a0318f36f0
This PR switches Cranelift over to the new register allocator, regalloc2. See [this document](https://gist.github.com/cfallin/08553421a91f150254fe878f67301801) for a summary of the design changes. This switchover has implications for core VCode/MachInst types and the lowering pass. Overall, this change brings improvements to both compile time and speed of generated code (runtime), as reported in #3942: ``` Benchmark Compilation (wallclock) Execution (wallclock) blake3-scalar 25% faster 28% faster blake3-simd no diff no diff meshoptimizer 19% faster 17% faster pulldown-cmark 17% faster no diff bz2 15% faster no diff SpiderMonkey, 21% faster 2% faster fib(30) clang.wasm 42% faster N/A ```
99 lines
1.4 KiB
Plaintext
99 lines
1.4 KiB
Plaintext
test compile precise-output
|
|
target aarch64
|
|
|
|
function %atomic_store_i64(i64, i64) {
|
|
block0(v0: i64, v1: i64):
|
|
atomic_store.i64 v0, v1
|
|
return
|
|
}
|
|
|
|
; block0:
|
|
; stlr x0, [x1]
|
|
; ret
|
|
|
|
function %atomic_store_i32(i32, i64) {
|
|
block0(v0: i32, v1: i64):
|
|
atomic_store.i32 v0, v1
|
|
return
|
|
}
|
|
|
|
; block0:
|
|
; stlr w0, [x1]
|
|
; ret
|
|
|
|
function %atomic_store_i16(i16, i64) {
|
|
block0(v0: i16, v1: i64):
|
|
atomic_store.i16 v0, v1
|
|
return
|
|
}
|
|
|
|
; block0:
|
|
; stlrh w0, [x1]
|
|
; ret
|
|
|
|
function %atomic_store_i8(i8, i64) {
|
|
block0(v0: i8, v1: i64):
|
|
atomic_store.i8 v0, v1
|
|
return
|
|
}
|
|
|
|
; block0:
|
|
; stlrb w0, [x1]
|
|
; ret
|
|
|
|
function %atomic_store_i64_i32(i64, i64) {
|
|
block0(v0: i64, v1: i64):
|
|
v2 = ireduce.i32 v0
|
|
atomic_store.i32 v2, v1
|
|
return
|
|
}
|
|
|
|
; block0:
|
|
; stlr w0, [x1]
|
|
; ret
|
|
|
|
function %atomic_store_i64_i16(i64, i64) {
|
|
block0(v0: i64, v1: i64):
|
|
v2 = ireduce.i16 v0
|
|
atomic_store.i16 v2, v1
|
|
return
|
|
}
|
|
|
|
; block0:
|
|
; stlrh w0, [x1]
|
|
; ret
|
|
|
|
function %atomic_store_i64_i8(i64, i64) {
|
|
block0(v0: i64, v1: i64):
|
|
v2 = ireduce.i8 v0
|
|
atomic_store.i8 v2, v1
|
|
return
|
|
}
|
|
|
|
; block0:
|
|
; stlrb w0, [x1]
|
|
; ret
|
|
|
|
function %atomic_store_i32_i16(i32, i64) {
|
|
block0(v0: i32, v1: i64):
|
|
v2 = ireduce.i16 v0
|
|
atomic_store.i16 v2, v1
|
|
return
|
|
}
|
|
|
|
; block0:
|
|
; stlrh w0, [x1]
|
|
; ret
|
|
|
|
function %atomic_store_i32_i8(i32, i64) {
|
|
block0(v0: i32, v1: i64):
|
|
v2 = ireduce.i8 v0
|
|
atomic_store.i8 v2, v1
|
|
return
|
|
}
|
|
|
|
; block0:
|
|
; stlrb w0, [x1]
|
|
; ret
|
|
|