Update and revamp wasm32 SIMD intrinsics

Lots of time and lots of things have happened since the simd128 support
was first added to this crate. Things are starting to settle down now so
this commit syncs the Rust intrinsic definitions with the current
specification (https://github.com/WebAssembly/simd). Unfortuantely not
everything can be enabled just yet but everything is in the pipeline for
getting enabled soon.

This commit also applies a major revamp to how intrinsics are tested.
The intention is that the setup should be much more lightweight and/or
easy to work with after this commit.

At a high-level, the changes here are:

* Testing with node.js and `#[wasm_bindgen]` has been removed. Instead
  intrinsics are tested with Wasmtime which has a nearly complete
  implementation of the SIMD spec (and soon fully complete!)

* Testing is switched to `wasm32-wasi` to make idiomatic Rust bits a bit
  easier to work with (e.g. `panic!)`

* Testing of this crate's simd128 feature for wasm is re-enabled. This
  will run on CI and both compile and execute intrinsics. This should
  bring wasm intrinsics to the same level of parity as x86 intrinsics,
  for example.

* New wasm intrinsics have been added:
  * `iNNxMM_loadAxA_{s,u}`
  * `vNNxMM_load_splat`
  * `v8x16_swizzle`
  * `v128_andnot`
  * `iNNxMM_abs`
  * `iNNxMM_narrow_*_{u,s}`
  * `iNNxMM_bitmask` - commented out until LLVM is updated to LLVM 11
  * `iNNxMM_widen_*_{u,s}` - commented out until
    bytecodealliance/wasmtime#1994 lands
  * `iNNxMM_{max,min}_{u,s}`
  * `iNNxMM_avgr_u`

* Some wasm intrinsics have been removed:
  * `i64x2_trunc_*`
  * `f64x2_convert_*`
  * `i8x16_mul`

* The `v8x16.shuffle` instruction is exposed. This is done through a
  `macro` (not `macro_rules!`, but `macro`). This is intended to be
  somewhat experimental and unstable until we decide otherwise. This
  instruction has 16 immediate-mode expressions and is as a result
  unsuited to the existing `constify_*` logic of this crate. I'm hoping
  that we can game out over time what a macro might look like and/or
  look for better solutions. For now, though, what's implemented is the
  first of its kind in this crate (an architecture-specific macro), so
  some extra scrutiny looking at it would be appreciated.

* Lots of `assert_instr` annotations have been fixed for wasm.

* All wasm simd128 tests are uncommented and passing now.

This is still missing tests for new intrinsics and it's also missing
tests for various corner cases. I hope to get to those later as the
upstream spec itself gets closer to stabilization.

In the meantime, however, I went ahead and updated the `hex.rs` example
with a wasm implementation using intrinsics. With it I got some very
impressive speedups using Wasmtime:

    test benches::large_default  ... bench:     213,961 ns/iter (+/- 5,108) = 4900 MB/s
    test benches::large_fallback ... bench:   3,108,434 ns/iter (+/- 75,730) = 337 MB/s
    test benches::small_default  ... bench:          52 ns/iter (+/- 0) = 2250 MB/s
    test benches::small_fallback ... bench:         358 ns/iter (+/- 0) = 326 MB/s

or otherwise using Wasmtime hex encoding using SIMD is 15x faster on 1MB
chunks or 7x faster on small <128byte chunks.

All of these intrinsics are still unstable and will continue to be so
presumably until the simd proposal in wasm itself progresses to a later
stage. Additionaly we'll still want to sync with clang on intrinsic
names (or decide not to) at some point in the future.

.github/workflows/main.yml

@@ -77,7 +77,7 @@ jobs:
         - mips64-unknown-linux-gnuabi64
         - mips64el-unknown-linux-gnuabi64
         - s390x-unknown-linux-gnu
-        - wasm32-unknown-unknown
+        - wasm32-wasi
         - i586-unknown-linux-gnu
         - x86_64-linux-android
         - arm-linux-androideabi
@@ -129,7 +129,7 @@ jobs:
           disable_assert_instr: true
         - target: s390x-unknown-linux-gnu
           os: ubuntu-latest
-        - target: wasm32-unknown-unknown
+        - target: wasm32-wasi
           os: ubuntu-latest
         - target: aarch64-unknown-linux-gnu
           os: ubuntu-latest

ci/docker/wasm32-wasi/Dockerfile

@@ -0,0 +1,22 @@
+FROM ubuntu:20.04
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN apt-get update -y && apt-get install -y --no-install-recommends \
+  ca-certificates \
+  clang \
+  cmake \
+  curl \
+  git \
+  libc6-dev \
+  make \
+  python \
+  python3 \
+  xz-utils
+
+RUN curl -L https://github.com/bytecodealliance/wasmtime/releases/download/dev/wasmtime-dev-x86_64-linux.tar.xz | tar xJf -
+ENV PATH=$PATH:/wasmtime-dev-x86_64-linux
+
+ENV CARGO_TARGET_WASM32_WASI_RUNNER="wasmtime \
+  --enable-simd \
+  --mapdir .::/checkout/target/wasm32-wasi/release/deps \
+  --"

ci/run.sh

@@ -44,6 +44,16 @@ cargo_test() {
     fi
     cmd="$cmd ${subcmd} --target=$TARGET $1"
     cmd="$cmd -- $2"
+
+    # wasm targets can't catch panics so if a test failures make sure the test
+    # harness isn't trying to capture output, otherwise we won't get any useful
+    # output.
+    case ${TARGET} in
+        wasm32*)
+            cmd="$cmd --nocapture"
+            ;;
+    esac
+
     $cmd
 }
 
