From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga11.intel.com (mga11.intel.com [192.55.52.93]) by dpdk.org (Postfix) with ESMTP id 1A3FC5AC8 for ; Tue, 20 Jan 2015 19:41:37 +0100 (CET) Received: from orsmga003.jf.intel.com ([10.7.209.27]) by fmsmga102.fm.intel.com with ESMTP; 20 Jan 2015 10:41:23 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.09,435,1418112000"; d="scan'208";a="514984624" Received: from irvmail001.ir.intel.com ([163.33.26.43]) by orsmga003.jf.intel.com with ESMTP; 20 Jan 2015 10:34:44 -0800 Received: from sivswdev02.ir.intel.com (sivswdev02.ir.intel.com [10.237.217.46]) by irvmail001.ir.intel.com (8.14.3/8.13.6/MailSET/Hub) with ESMTP id t0KIfLM8029512; Tue, 20 Jan 2015 18:41:21 GMT Received: from sivswdev02.ir.intel.com (localhost [127.0.0.1]) by sivswdev02.ir.intel.com with ESMTP id t0KIfL9u018884; Tue, 20 Jan 2015 18:41:21 GMT Received: (from kananye1@localhost) by sivswdev02.ir.intel.com with id t0KIfLDp018880; Tue, 20 Jan 2015 18:41:21 GMT From: Konstantin Ananyev To: dev@dpdk.org Date: Tue, 20 Jan 2015 18:41:03 +0000 Message-Id: <1421779267-18492-15-git-send-email-konstantin.ananyev@intel.com> X-Mailer: git-send-email 1.7.4.1 In-Reply-To: <1421779267-18492-1-git-send-email-konstantin.ananyev@intel.com> References: <1421779267-18492-1-git-send-email-konstantin.ananyev@intel.com> Subject: [dpdk-dev] [PATCH v3 14/18] libter_acl: move lo/hi dwords shuffle out from calc_addr X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Jan 2015 18:41:40 -0000 Reorganise SSE code-path a bit by moving lo/hi dwords shuffle out from calc_addr(). That allows to make calc_addr() for SSE and AVX2 practically identical and opens opportunity for further code deduplication. Signed-off-by: Konstantin Ananyev --- lib/librte_acl/acl_run_sse.h | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) diff --git a/lib/librte_acl/acl_run_sse.h b/lib/librte_acl/acl_run_sse.h index 1b7870e..4a174e9 100644 --- a/lib/librte_acl/acl_run_sse.h +++ b/lib/librte_acl/acl_run_sse.h @@ -172,9 +172,9 @@ acl_match_check_x4(int slot, const struct rte_acl_ctx *ctx, struct parms *parms, */ static inline __attribute__((always_inline)) xmm_t calc_addr_sse(xmm_t index_mask, xmm_t next_input, xmm_t shuffle_input, - xmm_t ones_16, xmm_t indices1, xmm_t indices2) + xmm_t ones_16, xmm_t tr_lo, xmm_t tr_hi) { - xmm_t addr, node_types, range, temp; + xmm_t addr, node_types; xmm_t dfa_msk, dfa_ofs, quad_ofs; xmm_t in, r, t; @@ -187,18 +187,14 @@ calc_addr_sse(xmm_t index_mask, xmm_t next_input, xmm_t shuffle_input, * it reaches a match. */ - /* Shuffle low 32 into temp and high 32 into indices2 */ - temp = (xmm_t)MM_SHUFFLEPS((__m128)indices1, (__m128)indices2, 0x88); - range = (xmm_t)MM_SHUFFLEPS((__m128)indices1, (__m128)indices2, 0xdd); - t = MM_XOR(index_mask, index_mask); /* shuffle input byte to all 4 positions of 32 bit value */ in = MM_SHUFFLE8(next_input, shuffle_input); /* Calc node type and node addr */ - node_types = MM_ANDNOT(index_mask, temp); - addr = MM_AND(index_mask, temp); + node_types = MM_ANDNOT(index_mask, tr_lo); + addr = MM_AND(index_mask, tr_lo); /* * Calc addr for DFAs - addr = dfa_index + input_byte @@ -211,7 +207,7 @@ calc_addr_sse(xmm_t index_mask, xmm_t next_input, xmm_t shuffle_input, r = _mm_add_epi8(r, range_base); t = _mm_srli_epi32(in, 24); - r = _mm_shuffle_epi8(range, r); + r = _mm_shuffle_epi8(tr_hi, r); dfa_ofs = _mm_sub_epi32(t, r); @@ -224,22 +220,22 @@ calc_addr_sse(xmm_t index_mask, xmm_t next_input, xmm_t shuffle_input, */ /* check ranges */ - temp = MM_CMPGT8(in, range); + t = MM_CMPGT8(in, tr_hi); /* convert -1 to 1 (bytes greater than input byte */ - temp = MM_SIGN8(temp, temp); + t = MM_SIGN8(t, t); /* horizontal add pairs of bytes into words */ - temp = MM_MADD8(temp, temp); + t = MM_MADD8(t, t); /* horizontal add pairs of words into dwords */ - quad_ofs = MM_MADD16(temp, ones_16); + quad_ofs = MM_MADD16(t, ones_16); - /* mask to range type nodes */ - temp = _mm_blendv_epi8(quad_ofs, dfa_ofs, dfa_msk); + /* blend DFA and QUAD/SINGLE. */ + t = _mm_blendv_epi8(quad_ofs, dfa_ofs, dfa_msk); /* add index into node position */ - return MM_ADD32(addr, temp); + return MM_ADD32(addr, t); } /* @@ -249,13 +245,19 @@ static inline __attribute__((always_inline)) xmm_t transition4(xmm_t next_input, const uint64_t *trans, xmm_t *indices1, xmm_t *indices2) { - xmm_t addr; + xmm_t addr, tr_lo, tr_hi; uint64_t trans0, trans2; + /* Shuffle low 32 into tr_lo and high 32 into tr_hi */ + tr_lo = (xmm_t)_mm_shuffle_ps((__m128)*indices1, (__m128)*indices2, + 0x88); + tr_hi = (xmm_t)_mm_shuffle_ps((__m128)*indices1, (__m128)*indices2, + 0xdd); + /* Calculate the address (array index) for all 4 transitions. */ addr = calc_addr_sse(xmm_index_mask.x, next_input, xmm_shuffle_input.x, - xmm_ones_16.x, *indices1, *indices2); + xmm_ones_16.x, tr_lo, tr_hi); /* Gather 64 bit transitions and pack back into 2 registers. */ -- 1.8.5.3