Patch Detail

HTTP 200 OK
Allow: GET, PUT, PATCH, HEAD, OPTIONS
Content-Type: application/json
Vary: Accept

{
    "id": 133679,
    "url": "http://patches.dpdk.org/api/patches/133679/?format=api",
    "web_url": "http://patches.dpdk.org/project/dpdk/patch/20231031181046.1203681-2-paul.szczepanek@arm.com/",
    "project": {
        "id": 1,
        "url": "http://patches.dpdk.org/api/projects/1/?format=api",
        "name": "DPDK",
        "link_name": "dpdk",
        "list_id": "dev.dpdk.org",
        "list_email": "dev@dpdk.org",
        "web_url": "http://core.dpdk.org",
        "scm_url": "git://dpdk.org/dpdk",
        "webscm_url": "http://git.dpdk.org/dpdk",
        "list_archive_url": "https://inbox.dpdk.org/dev",
        "list_archive_url_format": "https://inbox.dpdk.org/dev/{}",
        "commit_url_format": ""
    },
    "msgid": "<20231031181046.1203681-2-paul.szczepanek@arm.com>",
    "list_archive_url": "https://inbox.dpdk.org/dev/20231031181046.1203681-2-paul.szczepanek@arm.com",
    "date": "2023-10-31T18:10:44",
    "name": "[v3,1/3] eal: add pointer compression functions",
    "commit_ref": null,
    "pull_url": null,
    "state": "superseded",
    "archived": true,
    "hash": "53c4a08b914749d4ec3a531f13b05d9498948581",
    "submitter": {
        "id": 3199,
        "url": "http://patches.dpdk.org/api/people/3199/?format=api",
        "name": "Paul Szczepanek",
        "email": "paul.szczepanek@arm.com"
    },
    "delegate": {
        "id": 1,
        "url": "http://patches.dpdk.org/api/users/1/?format=api",
        "username": "tmonjalo",
        "first_name": "Thomas",
        "last_name": "Monjalon",
        "email": "thomas@monjalon.net"
    },
    "mbox": "http://patches.dpdk.org/project/dpdk/patch/20231031181046.1203681-2-paul.szczepanek@arm.com/mbox/",
    "series": [
        {
            "id": 30077,
            "url": "http://patches.dpdk.org/api/series/30077/?format=api",
            "web_url": "http://patches.dpdk.org/project/dpdk/list/?series=30077",
            "date": "2023-10-31T18:10:43",
            "name": "add pointer compression API",
            "version": 3,
            "mbox": "http://patches.dpdk.org/series/30077/mbox/"
        }
    ],
    "comments": "http://patches.dpdk.org/api/patches/133679/comments/",
    "check": "success",
    "checks": "http://patches.dpdk.org/api/patches/133679/checks/",
    "tags": {},
    "related": [],
    "headers": {
        "Return-Path": "<dev-bounces@dpdk.org>",
        "X-Original-To": "patchwork@inbox.dpdk.org",
        "Delivered-To": "patchwork@inbox.dpdk.org",
        "Received": [
            "from mails.dpdk.org (mails.dpdk.org [217.70.189.124])\n\tby inbox.dpdk.org (Postfix) with ESMTP id 28E9C43255;\n\tTue, 31 Oct 2023 19:11:38 +0100 (CET)",
            "from mails.dpdk.org (localhost [127.0.0.1])\n\tby mails.dpdk.org (Postfix) with ESMTP id 80CCB40DDB;\n\tTue, 31 Oct 2023 19:11:21 +0100 (CET)",
            "from foss.arm.com (foss.arm.com [217.140.110.172])\n by mails.dpdk.org (Postfix) with ESMTP id 4B1504029E\n for <dev@dpdk.org>; Tue, 31 Oct 2023 19:11:16 +0100 (CET)",
            "from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14])\n by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 58403DA7;\n Tue, 31 Oct 2023 11:11:57 -0700 (PDT)",
            "from ampere-altra-2-2.usa.Arm.com (unknown [10.118.91.160])\n by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 8B9883F7F4;\n Tue, 31 Oct 2023 11:11:15 -0700 (PDT)"
        ],
