2015-09-16 01:26:58 +02:00
|
|
|
// Copyright 2015 The Rust Project Developers. See the COPYRIGHT
|
|
|
|
// file at the top-level directory of this distribution and at
|
|
|
|
// http://rust-lang.org/COPYRIGHT.
|
|
|
|
//
|
|
|
|
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
|
|
|
|
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
|
|
|
|
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
|
|
|
|
// option. This file may not be copied, modified, or distributed
|
|
|
|
// except according to those terms.
|
|
|
|
|
|
|
|
// compile-flags: -C no-prepopulate-passes
|
|
|
|
|
2015-09-15 16:22:16 -05:00
|
|
|
#![crate_type = "lib"]
|
|
|
|
|
2015-09-16 01:26:58 +02:00
|
|
|
// Hack to get the correct size for the length part in slices
|
Avoid unnecessary copies of arguments that are simple bindings
Initially MIR differentiated between arguments and locals, which
introduced a need to add extra copies assigning the argument to a
local, even for simple bindings. This differentiation no longer exists,
but we're still creating those copies, bloating the MIR and LLVM IR we
emit.
Additionally, the current approach means that we create debug info for
both the incoming argument (marking it as an argument), and then
immediately shadow it a local that goes by the same name. This can be
confusing when using e.g. "info args" in gdb, or when e.g. a debugger
with a GUI displays the function arguments separately from the local
variables, especially when the binding is mutable, because the argument
doesn't change, while the local variable does.
2017-10-11 20:49:36 +02:00
|
|
|
// CHECK: @helper([[USIZE:i[0-9]+]] %arg0)
|
2015-09-16 01:26:58 +02:00
|
|
|
#[no_mangle]
|
|
|
|
fn helper(_: usize) {
|
|
|
|
}
|
|
|
|
|
|
|
|
// CHECK-LABEL: @no_op_slice_adjustment
|
|
|
|
#[no_mangle]
|
|
|
|
pub fn no_op_slice_adjustment(x: &[u8]) -> &[u8] {
|
|
|
|
// We used to generate an extra alloca and memcpy for the block's trailing expression value, so
|
|
|
|
// check that we copy directly to the return value slot
|
Avoid unnecessary copies of arguments that are simple bindings
Initially MIR differentiated between arguments and locals, which
introduced a need to add extra copies assigning the argument to a
local, even for simple bindings. This differentiation no longer exists,
but we're still creating those copies, bloating the MIR and LLVM IR we
emit.
Additionally, the current approach means that we create debug info for
both the incoming argument (marking it as an argument), and then
immediately shadow it a local that goes by the same name. This can be
confusing when using e.g. "info args" in gdb, or when e.g. a debugger
with a GUI displays the function arguments separately from the local
variables, especially when the binding is mutable, because the argument
doesn't change, while the local variable does.
2017-10-11 20:49:36 +02:00
|
|
|
// CHECK: %0 = insertvalue { i8*, [[USIZE]] } undef, i8* %x.ptr, 0
|
|
|
|
// CHECK: %1 = insertvalue { i8*, [[USIZE]] } %0, [[USIZE]] %x.meta, 1
|
|
|
|
// CHECK: ret { i8*, [[USIZE]] } %1
|
2015-09-16 01:26:58 +02:00
|
|
|
{ x }
|
|
|
|
}
|
Skip no-op adjustments in trans
That allows us to keep using trans_into() in case of adjustments that
may actually be ignored in trans because they are a plain deref/ref pair
with no overloaded deref or unsizing.
