I wrote:
>
> 1. I looked at a couple implementations of this idea, and found that
> the constants used in the carryless multiply are tied to the length of
> the blocks. With a lookup table we can do the 3-way algorithm on any
> portion of a full block length, rather than immediately fall to doing
> CRC serially. That would be faster on average. See for example
> https://github.com/komrad36/CRC/tree/master , but I don't think we
> actually have to fully unroll the loop like they do there.
>
> 2. With the above, we can use a larger full block size, and so on
> average less time would be spent in the carryless multiply. With that,
> we could possibly get away with an open coded loop in normal C rather
> than a new intrinsic (also found in the above repo). That would be
> more portable.
I added a port to x86 and poked at it, with the intent to have an easy
on-ramp to that at least accelerates computation of CRCs on FPIs.
The 0008 patch only worked on chunks of 1024 at a time. At that size,
the presence of hardware carryless multiplication is not that
important. I removed the hard-coded constants in favor of a lookup
table, so now it can handle anything up to 8400 bytes in a single
pass.
There are still some "taste" issues, but I like the overall shape here
and how light it was. With more hardware support, we can go much lower
than 1024 bytes, but that can be left for future work.
--
John Naylor
Amazon Web Services
From b889235866ad2593e7d093e6a74181a821b68430 Mon Sep 17 00:00:00 2001
From: John Naylor <john.nay...@postgresql.org>
Date: Wed, 11 Dec 2024 11:30:33 +0700
Subject: [PATCH v9 2/2] Implement interleaved CRC calculation, combined via
carryless multiplication
Changes from 0008:
- Use a lookup table to get the precomputed CRC instead of using constants.
This allows a single pass to handle up to 8400 bytes before combining CRCs.
On large inputs, we can just use a simple loop to emulate CLMUL
- Both Arm and x86 support, with no additional config or runtime checks.
Xiang Gao and John Naylor
---
src/include/port/pg_crc32c.h | 29 +++++++++++
src/port/pg_crc32c_armv8.c | 34 +++++++++++++
src/port/pg_crc32c_sb8.c | 94 ++++++++++++++++++++++++++++++++++++
src/port/pg_crc32c_sse42.c | 44 ++++++++++++++++-
4 files changed, 199 insertions(+), 2 deletions(-)
diff --git a/src/include/port/pg_crc32c.h b/src/include/port/pg_crc32c.h
index 63c8e3a00b..aa06bc201a 100644
--- a/src/include/port/pg_crc32c.h
+++ b/src/include/port/pg_crc32c.h
@@ -33,6 +33,7 @@
#ifndef PG_CRC32C_H
#define PG_CRC32C_H
+#include "port/pg_bitutils.h"
#include "port/pg_bswap.h"
typedef uint32 pg_crc32c;
@@ -107,4 +108,32 @@ extern pg_crc32c pg_comp_crc32c_sb8(pg_crc32c crc, const void *data, size_t len)
#endif
+
+/* semi-private to files in src/port that interleave CRC instructions */
+/* WIP: separate header in src/port? */
+
+#define CRC_BYTES_PER_ITER (3 * sizeof(uint64))
+#define CRC_MAX_BLOCK_LEN 350 /* can compute 8k inputs in a single pass */
+
+extern PGDLLIMPORT const uint64 combine_crc_lookup[CRC_MAX_BLOCK_LEN];
+
+/*
+ * Fallback for platforms that don't support intrinsics for carryless multiplication.
