xdiff: conditionally use Rust's implementation of xxhash

When no whitespace flags are present use xxhash, for faster
hashing, otherwise use DJB2a (which is what xdiff has been
using all along).

The benchmark below compares my series with version v2.49.0
(built in build_release/ and build_v2.49.0/ respectively),
running log commands on linux kernel with 3 different machines.

$ BASE=/path/to/git/root

    // laptop
    // CPU: 6-core Intel Core i7-8750H (-MT MCP-) speed/min/max: 726/800/4100 MHz
    $ hyperfine --warmup 3 -L exe $BASE/build_release/git,$BASE/build_v2.49.0/git '{exe} log --oneline --shortstat v6.8..v6.9 >/dev/null'
    Benchmark 1: /home/ezekiel/development/work/git/build_release/git log --oneline --shortstat v6.8..v6.9 >/dev/null
      Time (mean ± σ):     10.419 s ±  0.166 s    [User: 10.097 s, System: 0.284 s]
      Range (min … max):   10.215 s … 10.680 s    10 runs

    Benchmark 2: /home/ezekiel/development/work/git/build_v2.49.0/git log --oneline --shortstat v6.8..v6.9 >/dev/null
      Time (mean ± σ):     10.980 s ±  0.137 s    [User: 10.633 s, System: 0.308 s]
      Range (min … max):   10.791 s … 11.178 s    10 runs

    Summary
      /home/ezekiel/development/work/git/build_release/git log --oneline --shortstat v6.8..v6.9 >/dev/null ran
        1.05 ± 0.02 times faster than /home/ezekiel/development/work/git/build_v2.49.0/git log --oneline --shortstat v6.8..v6.9 >/dev/null

    // desktop
    // CPU: 8-core Intel Core i7-9700 (-MCP-) speed/min/max: 800/800/4700 MHz
    $ hyperfine --warmup 3 -L exe $BASE/build_release/git,$BASE/build_v2.49.0/git '{exe} log --oneline --shortstat v6.8..v6.9 >/dev/null'
    Benchmark 1: /home/steamuser/dev/git/build_release/git log --oneline --shortstat v6.8..v6.9 >/dev/null
      Time (mean ± σ):      6.823 s ±  0.020 s    [User: 6.624 s, System: 0.180 s]
      Range (min … max):    6.801 s …  6.858 s    10 runs

    Benchmark 2: /home/steamuser/dev/git/build_v2.49.0/git log --oneline --shortstat v6.8..v6.9 >/dev/null
      Time (mean ± σ):      8.151 s ±  0.024 s    [User: 7.928 s, System: 0.198 s]
      Range (min … max):    8.105 s …  8.184 s    10 runs

    Summary
      /home/steamuser/dev/git/build_release/git log --oneline --shortstat v6.8..v6.9 >/dev/null ran
        1.19 ± 0.01 times faster than /home/steamuser/dev/git/build_v2.49.0/git log --oneline --shortstat v6.8..v6.9 >/dev/null

    // router
    // CPU: dual core Intel Celeron 3965U (-MCP-) speed/min/max: 1300/400/2200 MHz
    $ hyperfine --warmup 3 -L exe $BASE/build_release/git,$BASE/build_v2.49.0/git '{exe} log --oneline --shortstat v6.8..v6.9 >/dev/null'
    Benchmark 1: /home/metal/dev/git/build_release/git log --oneline --shortstat v6.8..v6.9 >/dev/null
      Time (mean ± σ):     21.209 s ±  0.054 s    [User: 20.341 s, System: 0.605 s]
      Range (min … max):   21.135 s … 21.309 s    10 runs

    Benchmark 2: /home/metal/dev/git/build_v2.49.0/git log --oneline --shortstat v6.8..v6.9 >/dev/null
      Time (mean ± σ):     23.683 s ±  0.060 s    [User: 22.735 s, System: 0.672 s]
      Range (min … max):   23.566 s … 23.751 s    10 runs

    Summary
      /home/metal/dev/git/build_release/git log --oneline --shortstat v6.8..v6.9 >/dev/null ran
        1.12 ± 0.00 times faster than /home/metal/dev/git/build_v2.49.0/git log --oneline --shortstat v6.8..v6.9 >/dev/null

Signed-off-by: Ezekiel Newren <ezekielnewren@gmail.com>

Author: ezekielnewren

rust/Cargo.lock

@@ -13,3 +13,4 @@ crate-type = ["staticlib", "rlib"]
 
 [dependencies]
 interop = { path = "../interop" }
+xxhash-rust = { version = "0.8.15", features = ["xxh3"] }

rust/xdiff/Cargo.toml

@@ -0,0 +1,7 @@
+
+
+#[no_mangle]
+unsafe extern "C" fn xxh3_64(ptr: *const u8, size: usize) -> u64 {
+    let slice = std::slice::from_raw_parts(ptr, size);
+    xxhash_rust::xxh3::xxh3_64(slice)
+}

rust/xdiff/src/lib.rs

@@ -160,6 +160,9 @@ static void xdl_parse_lines(mmfile_t *mf, long narec, xdfile_t *xdf) {
 }
 
 
+extern u64 xxh3_64(u8 const* ptr, usize size);
+
+
 static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp,
 			   xdlclassifier_t *cf, xdfile_t *xdf) {
 	unsigned long *ha;
@@ -175,14 +178,26 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_
 
 	xdl_parse_lines(mf, narec, xdf);
 
+	if ((xpp->flags & XDF_WHITESPACE_FLAGS) == 0) {
+		for (usize i = 0; i < (usize) xdf->nrec; i++) {
+			xrecord_t *rec = xdf->recs[i];
+			rec->ha = xxh3_64(rec->ptr, rec->size);
+		}
+	} else {
+		for (usize i = 0; i < (usize) xdf->nrec; i++) {
+			xrecord_t *rec = xdf->recs[i];
+			char const* dump = (char const*) rec->ptr;
+			rec->ha = xdl_hash_record(&dump, (char const*) (rec->ptr + rec->size), xpp->flags);
+		}
+	}
+
 	for (usize i = 0; i < (usize) xdf->nrec; i++) {
 		xrecord_t *rec = xdf->recs[i];
-		char const* dump = (char const*) rec->ptr;
-		rec->ha = xdl_hash_record(&dump, (char const*) (rec->ptr + rec->size), xpp->flags);
 		xdl_classify_record(pass, cf, rec);
 	}
 
 
+
 	if (!XDL_CALLOC_ARRAY(rchg, xdf->nrec + 2))
 		goto abort;