From patchwork Wed Feb 15 17:09:41 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Hernan Vargas X-Patchwork-Id: 123971 X-Patchwork-Delegate: maxime.coquelin@redhat.com Return-Path: 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]) by inbox.dpdk.org (Postfix) with ESMTP id 704E141CA8; Wed, 15 Feb 2023 18:14:27 +0100 (CET) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 60F7B42D63; Wed, 15 Feb 2023 18:13:15 +0100 (CET) Received: from mga09.intel.com (mga09.intel.com [134.134.136.24]) by mails.dpdk.org (Postfix) with ESMTP id 95CB242D17 for ; Wed, 15 Feb 2023 18:13:02 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1676481182; x=1708017182; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=lHkXSaQ2Jbbvcfk9fKRmfFE08LeCMbGd1cI4JItPpk0=; b=M5JzceyFoLPViBmqHJMzYBU2Tfcme3wGtZFOahu05SQKR9qSVPUvMwMk tGEDm0Q3yb1xTScJflSra5rO9ruPIHpvQz6ayOf8SgkEYL0lcj4KFrKoZ hNgi/29qOCNoH2ddIP6VmyP5GXK1z8spKqABYwxnhXbbC6kpMlpN4Mxj6 meHLOuO+5M21PihvrA3OXKMvpYVzchSgpaE+8K5vIdzrxwM4QldfWZ1Qp y+lFNP4Q7106e0ot5h7sUSbEesS+cLhSJgMr2u2qxYhzvFduQFKOKK16D ykGgB5k9gG8IoDjrjsHBIEWYvfpLYBAQlWTw6UpZAeS6byeIwr/ImQCsP w==; X-IronPort-AV: E=McAfee;i="6500,9779,10622"; a="332789818" X-IronPort-AV: E=Sophos;i="5.97,300,1669104000"; d="scan'208";a="332789818" Received: from fmsmga003.fm.intel.com ([10.253.24.29]) by orsmga102.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 15 Feb 2023 09:10:00 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6500,9779,10622"; a="758489631" X-IronPort-AV: E=Sophos;i="5.97,300,1669104000"; d="scan'208";a="758489631" Received: from unknown (HELO csl-npg-qt0.la.intel.com) ([10.233.181.103]) by FMSMGA003.fm.intel.com with ESMTP; 15 Feb 2023 09:09:58 -0800 From: Hernan Vargas To: dev@dpdk.org, maxime.coquelin@redhat.com, gakhil@marvell.com, trix@redhat.com Cc: nicolas.chautru@intel.com, qi.z.zhang@intel.com, Hernan Vargas Subject: [PATCH v2 08/16] test/bbdev: add support for BLER for 4G Date: Wed, 15 Feb 2023 09:09:41 -0800 Message-Id: <20230215170949.60569-9-hernan.vargas@intel.com> X-Mailer: git-send-email 2.37.1 In-Reply-To: <20230215170949.60569-1-hernan.vargas@intel.com> References: <20230215170949.60569-1-hernan.vargas@intel.com> MIME-Version: 1.0 X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org New feature to add BLER support for 4G in test-bbdev. Signed-off-by: Hernan Vargas --- app/test-bbdev/test_bbdev_perf.c | 183 ++++++++++++++++++++++++++++++- 1 file changed, 182 insertions(+), 1 deletion(-) diff --git a/app/test-bbdev/test_bbdev_perf.c b/app/test-bbdev/test_bbdev_perf.c index e4eb71050a..acfefb7efa 100644 --- a/app/test-bbdev/test_bbdev_perf.c +++ b/app/test-bbdev/test_bbdev_perf.c @@ -1757,6 +1757,30 @@ gen_qm2_llr(int8_t *llrs, uint32_t j, double N0, double llr_max) llrs[j] = (int8_t) b; } +/* Simple LLR generation assuming AWGN and QPSK */ +static void +gen_turbo_llr(int8_t *llrs, uint32_t j, double N0, double llr_max) +{ + double b, b1, n; + double coeff = 2.0 * sqrt(N0); + + /* Ignore in vectors null LLRs not to be saturated */ + if (llrs[j] == 0) + return; + + /* Note don't change sign here */ + n = randn(j % 2); + b1 = ((llrs[j] > 0 ? 