+ */
+static inline uint64
+pg_clmul(uint32 a, uint32 b)
+{
+ uint64 result = 0;
+
+ while (a)
+ {
+ int pos = pg_rightmost_one_pos32(a);
+
+ result ^= (uint64) b << (pos);
+ a &= a - 1;
+ }
+
+ return result;
+}
+
#endif /* PG_CRC32C_H */
diff --git a/src/port/pg_crc32c_armv8.c b/src/port/pg_crc32c_armv8.c
index d47d838c50..f9f155b65e 100644
--- a/src/port/pg_crc32c_armv8.c
+++ b/src/port/pg_crc32c_armv8.c
@@ -23,6 +23,8 @@ pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len)
{
const unsigned char *p = data;
const unsigned char *pend = p + len;
+ const size_t min_blocklen = 42; /* Min size to consider interleaving */
+ const pg_crc32c orig_crc = crc; // XXX not for commit
/*
* ARMv8 doesn't require alignment, but aligned memory access is
@@ -48,6 +50,36 @@ pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len)
p += 4;
}
+ /* See pg_crc32c_sse42.c for explanation */
+ while (p + min_blocklen * CRC_BYTES_PER_ITER <= pend)
+ {
+ const size_t block_len = Min(CRC_MAX_BLOCK_LEN, (pend - p) / CRC_BYTES_PER_ITER);
+ const uint64 *in64 = (const uint64 *) (p);
+ pg_crc32c crc0 = crc,
+ crc1 = 0,
+ crc2 = 0;
+ uint64 mul0,
+ mul1,
+ precompute;
+
+ for (int i = 0; i < block_len; i++, in64++)
+ {
+ crc0 = __crc32cd(crc0, *(in64));
+ crc1 = __crc32cd(crc1, *(in64 + block_len));
+ crc2 = __crc32cd(crc2, *(in64 + block_len * 2));
+ }
+
+ precompute = combine_crc_lookup[block_len - 1];
+ mul0 = pg_clmul(crc0, (uint32) precompute);
+ mul1 = pg_clmul(crc1, (uint32) (precompute >> 32));
+
+ crc0 = __crc32cd(0, mul0);
+ crc1 = __crc32cd(0, mul1);
+ crc = crc0 ^ crc1 ^ crc2;
+
+ p += block_len * CRC_BYTES_PER_ITER;
+ }
+
/* Process eight bytes at a time, as far as we can. */
while (p + 8 <= pend)
{
@@ -71,5 +103,7 @@ pg_comp_crc32c_armv8(pg_crc32c crc, const void *data, size_t len)
crc = __crc32cb(crc, *p);
}
+ // XXX not for commit
+ Assert(crc == pg_comp_crc32c_sb8(orig_crc, data, len));
return crc;
}
diff --git a/src/port/pg_crc32c_sb8.c b/src/port/pg_crc32c_sb8.c
index eda20fa747..48afd8c3d3 100644
--- a/src/port/pg_crc32c_sb8.c
+++ b/src/port/pg_crc32c_sb8.c
@@ -1167,3 +1167,97 @@ static const uint32 pg_crc32c_table[8][256] = {
}
#endif /* WORDS_BIGENDIAN */
};
+
+/* Lookup table for combining interleaved CRC computations */
+/* WIP: it seems not great to use _sb8.c for semi-common helpers for files CRC hardware support? */
+const uint64 combine_crc_lookup[CRC_MAX_BLOCK_LEN] =
+{
