From f27298314ac0bc3b1c226ed35f40d1e217837131 Mon Sep 17 00:00:00 2001 From: Nicholas Nethercote Date: Fri, 7 Feb 2020 11:53:07 +1100 Subject: [PATCH] Optimize `sip::Hasher::short_write`. This commit changes `sip::Hasher` to use the faster `short_write` approach that was used for `SipHasher128` in #68914. This has no effect because `sip::Hasher::short_write` is currently unused. See the next commit for more details, and a fix. (One difference with #68914 is that this commit doesn't apply the `u8to64_le` change from that PR, because I found it is slower, because it introduces `memcpy` calls with non-statically-known lengths. Therefore, this commit also undoes the `u8to64_le` change in `SipHasher128` for this reason. This doesn't affect `SipHasher128` much because it doesn't use `u8to64_le` much, but I am making the change to keep the two implementations consistent.) --- src/libcore/hash/sip.rs | 96 ++++++++++++++++++++++++++++------------- 1 file changed, 66 insertions(+), 30 deletions(-) diff --git a/src/libcore/hash/sip.rs b/src/libcore/hash/sip.rs index c4fbd9dbadaea..4768eb2d56103 100644 --- a/src/libcore/hash/sip.rs +++ b/src/libcore/hash/sip.rs @@ -221,35 +221,76 @@ impl Hasher { self.ntail = 0; } - // Specialized write function that is only valid for buffers with len <= 8. - // It's used to force inlining of write_u8 and write_usize, those would normally be inlined - // except for composite types (that includes slices and str hashing because of delimiter). - // Without this extra push the compiler is very reluctant to inline delimiter writes, - // degrading performance substantially for the most common use cases. + // A specialized write function for values with size <= 8. + // + // The hashing of multi-byte integers depends on endianness. E.g.: + // - little-endian: `write_u32(0xDDCCBBAA)` == `write([0xAA, 0xBB, 0xCC, 0xDD])` + // - big-endian: `write_u32(0xDDCCBBAA)` == `write([0xDD, 0xCC, 0xBB, 0xAA])` + // + // This function does the right thing for little-endian hardware. On + // big-endian hardware `x` must be byte-swapped first to give the right + // behaviour. After any byte-swapping, the input must be zero-extended to + // 64-bits. The caller is responsible for the byte-swapping and + // zero-extension. #[inline] - fn short_write(&mut self, msg: &[u8]) { - debug_assert!(msg.len() <= 8); - let length = msg.len(); - self.length += length; + fn short_write(&mut self, _x: T, x: u64) { + let size = mem::size_of::(); + self.length += size; + // The original number must be zero-extended, not sign-extended. + debug_assert!(if size < 8 { x >> (8 * size) == 0 } else { true }); + + // The number of bytes needed to fill `self.tail`. let needed = 8 - self.ntail; - let fill = cmp::min(length, needed); - if fill == 8 { - self.tail = unsafe { load_int_le!(msg, 0, u64) }; - } else { - self.tail |= unsafe { u8to64_le(msg, 0, fill) } << (8 * self.ntail); - if length < needed { - self.ntail += length; - return; - } + + // SipHash parses the input stream as 8-byte little-endian integers. + // Inputs are put into `self.tail` until 8 bytes of data have been + // collected, and then that word is processed. + // + // For example, imagine that `self.tail` is 0x0000_00EE_DDCC_BBAA, + // `self.ntail` is 5 (because 5 bytes have been put into `self.tail`), + // and `needed` is therefore 3. + // + // - Scenario 1, `self.write_u8(0xFF)`: we have already zero-extended + // the input to 0x0000_0000_0000_00FF. We now left-shift it five + // bytes, giving 0x0000_FF00_0000_0000. We then bitwise-OR that value + // into `self.tail`, resulting in 0x0000_FFEE_DDCC_BBAA. + // (Zero-extension of the original input is critical in this scenario + // because we don't want the high two bytes of `self.tail` to be + // touched by the bitwise-OR.) `self.tail` is not yet full, so we + // return early, after updating `self.ntail` to 6. + // + // - Scenario 2, `self.write_u32(0xIIHH_GGFF)`: we have already + // zero-extended the input to 0x0000_0000_IIHH_GGFF. We now + // left-shift it five bytes, giving 0xHHGG_FF00_0000_0000. We then + // bitwise-OR that value into `self.tail`, resulting in + // 0xHHGG_FFEE_DDCC_BBAA. `self.tail` is now full, and we can use it + // to update `self.state`. (As mentioned above, this assumes a + // little-endian machine; on a big-endian machine we would have + // byte-swapped 0xIIHH_GGFF in the caller, giving 0xFFGG_HHII, and we + // would then end up bitwise-ORing 0xGGHH_II00_0000_0000 into + // `self.tail`). + // + self.tail |= x << (8 * self.ntail); + if size < needed { + self.ntail += size; + return; } + + // `self.tail` is full, process it. self.state.v3 ^= self.tail; S::c_rounds(&mut self.state); self.state.v0 ^= self.tail; - // Buffered tail is now flushed, process new input. - self.ntail = length - needed; - self.tail = unsafe { u8to64_le(msg, needed, self.ntail) }; + // Continuing scenario 2: we have one byte left over from the input. We + // set `self.ntail` to 1 and `self.tail` to `0x0000_0000_IIHH_GGFF >> + // 8*3`, which is 0x0000_0000_0000_00II. (Or on a big-endian machine + // the prior byte-swapping would leave us with 0x0000_0000_0000_00FF.) + // + // The `if` is needed to avoid shifting by 64 bits, which Rust + // complains about. + self.ntail = size - needed; + self.tail = if needed < 8 { x >> (8 * needed) } else { 0 }; } } @@ -280,19 +321,14 @@ impl super::Hasher for SipHasher13 { } impl super::Hasher for Hasher { - // see short_write comment for explanation #[inline] - fn write_usize(&mut self, i: usize) { - let bytes = unsafe { - crate::slice::from_raw_parts(&i as *const usize as *const u8, mem::size_of::()) - }; - self.short_write(bytes); + fn write_u8(&mut self, i: u8) { + self.short_write(i, i as u64); } - // see short_write comment for explanation #[inline] - fn write_u8(&mut self, i: u8) { - self.short_write(&[i]); + fn write_usize(&mut self, i: usize) { + self.short_write(i, i.to_le() as u64); } #[inline]