        "From": "Paul Szczepanek <paul.szczepanek@arm.com>",
        "To": "dev@dpdk.org",
        "Cc": "Paul Szczepanek <paul.szczepanek@arm.com>,\n Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>,\n Kamalakshitha Aligeri <kamalakshitha.aligeri@arm.com>",
        "Subject": "[PATCH v3 1/3] eal: add pointer compression functions",
        "Date": "Tue, 31 Oct 2023 18:10:44 +0000",
        "Message-Id": "<20231031181046.1203681-2-paul.szczepanek@arm.com>",
        "X-Mailer": "git-send-email 2.25.1",
        "In-Reply-To": "<20231031181046.1203681-1-paul.szczepanek@arm.com>",
        "References": "<20230927150854.3670391-2-paul.szczepanek@arm.com>\n <20231031181046.1203681-1-paul.szczepanek@arm.com>",
        "MIME-Version": "1.0",
        "Content-Transfer-Encoding": "8bit",
        "X-BeenThere": "dev@dpdk.org",
        "X-Mailman-Version": "2.1.29",
        "Precedence": "list",
        "List-Id": "DPDK patches and discussions <dev.dpdk.org>",
        "List-Unsubscribe": "<https://mails.dpdk.org/options/dev>,\n <mailto:dev-request@dpdk.org?subject=unsubscribe>",
        "List-Archive": "<http://mails.dpdk.org/archives/dev/>",
        "List-Post": "<mailto:dev@dpdk.org>",
        "List-Help": "<mailto:dev-request@dpdk.org?subject=help>",
        "List-Subscribe": "<https://mails.dpdk.org/listinfo/dev>,\n <mailto:dev-request@dpdk.org?subject=subscribe>",
        "Errors-To": "dev-bounces@dpdk.org"
    },
    "content": "Add a new utility header for compressing pointers. The provided\nfunctions can store pointers in 32-bit offsets.\n\nThe compression takes advantage of the fact that pointers are\nusually located in a limited memory region (like a mempool).\nWe can compress them by converting them to offsets from a base\nmemory address. Offsets can be stored in fewer bytes (dictated\nby the memory region size and alignment of the pointer).\nFor example: an 8 byte aligned pointer which is part of a 32GB\nmemory pool can be stored in 4 bytes.\n\nSuggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>\nSigned-off-by: Paul Szczepanek <paul.szczepanek@arm.com>\nSigned-off-by: Kamalakshitha Aligeri <kamalakshitha.aligeri@arm.com>\nReviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>\n---\n .mailmap                           |   1 +\n lib/eal/include/meson.build        |   1 +\n lib/eal/include/rte_ptr_compress.h | 272 +++++++++++++++++++++++++++++\n 3 files changed, 274 insertions(+)\n create mode 100644 lib/eal/include/rte_ptr_compress.h\n\n--\n2.25.1",
    "diff": "diff --git a/.mailmap b/.mailmap\nindex 864d33ee46..3f0c9d32f5 100644\n--- a/.mailmap\n+++ b/.mailmap\n@@ -1058,6 +1058,7 @@ Paul Greenwalt <paul.greenwalt@intel.com>\n Paulis Gributs <paulis.gributs@intel.com>\n Paul Luse <paul.e.luse@intel.com>\n Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>\n+Paul Szczepanek <paul.szczepanek@arm.com>\n Pavan Kumar Linga <pavan.kumar.linga@intel.com>\n Pavan Nikhilesh <pbhagavatula@marvell.com> <pbhagavatula@caviumnetworks.com>\n Pavel Belous <pavel.belous@aquantia.com>\ndiff --git a/lib/eal/include/meson.build b/lib/eal/include/meson.build\nindex a0463efac7..17d8373648 100644\n--- a/lib/eal/include/meson.build\n+++ b/lib/eal/include/meson.build\n@@ -36,6 +36,7 @@ headers += files(\n         'rte_pci_dev_features.h',\n         'rte_per_lcore.h',\n         'rte_pflock.h',\n+\t'rte_ptr_compress.h',\n         'rte_random.h',\n         'rte_reciprocal.h',\n         'rte_seqcount.h',\ndiff --git a/lib/eal/include/rte_ptr_compress.h b/lib/eal/include/rte_ptr_compress.h\nnew file mode 100644\nindex 0000000000..ceb4662c14\n--- /dev/null\n+++ b/lib/eal/include/rte_ptr_compress.h\n@@ -0,0 +1,272 @@\n+/* SPDX-License-Identifier: BSD-shift-Clause\n+ * Copyright(c) 2023 Arm Limited\n+ */\n+\n+#ifndef RTE_PTR_COMPRESS_H\n+#define RTE_PTR_COMPRESS_H\n+\n+/**\n+ * @file\n+ * Pointer compression and decompression functions.