+ 0x00000001493c7d27, 0x493c7d27ba4fc28e, 0xf20c0dfeddc0152b, 0xba4fc28e9e4addf8,
+ 0x3da6d0cb39d3b296, 0xddc0152b0715ce53, 0x1c291d0447db8317, 0x9e4addf80d3b6092,
+ 0x740eef02c96cfdc0, 0x39d3b296878a92a7, 0x083a6eecdaece73e, 0x0715ce53ab7aff2a,
+ 0xc49f4f672162d385, 0x47db831783348832, 0x2ad91c30299847d5, 0x0d3b6092b9e02b86,
+ 0x6992cea218b33a4e, 0xc96cfdc0b6dd949b, 0x7e90804878d9ccb7, 0x878a92a7bac2fd7b,
+ 0x1b3d8f29a60ce07b, 0xdaece73ece7f39f4, 0xf1d0f55e61d82e56, 0xab7aff2ad270f1a2,
+ 0xa87ab8a8c619809d, 0x2162d3852b3cac5d, 0x8462d80065863b64, 0x833488321b03397f,
+ 0x71d111a8ebb883bd, 0x299847d5b3e32c28, 0xffd852c6064f7f26, 0xb9e02b86dd7e3b0c,
+ 0xdcb17aa4f285651c, 0x18b33a4e10746f3c, 0xf37c5aeec7a68855, 0xb6dd949b271d9844,
+ 0x6051d5a28e766a0c, 0x78d9ccb793a5f730, 0x18b0d4ff6cb08e5c, 0xbac2fd7b6b749fb2,
+ 0x21f3d99c1393e203, 0xa60ce07bcec3662e, 0x8f15801496c515bb, 0xce7f39f4e6fc4e6a,
+ 0xa00457f78227bb8a, 0x61d82e56b0cd4768, 0x8d6d2c4339c7ff35, 0xd270f1a2d7a4825c,
+ 0x00ac29cf0ab3844b, 0xc619809d0167d312, 0xe9adf796f6076544, 0x2b3cac5d26f6a60a,
+ 0x96638b34a741c1bf, 0x65863b6498d8d9cb, 0xe0e9f35149c3cc9c, 0x1b03397f68bce87a,
+ 0x9af01f2d57a3d037, 0xebb883bd6956fc3b, 0x2cff42cf42d98888, 0xb3e32c283771e98f,
+ 0x88f25a3ab42ae3d9, 0x064f7f262178513a, 0x4e36f0b0e0ac139e, 0xdd7e3b0c170076fa,
+ 0xbd6f81f8444dd413, 0xf285651c6f345e45, 0x91c9bd4b41d17b64, 0x10746f3cff0dba97,
+ 0x885f087ba2b73df1, 0xc7a68855f872e54c, 0x4c1449321e41e9fc, 0x271d984486d8e4d2,
+ 0x52148f02651bd98b, 0x8e766a0c5bb8f1bc, 0xa3c6f37aa90fd27a, 0x93a5f730b3af077a,
+ 0xd7c0557f4984d782, 0x6cb08e5cca6ef3ac, 0x63ded06a234e0b26, 0x6b749fb2dd66cbbb,
+ 0x4d56973c4597456a, 0x1393e203e9e28eb4, 0x9669c9df7b3ff57a, 0xcec3662ec9c8b782,
+ 0xe417f38a3f70cc6f, 0x96c515bb93e106a4, 0x4b9e0f7162ec6c6d, 0xe6fc4e6ad813b325,
+ 0xd104b8fc0df04680, 0x8227bb8a2342001e, 0x5b3977300a2a8d7e, 0xb0cd47686d9a4957,
+ 0xe78eb416e8b6368b, 0x39c7ff35d2c3ed1a, 0x61ff0e01995a5724, 0xd7a4825c9ef68d35,
+ 0x8d96551c0c139b31, 0x0ab3844bf2271e60, 0x0bf80dd20b0bf8ca, 0x0167d3122664fd8b,
+ 0x8821abeded64812d, 0xf607654402ee03b2, 0x6a45d2b28604ae0f, 0x26f6a60a363bd6b3,
+ 0xd8d26619135c83fd, 0xa741c1bf5fabe670, 0xde87806c35ec3279, 0x98d8d9cb00bcf5f6,
+ 0x143387548ae00689, 0x49c3cc9c17f27698, 0x5bd2011f58ca5f00, 0x68bce87aaa7c7ad5,
+ 0xdd07448eb5cfca28, 0x57a3d037ded288f8, 0xdde8f5b959f229bc, 0x6956fc3b6d390dec,
+ 0xa3e3e02c37170390, 0x42d988886353c1cc, 0xd73c7beac4584f5c, 0x3771e98ff48642e9,