Unoptimized(!) benchmarks from servo/servo#7638
Before
```
test goser::bench_clone ... bench: 17,701 ns/iter (+/- 58) = 30 MB/s
test goser::bincode::bench_decoder ... bench: 33,715 ns/iter (+/- 300) = 11 MB/s
test goser::bincode::bench_deserialize ... bench: 36,804 ns/iter (+/- 329) = 9 MB/s
test goser::bincode::bench_encoder ... bench: 34,695 ns/iter (+/- 149) = 11 MB/s
test goser::bincode::bench_populate ... bench: 18,879 ns/iter (+/- 88)
test goser::bincode::bench_serialize ... bench: 31,668 ns/iter (+/- 156) = 11 MB/s
test goser::capnp::bench_deserialize ... bench: 2,049 ns/iter (+/- 87) = 218 MB/s
test goser::capnp::bench_deserialize_packed ... bench: 10,707 ns/iter (+/- 258) = 31 MB/s
test goser::capnp::bench_populate ... bench: 635 ns/iter (+/- 5)
test goser::capnp::bench_serialize ... bench: 35,657 ns/iter (+/- 155) = 12 MB/s
test goser::capnp::bench_serialize_packed ... bench: 37,881 ns/iter (+/- 146) = 8 MB/s
test goser::msgpack::bench_decoder ... bench: 50,634 ns/iter (+/- 307) = 5 MB/s
test goser::msgpack::bench_encoder ... bench: 25,738 ns/iter (+/- 90) = 11 MB/s
test goser::msgpack::bench_populate ... bench: 18,900 ns/iter (+/- 138)
test goser::protobuf::bench_decoder ... bench: 2,791 ns/iter (+/- 29) = 102 MB/s
test goser::protobuf::bench_encoder ... bench: 75,414 ns/iter (+/- 358) = 3 MB/s
test goser::protobuf::bench_populate ... bench: 19,248 ns/iter (+/- 92)
test goser::rustc_serialize_json::bench_decoder ... bench: 109,999 ns/iter (+/- 797) = 5 MB/s
test goser::rustc_serialize_json::bench_encoder ... bench: 58,777 ns/iter (+/- 418) = 10 MB/s
test goser::rustc_serialize_json::bench_populate ... bench: 18,887 ns/iter (+/- 76)
test goser::serde_json::bench_deserializer ... bench: 104,803 ns/iter (+/- 770) = 5 MB/s
test goser::serde_json::bench_populate ... bench: 18,890 ns/iter (+/- 69)
test goser::serde_json::bench_serializer ... bench: 75,046 ns/iter (+/- 435) = 8 MB/s
```
After
```
test goser::bench_clone ... bench: 16,052 ns/iter (+/- 188) = 34 MB/s
test goser::bincode::bench_decoder ... bench: 31,194 ns/iter (+/- 941) = 12 MB/s
test goser::bincode::bench_deserialize ... bench: 33,934 ns/iter (+/- 352) = 10 MB/s
test goser::bincode::bench_encoder ... bench: 30,737 ns/iter (+/- 1,969) = 13 MB/s
test goser::bincode::bench_populate ... bench: 17,234 ns/iter (+/- 176)
test goser::bincode::bench_serialize ... bench: 28,269 ns/iter (+/- 452) = 12 MB/s
test goser::capnp::bench_deserialize ... bench: 2,019 ns/iter (+/- 85) = 221 MB/s
test goser::capnp::bench_deserialize_packed ... bench: 10,662 ns/iter (+/- 527) = 31 MB/s
test goser::capnp::bench_populate ... bench: 607 ns/iter (+/- 2)
test goser::capnp::bench_serialize ... bench: 30,488 ns/iter (+/- 219) = 14 MB/s
test goser::capnp::bench_serialize_packed ... bench: 33,731 ns/iter (+/- 201) = 9 MB/s
test goser::msgpack::bench_decoder ... bench: 46,921 ns/iter (+/- 461) = 6 MB/s
test goser::msgpack::bench_encoder ... bench: 22,315 ns/iter (+/- 96) = 12 MB/s
test goser::msgpack::bench_populate ... bench: 17,268 ns/iter (+/- 73)
test goser::protobuf::bench_decoder ... bench: 2,658 ns/iter (+/- 44) = 107 MB/s
test goser::protobuf::bench_encoder ... bench: 71,024 ns/iter (+/- 359) = 4 MB/s
test goser::protobuf::bench_populate ... bench: 17,704 ns/iter (+/- 104)
test goser::rustc_serialize_json::bench_decoder ... bench: 107,867 ns/iter (+/- 759) = 5 MB/s
test goser::rustc_serialize_json::bench_encoder ... bench: 52,327 ns/iter (+/- 479) = 11 MB/s
test goser::rustc_serialize_json::bench_populate ... bench: 17,262 ns/iter (+/- 68)
test goser::serde_json::bench_deserializer ... bench: 99,156 ns/iter (+/- 657) = 6 MB/s
test goser::serde_json::bench_populate ... bench: 17,264 ns/iter (+/- 77)
test goser::serde_json::bench_serializer ... bench: 66,135 ns/iter (+/- 392) = 9 MB/s
```
2015-09-18 15:46:58 +02:00
|
|
|
|
|
|
|
// CHECK-LABEL: @no_op_slice_adjustment2
|
|
|
|
#[no_mangle]
|
|
|
|
pub fn no_op_slice_adjustment2(x: &[u8]) -> &[u8] {
|
|
|
|
// We used to generate an extra alloca and memcpy for the function's return value, so check
|
|
|
|
// that there's no memcpy (the slice is written to sret_slot element-wise)
|
|
|
|
// CHECK-NOT: call void @llvm.memcpy.
|
|
|
|
no_op_slice_adjustment(x)
|
|
|
|
}
|