\n+ *\n+ * When passing arrays full of pointers between threads, memory containing\n+ * the pointers is copied multiple times which is especially costly between\n+ * cores. These functions allow us to compress the pointers.\n+ *\n+ * Compression takes advantage of the fact that pointers are usually located in\n+ * a limited memory region (like a mempool). We compress them by converting them\n+ * to offsets from a base memory address. Offsets can be stored in fewer bytes.\n+ *\n+ * The compression functions come in two varieties: 32-bit and 16-bit.\n+ *\n+ * To determine how many bits are needed to compress the pointer calculate\n+ * the biggest offset possible (highest value pointer - base pointer)\n+ * and shift the value right according to alignment (shift by exponent of the\n+ * power of 2 of alignment: aligned by 4 - shift by 2, aligned by 8 - shift by\n+ * 3, etc.). The resulting value must fit in either 32 or 16 bits.\n+ *\n+ * For usage example and further explanation please see \"Pointer Compression\" in\n+ * doc/guides/prog_guide/env_abstraction_layer.rst\n+ */\n+\n+#include <stdint.h>\n+#include <inttypes.h>\n+\n+#include <rte_branch_prediction.h>\n+#include <rte_common.h>\n+#include <rte_debug.h>\n+#include <rte_vect.h>\n+\n+#ifdef __cplusplus\n+extern \"C\" {\n+#endif\n+\n+/**\n+ * Compress pointers into 32-bit offsets from base pointer.\n+ *\n+ * @note It is programmer's responsibility to ensure the resulting offsets fit\n+ * into 32 bits. Alignment of the structures pointed to by the pointers allows\n+ * us to drop bits from the offsets. This is controlled by the bit_shift\n+ * parameter. This means that if structures are aligned by 8 bytes they must be\n+ * within 32GB of the base pointer. If there is no such alignment guarantee they\n+ * must be within 4GB.\n+ *\n+ * @param ptr_base\n+ *   A pointer used to calculate offsets of pointers in src_table.\n+ * @param src_table\n+ *   A pointer to an array of pointers.\n+ * @param dest_table\n+ *   A pointer to an array of compressed pointers returned by this function.\n+ * @param n\n+ *   The number of objects to compress, must be strictly positive.\n+ * @param bit_shift\n+ *   Byte alignment of memory pointed to by the pointers allows for\n+ *   bits to be dropped from the offset and hence widen the memory region that\n+ *   can be covered. This controls how many bits are right shifted.\n+ **/\n+static __rte_always_inline void\n+rte_ptr_compress_32(void *ptr_base, void **src_table,\n+\t\tuint32_t *dest_table, unsigned int n, unsigned int bit_shift)\n+{\n+\tunsigned int i = 0;\n+#if defined RTE_HAS_SVE_ACLE\n+\tsvuint64_t v_src_table;\n+\tsvuint64_t v_dest_table;\n+\tsvbool_t pg = svwhilelt_b64(i, n);\n+\tdo {\n+\t\tv_src_table = svld1_u64(pg, (uint64_t *)src_table + i);\n+\t\tv_dest_table = svsub_x(pg, v_src_table, (uint64_t)ptr_base);\n+\t\tv_dest_table = svlsr_x(pg, v_dest_table, bit_shift);\n+\t\tsvst1w(pg, &dest_table[i], v_dest_table);\n+\t\ti += svcntd();\n+\t\tpg = svwhilelt_b64(i, n);\n+\t} while (svptest_any(svptrue_b64(), pg));\n+#elif defined __ARM_NEON\n+\tuint64_t