+ 0x80ff0093531377e2, 0xb42ae3d9dd35bc8d, 0x8fe4c34db25b29f2, 0x2178513a9a5ede41,
+ 0xdf99fc11a563905d, 0xe0ac139e45cddf4e, 0x6c23e841acfa3103, 0x170076faa51b6135,
+ 0xfe314258dfd94fb2, 0x444dd41380f2886b, 0x0d8373a067969a6a, 0x6f345e45021ac5ef,
+ 0x19e3635ee8310afa, 0x41d17b6475451b04, 0x29f268b48e1450f7, 0xff0dba97cbbe4ee1,
+ 0x1dc0632a3a83de21, 0xa2b73df1e0cdcf86, 0x1614f396453c1679, 0xf872e54cdefba41c,
+ 0x9e2993d3613eee91, 0x1e41e9fcddaf5114, 0x6bebd73c1f1dd124, 0x86d8e4d2bedc6ba1,
+ 0x63ae91e6eca08ffe, 0x651bd98b3ae30875, 0xf8c9da7a0cd1526a, 0x5bb8f1bcb1630f04,
+ 0x945a19c1ff47317b, 0xa90fd27ad6c3a807, 0xee8213b79a7781e0, 0xb3af077a63d097e9,
+ 0x93781dc71d31175f, 0x4984d78294eb256e, 0xccc4a1b913184649, 0xca6ef3ac4be7fd90,
+ 0xa2c2d9717d5c1d64, 0x234e0b2680ba859a, 0x1cad44526eeed1c9, 0xdd66cbbb22c3799f,
+ 0x74922601d8ecc578, 0x4597456ab3a6da94, 0xc55f7eabcaf933fe, 0xe9e28eb450bfaade,
+ 0xa19623292e7d11a7, 0x7b3ff57a7d14748f, 0x2d37074932d8041c, 0xc9c8b782889774e1,
+ 0x397d84a16cc8a0ff, 0x3f70cc6f5aa1f3cf, 0x791132708a074012, 0x93e106a433bc58b3,
+ 0xbc8178039f2b002a, 0x62ec6c6dbd0bb25f, 0x88eb3c0760bf0a6a, 0xd813b3258515c07f,
+ 0x6e4cb6303be3c09b, 0x0df04680d8440525, 0x71971d5c682d085d, 0x2342001e465a4eee,
+ 0xf33b8bc628b5de82, 0x0a2a8d7e077d54e0, 0x9fb3bbc02e5f3c8c, 0x6d9a4957c00df280,
+ 0x6ef22b23d0a37f43, 0xe8b6368ba52f58ec, 0xce2df76800712e86, 0xd2c3ed1ad6748e82,
+ 0xe53a4fc747972100, 0x995a572451aeef66, 0xbe60a91a71900712, 0x9ef68d35359674f7,
+ 0x1dfa0a15647fbd15, 0x0c139b311baaa809, 0x8ec52396469aef86, 0xf2271e6086d42d06,
+ 0x0e766b114aba1470, 0x0b0bf8ca1c2cce0a, 0x475846a4aa0cd2d3, 0x2664fd8bf8448640,
+ 0xb2a3dfa6ac4fcdec, 0xed64812de81cf154, 0xdc1a160cc2c7385c, 0x02ee03b295ffd7dc,
+ 0x79afdf1c91de6176, 0x8604ae0f84ee89ac, 0x07ac6e46533e308d, 0x363bd6b35f0e0438,
+ 0x15f85253604d6e09, 0x135c83fdaeb3e622, 0x1bec24dd4263eb04, 0x5fabe67050c2cb16,
+ 0x4c36cd5b6667afe7, 0x35ec32791a6889b8, 0xe0a22e29de42c92a, 0x00bcf5f67f47463d,
+ 0x7c2b6ed9b82b6080, 0x8ae00689828d550b, 0x06ff88fddca2b4da, 0x17f276984ac726eb,
+ 0xf7317cf0529295e6, 0x58ca5f005e9f28eb, 0x61b6e40b40c14fff, 0xaa7c7ad596a1f19b,
+ 0xde8a97f8997157e1, 0xb5cfca28b0ed8196, 0x88f61445097e41e6, 0xded288f84ce8bfe5,
+ 0xd4520e9ee36841ad, 0x59f229bcd1a9427c, 0x0c592bd593f3319c, 0x6d390decb58ac6fe,
+ 0x38edfaf3e3809241, 0x37170390f22fd3e2, 0x72cbfcdb83c2df88, 0x6353c1ccd6b1825a,
+ 0x348331a54e4ff232, 0xc4584f5c6664d9c1, 0xc3977c19836b5a6e, 0xf48642e923d5e7e5,
