Extract SipHash implementation into a header. #134197
Open
+168
−130
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Created using spr 1.3.6-beta.1
|
@llvm/pr-subscribers-llvm-support Author: Peter Collingbourne (pcc) ChangesThis is so that we'll be able to use it in compiler-rt as well. Full diff: https://github.com/llvm/llvm-project/pull/134197.diff 4 Files Affected:
diff --git a/llvm/lib/Support/CMakeLists.txt b/llvm/lib/Support/CMakeLists.txt
index 2754c97fce6c1..1b18eb7c6346b 100644
--- a/llvm/lib/Support/CMakeLists.txt
+++ b/llvm/lib/Support/CMakeLists.txt
@@ -368,3 +368,8 @@ if(LLVM_WITH_Z3)
${Z3_INCLUDE_DIR}
)
endif()
+
+target_include_directories(LLVMSupport SYSTEM
+ PRIVATE
+ ${LLVM_THIRD_PARTY_DIR}/siphash/include
+ )
diff --git a/llvm/lib/Support/SipHash.cpp b/llvm/lib/Support/SipHash.cpp
index 68545913a4f59..682e9231c776f 100644
--- a/llvm/lib/Support/SipHash.cpp
+++ b/llvm/lib/Support/SipHash.cpp
@@ -15,9 +15,9 @@
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringRef.h"
-#include "llvm/Support/Compiler.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/Endian.h"
+#include "siphash/SipHash.h"
#include <cstdint>
using namespace llvm;
@@ -25,135 +25,6 @@ using namespace support;
#define DEBUG_TYPE "llvm-siphash"
-// Lightly adapted from the SipHash reference C implementation:
-// https://github.com/veorq/SipHash
-// by Jean-Philippe Aumasson and Daniel J. Bernstein
-
-#define ROTL(x, b) (uint64_t)(((x) << (b)) | ((x) >> (64 - (b))))
-
-#define SIPROUND \
- do { \
- v0 += v1; \
- v1 = ROTL(v1, 13); \
- v1 ^= v0; \
- v0 = ROTL(v0, 32); \
- v2 += v3; \
- v3 = ROTL(v3, 16); \
- v3 ^= v2; \
- v0 += v3; \
- v3 = ROTL(v3, 21); \
- v3 ^= v0; \
- v2 += v1; \
- v1 = ROTL(v1, 17); \
- v1 ^= v2; \
- v2 = ROTL(v2, 32); \
- } while (0)
-
-namespace {
-
-/// Computes a SipHash value
-///
-/// \param in: pointer to input data (read-only)
-/// \param inlen: input data length in bytes (any size_t value)
-/// \param k: reference to the key data 16-byte array (read-only)
-/// \returns output data, must be 8 or 16 bytes
-///
-template <int cROUNDS, int dROUNDS, size_t outlen>
-void siphash(const unsigned char *in, uint64_t inlen,
- const unsigned char (&k)[16], unsigned char (&out)[outlen]) {
-
- const unsigned char *ni = (const unsigned char *)in;
- const unsigned char *kk = (const unsigned char *)k;
-
- static_assert(outlen == 8 || outlen == 16, "result should be 8 or 16 bytes");
-
- uint64_t v0 = UINT64_C(0x736f6d6570736575);
- uint64_t v1 = UINT64_C(0x646f72616e646f6d);
- uint64_t v2 = UINT64_C(0x6c7967656e657261);
- uint64_t v3 = UINT64_C(0x7465646279746573);
- uint64_t k0 = endian::read64le(kk);
- uint64_t k1 = endian::read64le(kk + 8);
- uint64_t m;
- int i;
- const unsigned char *end = ni + inlen - (inlen % sizeof(uint64_t));
- const int left = inlen & 7;
- uint64_t b = ((uint64_t)inlen) << 56;
- v3 ^= k1;
- v2 ^= k0;
- v1 ^= k1;
- v0 ^= k0;
-
- if (outlen == 16)
- v1 ^= 0xee;
-
- for (; ni != end; ni += 8) {