ptr_diff;\n+\tuint64x2_t v_src_table;\n+\tuint64x2_t v_dest_table;\n+\t/* right shift is done by left shifting by negative int */\n+\tint64x2_t v_shift = vdupq_n_s64(-bit_shift);\n+\tuint64x2_t v_ptr_base = vdupq_n_u64((uint64_t)ptr_base);\n+\tfor (; i < (n & ~0x1); i += 2) {\n+\t\tv_src_table = vld1q_u64((const uint64_t *)src_table + i);\n+\t\tv_dest_table = vsubq_u64(v_src_table, v_ptr_base);\n+\t\tv_dest_table = vshlq_u64(v_dest_table, v_shift);\n+\t\tvst1_u32(dest_table + i, vqmovn_u64(v_dest_table));\n+\t}\n+\t/* process leftover single item in case of odd number of n */\n+\tif (unlikely(n & 0x1)) {\n+\t\tptr_diff = RTE_PTR_DIFF(src_table[i], ptr_base);\n+\t\tdest_table[i] = (uint32_t) (ptr_diff >> bit_shift);\n+\t}\n+#else\n+\tuintptr_t ptr_diff;\n+\tfor (; i < n; i++) {\n+\t\tptr_diff = RTE_PTR_DIFF(src_table[i], ptr_base);\n+\t\tptr_diff = ptr_diff >> bit_shift;\n+\t\tRTE_ASSERT(ptr_diff <= UINT32_MAX);\n+\t\tdest_table[i] = (uint32_t) ptr_diff;\n+\t}\n+#endif\n+}\n+\n+/**\n+ * Decompress pointers from 32-bit offsets from base pointer.\n+ *\n+ * @param ptr_base\n+ *   A pointer which was used to calculate offsets in src_table.\n+ * @param src_table\n+ *   A pointer to an array to compressed pointers.\n+ * @param dest_table\n+ *   A pointer to an array of decompressed pointers returned by this function.\n+ * @param n\n+ *   The number of objects to decompress, must be strictly positive.\n+ * @param bit_shift\n+ *   Byte alignment of memory pointed to by the pointers allows for\n+ *   bits to be dropped from the offset and hence widen the memory region that\n+ *   can be covered. This controls how many bits are left shifted when pointers\n+ *   are recovered from the offsets.\n+ **/\n+static __rte_always_inline void\n+rte_ptr_decompress_32(void *ptr_base, uint32_t *src_table,\n+\t\tvoid **dest_table, unsigned int n, unsigned int bit_shift)\n+{\n+\tunsigned int i = 0;\n+#if defined RTE_HAS_SVE_ACLE\n+\tsvuint64_t v_src_table;\n+\tsvuint64_t v_dest_table;\n+\tsvbool_t pg = svwhilelt_b64(i, n);\n+\tdo {\n+\t\tv_src_table = svld1uw_u64(pg, &src_table[i]);\n+\t\tv_src_table = svlsl_x(pg, v_src_table, bit_shift);\n+\t\tv_dest_table = svadd_x(pg, v_src_table, (uint64_t)ptr_base);\n+\t\tsvst1(pg, (uint64_t *)dest_table + i, v_dest_table);\n+\t\ti += svcntd();\n+\t\tpg = svwhilelt_b64(i, n);\n+\t} while (svptest_any(svptrue_b64(), pg));\n+#elif defined __ARM_NEON\n+\tuint64_t ptr_diff;\n+\tuint64x2_t v_src_table;\n+\tuint64x2_t v_dest_table;\n+\tint64x2_t v_shift = vdupq_n_s64(bit_shift);\n+\tuint64x2_t v_ptr_base = vdupq_n_u64((uint64_t)ptr_base);\n+\tfor (; i < (n & ~0x1); i += 2) {\n+\t\tv_src_table = vmovl_u32(vld1_u32(src_table + i));\n+\t\tv_src_table = vshlq_u64(v_dest_table, v_shift);\n+\t\tv_dest_table = vaddq_u64(v_src_table, v_ptr_base);\n+\t\tvst1q_u64((uint64_t *)dest_table + i, v_dest_table);\n+\t}\n+\t/* process leftover single item in case of odd number of n */\n+\tif (unlikely(n & 0x1)) {\n+\t\tptr_diff = ((uint64_t) src_table[i]) << bit_shift;\n+\t\tdest_table[i] = RTE_PTR_ADD(ptr_base, ptr_diff);\n+\t}\n+#else\n+\tuintptr_t ptr_diff;\n+\tfor (; i < n; i++) {\n+\t\tptr_diff = ((uintptr_t) src_table[i]) << bit_shift;\n+\t\tdest_table[i] = RTE_PTR_ADD(ptr_base, ptr_diff);\n+\t}\n+#endif\n+}\n+\n+/**\n+ * Compress pointers into 16-bit offsets from base pointer.