+ 0xdafaea7c65065343, 0x531377e21495d20d, 0x73db4c04a29c82eb, 0xdd35bc8df370b37f,
+ 0x72675ce8ea6dd7dc, 0xb25b29f2e9415bce, 0x3ec2ff8396309b0f, 0x9a5ede41c776b648,
+ 0xe8c7a017c22c52c5, 0xa563905dcecfcd43, 0xcf4bfaefd8311ee7, 0x45cddf4e24e6fe8f,
+ 0x6bde1ac7d0c6d7c9, 0xacfa310345aa5d4a, 0xae1175c2cf067065, 0xa51b613582f89c77,
+ 0xf7506984a348c84e, 0xdfd94fb2d07737ea, 0xe0863e5636069dd2, 0x80f2886bc4cedd32,
+ 0xd7e661ae9a97be47, 0x67969a6af45cd585, 0x01afc14f93f36e2b, 0x021ac5ef195bc82d,
+ 0xd2fd8e3ce622aaca, 0xe8310afa23912612, 0xc4eb27b2a1fd0859, 0x75451b04a2edbd17,
+ 0x632098732cefbfdd, 0x8e1450f7f36d84e2, 0xf29971cf9664532d, 0xcbbe4ee1cfeff4b3,
+ 0xaf6939d96737eead, 0x3a83de21f52d28d3, 0x650ef6c5fb3bb2c8, 0xe0cdcf864a9d4498,
+ 0x36e108faaef471c1, 0x453c16790d08bb68, 0x09c20a6c3b6c03be, 0xdefba41c4de20a7c,
+ 0x0a1a6a8877792405, 0x613eee91b95a9eb0, 0x286d109b11f2bc8f, 0xddaf51147956e76a,
+ 0x9fd51b88032a8058, 0x1f1dd1241b93589c, 0x4860285dcc66546f, 0xbedc6ba1005bb964,
+ 0x6e221adc28198362, 0xeca08ffe3f2e57b1, 0x0e0a10735f54bb14, 0x3ae3087599e44d01,
+ 0x37f194212591f073, 0x0cd1526a0871bd30, 0xe9bbf6481fb48d12, 0xb1630f043888ed03,
+ 0x0fa0277f1e22167e, 0xff47317bd272cadf, 0xeb2fb89a8653215c, 0xd6c3a807f6e6d69e,
+ 0x1c47ed30b9f5bf62, 0x9a7781e09dde6145, 0x271cfb40ed49c4d3, 0x63d097e91ad321bc,
+ 0xea1cb6e7f206e4b8, 0x1d31175f60165873, 0x9f737f83159dff70, 0x94eb256ee1a468d0,
+ 0xd4619bbcda11f51b, 0x1318464993189d18, 0x794dd0f2ac4f4691, 0x4be7fd9087d07ae0,
+ 0xb6d42cd90db9f589, 0x7d5c1d64c51a240c, 0x8b9be230ab819fbb, 0x80ba859a5cc19671,
+ 0xd4617a4c46183f0a, 0x6eeed1c993e7c448, 0xb9f93bd067fe6e36, 0x22c3799fca110698,
+ 0xb8b67c1c8a2acc83, 0xd8ecc578eb75a090, 0xc5ca433a3e18bd99, 0xb3a6da94480e7e4d,
+ 0x5e5dcd9560bced33, 0xcaf933fe0bf69a3f, 0x7b589372dbf59471, 0x50bfaadea00bae3d,
+ 0x0afb7f3b4b7df256, 0x2e7d11a77959fe2a, 0x0f97c69068e3d179, 0x7d14748fa160e585,
+ 0x3e254fe4cac39a0b, 0x32d8041cf4229b7a, 0x141e8512007ca0f9, 0x889774e10e0126b2,
+ 0xe5e25bd082fe946e, 0x6cc8a0ff013b3856, 0xacf1231667c69966, 0x5aa1f3cffa0f2bd0,
+ 0x7b454cb35d4c91fc, 0x8a07401279d95f64, 0x311709b8807121c0, 0x33bc58b3b0a3f16d,
+ 0x9948a7d2618e0996, 0x9f2b002a2308bca9, 0x809cef1f343272b3, 0xbd0bb25ff5c40599,
+ 0x11dde5b740c1c64c, 0x60bf0a6a71cc89e8,
+};
diff --git a/src/port/pg_crc32c_sse42.c b/src/port/pg_crc32c_sse42.c
index dcc4904a82..d2b435956f 100644
--- a/src/port/pg_crc32c_sse42.c