@@ -72,20 +82,11 @@ case ${TARGET} in
         export RUSTFLAGS="${RUSTFLAGS} -C target-feature=+avx"
         cargo_test "--release"
         ;;
-    wasm32-unknown-unknown*)
-        # Attempt to actually run some SIMD tests in node.js. Unfortunately
-        # though node.js (transitively through v8) doesn't have support for the
-        # full SIMD spec yet, only some functions. As a result only pass in
-        # some target features and a special `--cfg`
-        # FIXME: broken
-        #export RUSTFLAGS="${RUSTFLAGS} -C target-feature=+simd128 --cfg only_node_compatible_functions"
-        #cargo_test "--release"
-
-        # After that passes make sure that all intrinsics compile, passing in
-        # the extra feature to compile in non-node-compatible SIMD.
-        # FIXME: broken
-        #export RUSTFLAGS="${RUSTFLAGS} -C target-feature=+simd128,+unimplemented-simd128"
-        #cargo_test "--release --no-run"
+    wasm32*)
+        prev="$RUSTFLAGS"
+        export RUSTFLAGS="${RUSTFLAGS} -C target-feature=+simd128,+unimplemented-simd128"
+        cargo_test "--release"
+        export RUSTFLAGS="$prev"
         ;;
     # FIXME: don't build anymore
     #mips-*gnu* | mipsel-*gnu*)
@@ -111,7 +112,7 @@ case ${TARGET} in
 
 esac
 
-if [ "$NORUN" != "1" ] && [ "$NOSTD" != 1 ] && [ "$TARGET" != "wasm32-unknown-unknown" ]; then
+if [ "$NORUN" != "1" ] && [ "$NOSTD" != 1 ]; then
     # Test examples
     (
         cd examples

crates/assert-instr-macro/src/lib.rs

@@ -131,8 +131,7 @@ pub fn assert_instr(
     };
 
     let tokens: TokenStream = quote! {
-        #[cfg_attr(target_arch = "wasm32", wasm_bindgen_test)]
-        #[cfg_attr(not(target_arch = "wasm32"), test)]
+        #[test]
         #[allow(non_snake_case)]
         fn #assert_name() {
             #to_test
@@ -146,11 +145,6 @@ pub fn assert_instr(
                                    #instr);
         }
     };
-    // why? necessary now to get tests to work?
-    let tokens: TokenStream = tokens
-        .to_string()
-        .parse()
-        .expect("cannot parse tokenstream");
 
     let tokens: TokenStream = quote! {
         #item

crates/core_arch/Cargo.toml

@@ -26,8 +26,5 @@ maintenance = { status = "experimental" }
 stdarch-test = { version = "0.*", path = "../stdarch-test" }
 std_detect = { version = "0.*", path = "../std_detect" }
 
-[target.wasm32-unknown-unknown.dev-dependencies]
-wasm-bindgen-test = "0.2.47"
-
 [package.metadata.docs.rs]
 rustdoc-args = [ "--cfg", "dox" ]

crates/core_arch/src/lib.rs

@@ -32,7 +32,10 @@
     adx_target_feature,
     rtm_target_feature,
     f16c_target_feature,
-    external_doc
+    external_doc,
+    allow_internal_unstable,
+    allow_internal_unsafe,
+    decl_macro
 )]
 #![cfg_attr(test, feature(test, abi_vectorcall, untagged_unions))]
 #![deny(clippy::missing_inline_in_public_items)]
@@ -66,13 +69,10 @@ extern crate std_detect;
 #[cfg(test)]
 extern crate stdarch_test;
 
-#[cfg(all(test, target_arch = "wasm32"))]
-extern crate wasm_bindgen_test;
-
 #[path = "mod.rs"]
 mod core_arch;
 
-pub use self::core_arch::arch::*;
+pub use self::core_arch::arch;
 
 #[allow(unused_imports)]
 use core::{ffi, hint, intrinsics, marker, mem, ops, ptr, sync};

crates/core_arch/src/mod.rs

@@ -1,5 +1,7 @@
 //! `core_arch`
 
+#![allow(improper_ctypes_definitions)]
+
 #[macro_use]
 mod macros;
 

crates/core_arch/src/wasm32/atomic.rs

@@ -10,8 +10,6 @@
 
 #[cfg(test)]
 use stdarch_test::assert_instr;
-#[cfg(test)]
-use wasm_bindgen_test::wasm_bindgen_test;
 
 extern "C" {
     #[link_name = "llvm.wasm.atomic.wait.i32"]

crates/core_arch/src/wasm32/memory.rs

@@ -1,7 +1,5 @@
 #[cfg(test)]
 use stdarch_test::assert_instr;
-#[cfg(test)]
-use wasm_bindgen_test::wasm_bindgen_test;
 
 extern "C" {
     #[link_name = "llvm.wasm.memory.grow.i32"]

crates/core_arch/src/wasm32/mod.rs

@@ -2,8 +2,6 @@
 
 #[cfg(test)]
 use stdarch_test::assert_instr;
-#[cfg(test)]
-use wasm_bindgen_test::wasm_bindgen_test;
 
 #[cfg(any(target_feature = "atomics", dox))]
 mod atomic;
@@ -12,6 +10,8 @@ pub use self::atomic::*;
 
 #[cfg(any(target_feature = "simd128", dox))]
 mod simd128;
+// #[cfg(any(target_feature = "simd128", dox))]
+// pub use self::simd128::v128_shuffle;
 #[cfg(any(target_feature = "simd128", dox))]
 pub use self::simd128::*;