\n+ *\n+ * @note It is programmer's responsibility to ensure the resulting offsets fit\n+ * into 16 bits. Alignment of the structures pointed to by the pointers allows\n+ * us to drop bits from the offsets. This is controlled by the bit_shift\n+ * parameter. This means that if structures are aligned by 8 bytes they must be\n+ * within 256KB of the base pointer. If there is no such alignment guarantee\n+ * they must be within 64KB.\n+ *\n+ * @param ptr_base\n+ *   A pointer used to calculate offsets of pointers in src_table.\n+ * @param src_table\n+ *   A pointer to an array of pointers.\n+ * @param dest_table\n+ *   A pointer to an array of compressed pointers returned by this function.\n+ * @param n\n+ *   The number of objects to compress, must be strictly positive.\n+ * @param bit_shift\n+ *   Byte alignment of memory pointed to by the pointers allows for\n+ *   bits to be dropped from the offset and hence widen the memory region that\n+ *   can be covered. This controls how many bits are right shifted.\n+ **/\n+static __rte_always_inline void\n+rte_ptr_compress_16(void *ptr_base, void **src_table,\n+\t\tuint16_t *dest_table, unsigned int n, unsigned int bit_shift)\n+{\n+\n+\tunsigned int i = 0;\n+#if defined RTE_HAS_SVE_ACLE\n+\tsvuint64_t v_src_table;\n+\tsvuint64_t v_dest_table;\n+\tsvbool_t pg = svwhilelt_b64(i, n);\n+\tdo {\n+\t\tv_src_table = svld1_u64(pg, (uint64_t *)src_table + i);\n+\t\tv_dest_table = svsub_x(pg, v_src_table, (uint64_t)ptr_base);\n+\t\tv_dest_table = svlsr_x(pg, v_dest_table, bit_shift);\n+\t\tsvst1h(pg, &dest_table[i], v_dest_table);\n+\t\ti += svcntd();\n+\t\tpg = svwhilelt_b64(i, n);\n+\t} while (svptest_any(svptrue_b64(), pg));\n+#else\n+\tuintptr_t ptr_diff;\n+\tfor (; i < n; i++) {\n+\t\tptr_diff = RTE_PTR_DIFF(src_table[i], ptr_base);\n+\t\tptr_diff = ptr_diff >> bit_shift;\n+\t\tRTE_ASSERT(ptr_diff <= UINT16_MAX);\n+\t\tdest_table[i] = (uint16_t) ptr_diff;\n+\t}\n+#endif\n+}\n+\n+/**\n+ * Decompress pointers from 16-bit offsets from base pointer.\n+ *\n+ * @param ptr_base\n+ *   A pointer which was used to calculate offsets in src_table.\n+ * @param src_table\n+ *   A pointer to an array to compressed pointers.\n+ * @param dest_table\n+ *   A pointer to an array of decompressed pointers returned by this function.\n+ * @param n\n+ *   The number of objects to decompress, must be strictly positive.\n+ * @param bit_shift\n+ *   Byte alignment of memory pointed to by the pointers allows for\n+ *   bits to be dropped from the offset and hence widen the memory region that\n+ *   can be covered. This controls how many bits are left shifted when pointers\n+ *   are recovered from the offsets.\n+ **/\n+static __rte_always_inline void\n+rte_ptr_decompress_16(void *ptr_base, uint16_t *src_table,\n+\t\tvoid **dest_table, unsigned int n, unsigned int bit_shift)\n+{\n+\tunsigned int i = 0;\n+#if defined RTE_HAS_SVE_ACLE\n+\tsvuint64_t v_src_table;\n+\tsvuint64_t v_dest_table;\n+\tsvbool_t pg = svwhilelt_b64(i, n);\n+\tdo {\n+\t\tv_src_table = svld1uh_u64(pg, &src_table[i]);\n+\t\tv_src_table = svlsl_x(pg, v_src_table, bit_shift);\n+\t\tv_dest_table = svadd_x(pg, v_src_table, (uint64_t)ptr_base);\n+\t\tsvst1(pg, (uint64_t *)dest_table + i, v_dest_table);\n+\t\ti += svcntd();\n+\t\tpg = svwhilelt_b64(i, n);\n+\t} while (svptest_any(svptrue_b64(), pg));\n+#else\n+\tuintptr_t ptr_diff;\n+\tfor (; i < n; i++) {\n+\t\tptr_diff = ((uintptr_t) src_table[i]) << bit_shift;\n+\t\tdest_table[i] = RTE_PTR_ADD(ptr_base, ptr_diff);\n+\t}\n+#endif\n+}\n+\n+#ifdef __cplusplus\n+}\n+#endif\n+\n+#endif /* RTE_PTR_COMPRESS_H */\n",
    "prefixes": [
        "v3",
        "1/3"
    ]
}