+++ b/src/port/pg_crc32c_sse42.c
@@ -25,15 +25,53 @@ pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len)
{
const unsigned char *p = data;
const unsigned char *pend = p + len;
+ const size_t min_blocklen = 42; /* Min size to consider interleaving */
+ const pg_crc32c orig_crc = crc; /* XXX not for commit */
/*
- * Process eight bytes of data at a time.
- *
* NB: We do unaligned accesses here. The Intel architecture allows that,
* and performance testing didn't show any performance gain from aligning
* the begin address.
*/
#ifdef __x86_64__
+
+ /*
+ * On large inputs, we divide into 3 equal chunks and compute CRC on each
+ * independently. This works becasue we can combine the results using
+ * carryless mulitplication. This is faster because on many architectures
+ * a CRC instruction can be issued every cycle but the latency of its
+ * result will take several cycles.
+ */
+ while (p + min_blocklen * CRC_BYTES_PER_ITER <= pend)
+ {
+ const size_t block_len = Min(CRC_MAX_BLOCK_LEN, (pend - p) / CRC_BYTES_PER_ITER);
+ const uint64 *in64 = (const uint64 *) (p);
+ pg_crc32c crc0 = crc,
+ crc1 = 0,
+ crc2 = 0;
+ uint64 mul0,
+ mul1,
+ precompute;
+
+ for (int i = 0; i < block_len; i++, in64++)
+ {
+ crc0 = _mm_crc32_u64(crc0, *(in64));
+ crc1 = _mm_crc32_u64(crc1, *(in64 + block_len));
+ crc2 = _mm_crc32_u64(crc2, *(in64 + block_len * 2));
+ }
+
+ precompute = combine_crc_lookup[block_len - 1];
+ mul0 = pg_clmul(crc0, (uint32) precompute);
+ mul1 = pg_clmul(crc1, (uint32) (precompute >> 32));
+
+ crc0 = _mm_crc32_u64(0, mul0);
+ crc1 = _mm_crc32_u64(0, mul1);
+ crc = crc0 ^ crc1 ^ crc2;
+
+ p += block_len * CRC_BYTES_PER_ITER;
+ }
+
+ /* Process eight bytes of data at a time. */
while (p + 8 <= pend)
{
crc = (uint32) _mm_crc32_u64(crc, *((const uint64 *) p));
@@ -66,5 +104,7 @@ pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len)
p++;
}
+ /* XXX not for commit */
+ Assert(crc == pg_comp_crc32c_sb8(orig_crc, data, len));
return crc;
}
--
2.47.1
From 0bd72ee6440ded81531b3e0ec3009550a068bf11 Mon Sep 17 00:00:00 2001
From: Paul Amonson <paul.d.amon...@intel.com>
Date: Mon, 6 May 2024 08:34:17 -0700
Subject: [PATCH v9 1/2] Add a Postgres SQL function for crc32c benchmarking
Add a drive_crc32c() function to use for benchmarking crc32c
computation. The function takes 2 arguments:
(1) count: num of times CRC32C is computed in a loop.
(2) num: #bytes in the buffer to calculate crc over.