- m = endian::read64le(ni);
- v3 ^= m;
-
- for (i = 0; i < cROUNDS; ++i)
- SIPROUND;
-
- v0 ^= m;
- }
-
- switch (left) {
- case 7:
- b |= ((uint64_t)ni[6]) << 48;
- LLVM_FALLTHROUGH;
- case 6:
- b |= ((uint64_t)ni[5]) << 40;
- LLVM_FALLTHROUGH;
- case 5:
- b |= ((uint64_t)ni[4]) << 32;
- LLVM_FALLTHROUGH;
- case 4:
- b |= ((uint64_t)ni[3]) << 24;
- LLVM_FALLTHROUGH;
- case 3:
- b |= ((uint64_t)ni[2]) << 16;
- LLVM_FALLTHROUGH;
- case 2:
- b |= ((uint64_t)ni[1]) << 8;
- LLVM_FALLTHROUGH;
- case 1:
- b |= ((uint64_t)ni[0]);
- break;
- case 0:
- break;
- }
-
- v3 ^= b;
-
- for (i = 0; i < cROUNDS; ++i)
- SIPROUND;
-
- v0 ^= b;
-
- if (outlen == 16)
- v2 ^= 0xee;
- else
- v2 ^= 0xff;
-
- for (i = 0; i < dROUNDS; ++i)
- SIPROUND;
-
- b = v0 ^ v1 ^ v2 ^ v3;
- endian::write64le(out, b);
-
- if (outlen == 8)
- return;
-
- v1 ^= 0xdd;
-
- for (i = 0; i < dROUNDS; ++i)
- SIPROUND;
-
- b = v0 ^ v1 ^ v2 ^ v3;
- endian::write64le(out + 8, b);
-}
-
-} // end anonymous namespace
-
void llvm::getSipHash_2_4_64(ArrayRef<uint8_t> In, const uint8_t (&K)[16],
uint8_t (&Out)[8]) {
siphash<2, 4>(In.data(), In.size(), K, Out);
diff --git a/llvm/utils/gn/secondary/llvm/lib/Support/BUILD.gn b/llvm/utils/gn/secondary/llvm/lib/Support/BUILD.gn
index fe7ff6ef68f99..5461ed5246b85 100644
--- a/llvm/utils/gn/secondary/llvm/lib/Support/BUILD.gn
+++ b/llvm/utils/gn/secondary/llvm/lib/Support/BUILD.gn
@@ -31,6 +31,7 @@ static_library("Support") {
include_dirs = [
"Unix",
"Windows",
+ "//third-party/siphash/include",
]
sources = [
"AArch64AttributeParser.cpp",
diff --git a/third-party/siphash/include/siphash/SipHash.h b/third-party/siphash/include/siphash/SipHash.h
new file mode 100644
index 0000000000000..9653e9428b123
--- /dev/null
+++ b/third-party/siphash/include/siphash/SipHash.h
@@ -0,0 +1,161 @@
+//===--- SipHash.h - An implementation of SipHash -------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This is a header-only implementation of SipHash. It lacks library
+// dependencies so it can be used from LLVM and compiler-rt.
+//
+//===----------------------------------------------------------------------===//
+
+#include <stddef.h>
+#include <stdint.h>
+
+// Lightly adapted from the SipHash reference C implementation:
+// https://github.com/veorq/SipHash
+// by Jean-Philippe Aumasson and Daniel J. Bernstein
+
+#define ROTL(x, b) (uint64_t)(((x) << (b)) | ((x) >> (64 - (b))))
+
+#define U32TO8_LE(p, v) \
+ (p)[0] = (uint8_t)((v)); \
+ (p)[1] = (uint8_t)((v) >> 8); \
+ (p)[2] = (uint8_t)((v) >> 16); \
+ (p)[3] = (uint8_t)((v) >> 24);
+
+#define U64TO8_LE(p, v) \
+ U32TO8_LE((p), (uint32_t)((v))); \
+ U32TO8_LE((p) + 4, (uint32_t)((v) >> 32));
+
+#define U8TO64_LE(p) \
+ (((uint64_t)((p)[0])) | ((uint64_t)((p)[1]) << 8) | \
+ ((uint64_t)((p)[2]) << 16) | ((uint64_t)((p)[3]) << 24) | \
+ ((uint64_t)((p)[4]) << 32) | ((uint64_t)((p)[5]) << 40) | \
+ ((uint64_t)((p)[6]) << 48) | ((uint64_t)((p)[7]) << 56))
+
+#define SIPROUND \
+ do { \
+ v0 += v1; \
