  return ready;
+}
+
+async function runTest() {
+  const browser = await puppeteer.launch({
+    headless: false,
+    args: ["--enable-unsafe-webgpu"],
+  });
+  const page = await browser.newPage();
+
+  page
+    .on("console", (message) =>
+      console.log(`message from console ${message.text()}`),
+    )
+    .on("pageerror", ({ message }) =>
+      console.log(`error from page ${message}`),
+    );
+
+  const res = await page.goto("http://localhost:8000/examples/index.html");
+  if (res.status() !== 200) throw new Error("Failed to load page");
+
+  const textSelector = await page.waitForSelector("#result");
+  const buttonSelector = await page.waitForSelector("input[type=button]");
+  const ready = await waitForText(textSelector, "ready");
+  if (!ready) throw new Error("Failed to load page");
+
+  await buttonSelector.evaluate((e) => e.click());
+  const done = await waitForText(textSelector, "hen");
+  if (!done) throw new Error("failed to get hen");
+
+  cleanup(null);
+}
+
+runTest().catch((err) => cleanup(err));