XXX not for commit
Extracted from a patch by Raghuveer Devulapalli
---
contrib/meson.build | 1 +
contrib/test_crc32c/Makefile | 20 +++++++
contrib/test_crc32c/expected/test_crc32c.out | 57 ++++++++++++++++++++
contrib/test_crc32c/meson.build | 34 ++++++++++++
contrib/test_crc32c/sql/test_crc32c.sql | 3 ++
contrib/test_crc32c/test_crc32c--1.0.sql | 1 +
contrib/test_crc32c/test_crc32c.c | 47 ++++++++++++++++
contrib/test_crc32c/test_crc32c.control | 4 ++
8 files changed, 167 insertions(+)
create mode 100644 contrib/test_crc32c/Makefile
create mode 100644 contrib/test_crc32c/expected/test_crc32c.out
create mode 100644 contrib/test_crc32c/meson.build
create mode 100644 contrib/test_crc32c/sql/test_crc32c.sql
create mode 100644 contrib/test_crc32c/test_crc32c--1.0.sql
create mode 100644 contrib/test_crc32c/test_crc32c.c
create mode 100644 contrib/test_crc32c/test_crc32c.control
diff --git a/contrib/meson.build b/contrib/meson.build
index 159ff41555..9275cb4ae9 100644
--- a/contrib/meson.build
+++ b/contrib/meson.build
@@ -12,6 +12,7 @@ contrib_doc_args = {
'install_dir': contrib_doc_dir,
}
+subdir('test_crc32c')
subdir('amcheck')
subdir('auth_delay')
subdir('auto_explain')
diff --git a/contrib/test_crc32c/Makefile b/contrib/test_crc32c/Makefile
new file mode 100644
index 0000000000..5b747c6184
--- /dev/null
+++ b/contrib/test_crc32c/Makefile
@@ -0,0 +1,20 @@
+MODULE_big = test_crc32c
+OBJS = test_crc32c.o
+PGFILEDESC = "test"
+EXTENSION = test_crc32c
+DATA = test_crc32c--1.0.sql
+
+first: all
+
+# test_crc32c.o: CFLAGS+=-g
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = src/test/modules/test_crc32c
+top_builddir = ../../../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/test_crc32c/expected/test_crc32c.out b/contrib/test_crc32c/expected/test_crc32c.out
new file mode 100644
index 0000000000..dff6bb3133
--- /dev/null
+++ b/contrib/test_crc32c/expected/test_crc32c.out
@@ -0,0 +1,57 @@
+CREATE EXTENSION test_crc32c;
+select drive_crc32c(1, i) from generate_series(100, 300, 4) i;
+ drive_crc32c
+--------------
+ 532139994
+ 2103623867
+ 785984197
+ 2686825890
+ 3213049059
+ 3819630168
+ 1389234603
+ 534072900
+ 2930108140
+ 2496889855
+ 1475239611
+ 136366931
+ 3067402116
+ 2012717871
+ 3682416023
+ 2054270645
+ 1817339875
+ 4100939569
+ 1192727539
+ 3636976218
+ 369764421
+ 3161609879
+ 1067984880
+ 1235066769
+ 3138425899
+ 648132037
+ 4203750233
+ 1330187888
+ 2683521348
+ 1951644495
+ 2574090107
+ 3904902018
+ 3772697795
+ 1644686344
+ 2868962106
+ 3369218491
+ 3902689890
+ 3456411865
+ 141004025
+ 1504497996
+ 3782655204
+ 3544797610
+ 3429174879
+ 2524728016
+ 3935861181
+ 25498897
+ 692684159
+ 345705535
+ 2761600287
+ 2654632420
+ 3945991399
+(51 rows)
+
diff --git a/contrib/test_crc32c/meson.build b/contrib/test_crc32c/meson.build
new file mode 100644
index 0000000000..d7bec4ba1c
--- /dev/null