+ v1 = ROTL(v1, 13); \
+ v1 ^= v0; \
+ v0 = ROTL(v0, 32); \
+ v2 += v3; \
+ v3 = ROTL(v3, 16); \
+ v3 ^= v2; \
+ v0 += v3; \
+ v3 = ROTL(v3, 21); \
+ v3 ^= v0; \
+ v2 += v1; \
+ v1 = ROTL(v1, 17); \
+ v1 ^= v2; \
+ v2 = ROTL(v2, 32); \
+ } while (0)
+
+namespace {
+
+/// Computes a SipHash value
+///
+/// \param in: pointer to input data (read-only)
+/// \param inlen: input data length in bytes (any size_t value)
+/// \param k: reference to the key data 16-byte array (read-only)
+/// \returns output data, must be 8 or 16 bytes
+///
+template <int cROUNDS, int dROUNDS, size_t outlen>
+void siphash(const unsigned char *in, uint64_t inlen,
+ const unsigned char (&k)[16], unsigned char (&out)[outlen]) {
+
+ const unsigned char *ni = (const unsigned char *)in;
+ const unsigned char *kk = (const unsigned char *)k;
+
+ static_assert(outlen == 8 || outlen == 16, "result should be 8 or 16 bytes");
+
+ uint64_t v0 = UINT64_C(0x736f6d6570736575);
+ uint64_t v1 = UINT64_C(0x646f72616e646f6d);
+ uint64_t v2 = UINT64_C(0x6c7967656e657261);
+ uint64_t v3 = UINT64_C(0x7465646279746573);
+ uint64_t k0 = U8TO64_LE(kk);
+ uint64_t k1 = U8TO64_LE(kk + 8);
+ uint64_t m;
+ int i;
+ const unsigned char *end = ni + inlen - (inlen % sizeof(uint64_t));
+ const int left = inlen & 7;
+ uint64_t b = ((uint64_t)inlen) << 56;
+ v3 ^= k1;
+ v2 ^= k0;
+ v1 ^= k1;
+ v0 ^= k0;
+
+ if (outlen == 16)
+ v1 ^= 0xee;
+
+ for (; ni != end; ni += 8) {
+ m = U8TO64_LE(ni);
+ v3 ^= m;
+
+ for (i = 0; i < cROUNDS; ++i)
+ SIPROUND;
+
+ v0 ^= m;
+ }
+
+ switch (left) {
+ case 7:
+ b |= ((uint64_t)ni[6]) << 48;
+ /* FALLTHRU */
+ case 6:
+ b |= ((uint64_t)ni[5]) << 40;
+ /* FALLTHRU */
+ case 5:
+ b |= ((uint64_t)ni[4]) << 32;
+ /* FALLTHRU */
+ case 4:
+ b |= ((uint64_t)ni[3]) << 24;
+ /* FALLTHRU */
+ case 3:
+ b |= ((uint64_t)ni[2]) << 16;
+ /* FALLTHRU */
+ case 2:
+ b |= ((uint64_t)ni[1]) << 8;
+ /* FALLTHRU */
+ case 1:
+ b |= ((uint64_t)ni[0]);
+ /* FALLTHRU */
+ break;
+ case 0:
+ break;
+ }
+
+ v3 ^= b;
+
+ for (i = 0; i < cROUNDS; ++i)
+ SIPROUND;
+
+ v0 ^= b;
+
+ if (outlen == 16)
+ v2 ^= 0xee;
+ else
+ v2 ^= 0xff;
+
+ for (i = 0; i < dROUNDS; ++i)
+ SIPROUND;
+
+ b = v0 ^ v1 ^ v2 ^ v3;
+ U64TO8_LE(out, b);
+
+ if (outlen == 8)
+ return;
+
+ v1 ^= 0xdd;
+
+ for (i = 0; i < dROUNDS; ++i)
+ SIPROUND;
+
+ b = v0 ^ v1 ^ v2 ^ v3;
+ U64TO8_LE(out + 8, b);
+}
+
+} // end anonymous namespace
|
|
✅ With the latest revision this PR passed the C/C++ code formatter. |
pcc
added a commit
to pcc/llvm-project
that referenced
this pull request
Apr 3, 2025
This is so that we'll be able to use it in compiler-rt as well. Dependencies on LLVM Support were removed from the header by restoring code from the original SipHash implementation. Pull Request: llvm#134197
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is so that we'll be able to use it in compiler-rt as well.
Dependencies on LLVM Support were removed from the header by restoring
code from the original SipHash implementation.