v1-zero-extend-instead-of-cast.patch

text/x-patch

Filename: v1-zero-extend-instead-of-cast.patch
Type: text/x-patch
Part: 0
Message: Re: Improve CRC32C performance on SSE4.2

Patch

Same data as JSON: GET /api/v1/attachments/:id/patch the parsed metadata as JSON — format, series position, per-file stats; never the diff bytes. API reference →
Format: unified
Series: patch v1
File+
src/port/pg_crc32c_sse42.c 1 1
src/port/pg_crc32c_sse42_choose.c 1 3
diff --git a/src/port/pg_crc32c_sse42.c b/src/port/pg_crc32c_sse42.c
index 9af3474a6ca..1a717255355 100644
--- a/src/port/pg_crc32c_sse42.c
+++ b/src/port/pg_crc32c_sse42.c
@@ -123,7 +123,7 @@ pg_comp_crc32c_avx512(pg_crc32c crc, const void *data, size_t len)
 		__m512i		k;
 
 		k = _mm512_broadcast_i32x4(_mm_setr_epi32(0x740eef02, 0, 0x9e4addf8, 0));
-		x0 = _mm512_xor_si512(_mm512_castsi128_si512(_mm_cvtsi32_si128(crc0)), x0);
+		x0 = _mm512_xor_si512(_mm512_zextsi128_si512(_mm_cvtsi32_si128(crc0)), x0);
 		buf += 64;
 
 		/* Main loop. */
diff --git a/src/port/pg_crc32c_sse42_choose.c b/src/port/pg_crc32c_sse42_choose.c
index 802e47788c1..74d2421ba2b 100644
--- a/src/port/pg_crc32c_sse42_choose.c
+++ b/src/port/pg_crc32c_sse42_choose.c
@@ -95,9 +95,7 @@ pg_comp_crc32c_choose(pg_crc32c crc, const void *data, size_t len)
 			__cpuidex(exx, 7, 0);
 #endif
 
-#if defined(__clang__) && !defined(__OPTIMIZE__)
-			/* Some versions of clang are broken at -O0 */
-#elif defined(USE_AVX512_CRC32C_WITH_RUNTIME_CHECK)
+#ifdef USE_AVX512_CRC32C_WITH_RUNTIME_CHECK
 			if (exx[2] & (1 << 10) &&	/* VPCLMULQDQ */
 				exx[1] & (1 << 31)) /* AVX512-VL */
 				pg_comp_crc32c = pg_comp_crc32c_avx512;