+++ b/contrib/test_crc32c/meson.build
@@ -0,0 +1,34 @@
+# Copyright (c) 2022-2024, PostgreSQL Global Development Group
+
+test_crc32c_sources = files(
+ 'test_crc32c.c',
+)
+
+if host_system == 'windows'
+ test_crc32c_sources += rc_lib_gen.process(win32ver_rc, extra_args: [
+ '--NAME', 'test_crc32c',
+ '--FILEDESC', 'test_crc32c - test code for crc32c library',])
+endif
+
+test_crc32c = shared_module('test_crc32c',
+ test_crc32c_sources,
+ kwargs: contrib_mod_args,
+)
+contrib_targets += test_crc32c
+
+install_data(
+ 'test_crc32c.control',
+ 'test_crc32c--1.0.sql',
+ kwargs: contrib_data_args,
+)
+
+tests += {
+ 'name': 'test_crc32c',
+ 'sd': meson.current_source_dir(),
+ 'bd': meson.current_build_dir(),
+ 'regress': {
+ 'sql': [
+ 'test_crc32c',
+ ],
+ },
+}
diff --git a/contrib/test_crc32c/sql/test_crc32c.sql b/contrib/test_crc32c/sql/test_crc32c.sql
new file mode 100644
index 0000000000..95c6dfe448
--- /dev/null
+++ b/contrib/test_crc32c/sql/test_crc32c.sql
@@ -0,0 +1,3 @@
+CREATE EXTENSION test_crc32c;
+
+select drive_crc32c(1, i) from generate_series(100, 300, 4) i;
diff --git a/contrib/test_crc32c/test_crc32c--1.0.sql b/contrib/test_crc32c/test_crc32c--1.0.sql
new file mode 100644
index 0000000000..52b9772f90
--- /dev/null
+++ b/contrib/test_crc32c/test_crc32c--1.0.sql
@@ -0,0 +1 @@
+CREATE FUNCTION drive_crc32c (count int, num int) RETURNS bigint AS 'MODULE_PATHNAME' LANGUAGE C;
diff --git a/contrib/test_crc32c/test_crc32c.c b/contrib/test_crc32c/test_crc32c.c
new file mode 100644
index 0000000000..b350caf5ce
--- /dev/null
+++ b/contrib/test_crc32c/test_crc32c.c
@@ -0,0 +1,47 @@
+/* select drive_crc32c(1000000, 1024); */
+
+#include "postgres.h"
+#include "fmgr.h"
+#include "port/pg_crc32c.h"
+#include "common/pg_prng.h"
+
+PG_MODULE_MAGIC;
+
+/*
+ * drive_crc32c(count: int, num: int) returns bigint
+ *
+ * count is the nuimber of loops to perform
+ *
+ * num is the number byte in the buffer to calculate
+ * crc32c over.
+ */
+PG_FUNCTION_INFO_V1(drive_crc32c);
+Datum
+drive_crc32c(PG_FUNCTION_ARGS)
+{
+ int64 count = PG_GETARG_INT64(0);
+ int64 num = PG_GETARG_INT64(1);
+ char* data = malloc((size_t)num);
+ pg_crc32c crc;
+ pg_prng_state state;
+ uint64 seed = 42;
+ pg_prng_seed(&state, seed);
+ /* set random data */
+ for (uint64 i = 0; i < num; i++)
+ {
+ data[i] = pg_prng_uint32(&state) % 255;
+ }
+
+ INIT_CRC32C(crc);
+
+ while(count--)
+ {
+ INIT_CRC32C(crc);
+ COMP_CRC32C(crc, data, num);
+ FIN_CRC32C(crc);
+ }
+
+ free((void *)data);
+
+ PG_RETURN_INT64((int64_t)crc);
+}
diff --git a/contrib/test_crc32c/test_crc32c.control b/contrib/test_crc32c/test_crc32c.control
new file mode 100644
index 0000000000..878a077ee1
--- /dev/null
+++ b/contrib/test_crc32c/test_crc32c.control
@@ -0,0 +1,4 @@
+comment = 'test'
+default_version = '1.0'
+module_pathname = '$libdir/test_crc32c'
+relocatable = true
--
2.47.1
