about summary refs log tree commit diff
path: root/compiler/rustc_span/src/source_map.rs
diff options
context:
space:
mode:
authorbors <bors@rust-lang.org>2023-04-18 22:27:15 +0000
committerbors <bors@rust-lang.org>2023-04-18 22:27:15 +0000
commitb3f13795093c3c6473fb88910947bf6a35bedb26 (patch)
tree472e7c40fdc344e7b75e94e5f2aa237b465d34a3 /compiler/rustc_span/src/source_map.rs
parentc609da59d9fc05b1c7dc879d79700ccd8140b5fc (diff)
parent073d99b25d2e656ea053ab8dae03ea921508da76 (diff)
downloadrust-b3f13795093c3c6473fb88910947bf6a35bedb26.tar.gz
rust-b3f13795093c3c6473fb88910947bf6a35bedb26.zip
Auto merge of #110083 - saethlin:encode-hashes-as-bytes, r=cjgillot
Encode hashes as bytes, not varint

In a few places, we store hashes as `u64` or `u128` and then apply `derive(Decodable, Encodable)` to the enclosing struct/enum. It is more efficient to encode hashes directly than try to apply some varint encoding. This PR adds two new types `Hash64` and `Hash128` which are produced by `StableHasher` and replace every use of storing a `u64` or `u128` that represents a hash.

Distribution of the byte lengths of leb128 encodings, from `x build --stage 2` with `incremental = true`

Before:
```
(  1) 373418203 (53.7%, 53.7%): 1
(  2) 196240113 (28.2%, 81.9%): 3
(  3) 108157958 (15.6%, 97.5%): 2
(  4)  17213120 ( 2.5%, 99.9%): 4
(  5)    223614 ( 0.0%,100.0%): 9
(  6)    216262 ( 0.0%,100.0%): 10
(  7)     15447 ( 0.0%,100.0%): 5
(  8)      3633 ( 0.0%,100.0%): 19
(  9)      3030 ( 0.0%,100.0%): 8
( 10)      1167 ( 0.0%,100.0%): 18
( 11)      1032 ( 0.0%,100.0%): 7
( 12)      1003 ( 0.0%,100.0%): 6
( 13)        10 ( 0.0%,100.0%): 16
( 14)        10 ( 0.0%,100.0%): 17
( 15)         5 ( 0.0%,100.0%): 12
( 16)         4 ( 0.0%,100.0%): 14
```

After:
```
(  1) 372939136 (53.7%, 53.7%): 1
(  2) 196240140 (28.3%, 82.0%): 3
(  3) 108014969 (15.6%, 97.5%): 2
(  4)  17192375 ( 2.5%,100.0%): 4
(  5)       435 ( 0.0%,100.0%): 5
(  6)        83 ( 0.0%,100.0%): 18
(  7)        79 ( 0.0%,100.0%): 10
(  8)        50 ( 0.0%,100.0%): 9
(  9)         6 ( 0.0%,100.0%): 19
```

The remaining 9 or 10 and 18 or 19 are `u64` and `u128` respectively that have the high bits set. As far as I can tell these are coming primarily from `SwitchTargets`.
Diffstat (limited to 'compiler/rustc_span/src/source_map.rs')
-rw-r--r--compiler/rustc_span/src/source_map.rs6
1 files changed, 3 insertions, 3 deletions
diff --git a/compiler/rustc_span/src/source_map.rs b/compiler/rustc_span/src/source_map.rs
index 7f29922f696..1294a8b8e6b 100644
--- a/compiler/rustc_span/src/source_map.rs
+++ b/compiler/rustc_span/src/source_map.rs
@@ -13,7 +13,7 @@ pub use crate::hygiene::{ExpnData, ExpnKind};
 pub use crate::*;
 
 use rustc_data_structures::fx::FxHashMap;
-use rustc_data_structures::stable_hasher::StableHasher;
+use rustc_data_structures::stable_hasher::{Hash128, Hash64, StableHasher};
 use rustc_data_structures::sync::{AtomicU32, Lrc, MappedReadGuard, ReadGuard, RwLock};
 use std::cmp;
 use std::hash::Hash;
@@ -138,7 +138,7 @@ impl FileLoader for RealFileLoader {
 pub struct StableSourceFileId {
     /// A hash of the source file's [`FileName`]. This is hash so that it's size
     /// is more predictable than if we included the actual [`FileName`] value.
-    pub file_name_hash: u64,
+    pub file_name_hash: Hash64,
 
     /// The [`CrateNum`] of the crate this source file was originally parsed for.
     /// We cannot include this information in the hash because at the time
@@ -331,7 +331,7 @@ impl SourceMap {
         &self,
         filename: FileName,
         src_hash: SourceFileHash,
-        name_hash: u128,
+        name_hash: Hash128,
         source_len: usize,
         cnum: CrateNum,
         file_local_lines: Lock<SourceFileLines>,