2.0 : -2.0) + + coeff * n) / N0; + b = b1 * (1 << 4); + b = round(b); + if (b > llr_max) + b = llr_max; + if (b < -llr_max) + b = -llr_max; + llrs[j] = (int8_t) b; +} + /* Generate LLR for a given SNR */ static void generate_llr_input(uint16_t n, struct rte_bbdev_op_data *inputs, @@ -1792,6 +1816,27 @@ generate_llr_input(uint16_t n, struct rte_bbdev_op_data *inputs, } } +/* Generate LLR for turbo decoder for a given SNR */ +static void +generate_turbo_llr_input(uint16_t n, struct rte_bbdev_op_data *inputs, + struct rte_bbdev_dec_op *ref_op) +{ + struct rte_mbuf *m; + uint32_t i, j, range; + double N0, llr_max; + + llr_max = 127; + range = ref_op->turbo_dec.input.length; + N0 = 1.0 / pow(10.0, get_snr() / 10.0); + + for (i = 0; i < n; ++i) { + m = inputs[i].data; + int8_t *llrs = rte_pktmbuf_mtod_offset(m, int8_t *, 0); + for (j = 0; j < range; ++j) + gen_turbo_llr(llrs, j, N0, llr_max); + } +} + static void copy_reference_ldpc_dec_op(struct rte_bbdev_dec_op **ops, unsigned int n, unsigned int start_idx, @@ -2306,6 +2351,30 @@ validate_ldpc_bler(struct rte_bbdev_dec_op **ops, const uint16_t n) return errors; } +/* Check Number of code blocks errors */ +static int +validate_turbo_bler(struct rte_bbdev_dec_op **ops, const uint16_t n) +{ + unsigned int i; + struct op_data_entries *hard_data_orig = &test_vector.entries[DATA_HARD_OUTPUT]; + struct rte_bbdev_op_turbo_dec *ops_td; + struct rte_bbdev_op_data *hard_output; + int errors = 0; + struct rte_mbuf *m; + + for (i = 0; i < n; ++i) { + ops_td = &ops[i]->turbo_dec; + hard_output = &ops_td->hard_output; + m = hard_output->data; + if (memcmp(rte_pktmbuf_mtod_offset(m, uint32_t *, 0), + hard_data_orig->segments[0].addr, + hard_data_orig->segments[0].length)) + errors++; + } + return errors; +} + + static int validate_ldpc_dec_op(struct rte_bbdev_dec_op **ops, const uint16_t n, struct rte_bbdev_dec_op *ref_op, const int vector_mask) @@ -3738,6 +3807,114 @@ bler_pmd_lcore_ldpc_dec(void *arg) return TEST_SUCCESS; } + +static int +bler_pmd_lcore_turbo_dec(void *arg) +{ + struct thread_params *tp = arg; + uint16_t enq, deq; + uint64_t total_time = 0, start_time; + const uint16_t queue_id = tp->queue_id; + const uint16_t burst_sz = tp->op_params->burst_sz; + const uint16_t num_ops = tp->op_params->num_to_process; + struct rte_bbdev_dec_op *ops_enq[num_ops]; + struct rte_bbdev_dec_op *ops_deq[num_ops]; + struct rte_bbdev_dec_op *ref_op = tp->op_params->ref_dec_op; + struct test_buffers *bufs = NULL; + int i, j, ret; + struct rte_bbdev_info info; + uint16_t num_to_enq; + + TEST_ASSERT_SUCCESS((burst_sz > MAX_BURST), + "BURST_SIZE should be <= %u", MAX_BURST); + + rte_bbdev_info_get(tp->dev_id, &info); + + TEST_ASSERT_SUCCESS((num_ops > info.drv.queue_size_lim), + "NUM_OPS cannot exceed %u for this device", + info.drv.queue_size_lim); + + bufs = &tp->op_params->q_bufs[GET_SOCKET(info.socket_id)][queue_id]; + + rte_wait_until_equal_16(&tp->op_params->sync, SYNC_START, __ATOMIC_RELAXED); + + ret = rte_bbdev_dec_op_alloc_bulk(tp->op_params->mp, ops_enq, num_ops); + TEST_ASSERT_SUCCESS(ret, "Allocation failed for %d ops", num_ops); + + /* For BLER tests we need to enable early termination */ + if (!check_bit(ref_op->turbo_dec.op_flags, + RTE_BBDEV_TURBO_EARLY_TERMINATION)) + ref_op->turbo_dec.op_flags += + RTE_BBDEV_TURBO_EARLY_TERMINATION; + ref_op->turbo_dec.iter_max = get_iter_max(); + ref_op->turbo_dec.iter_count = ref_op->turbo_dec.iter_max; + + if (test_vector.op_type != RTE_BBDEV_OP_NONE) + copy_reference_dec_op(ops_enq, num_ops, 0, bufs->inputs, + bufs->hard_outputs, bufs->soft_outputs, + ref_op); + generate_turbo_llr_input(num_ops, bufs->inputs, ref_op); + + /* Set counter to validate the ordering */ + for (j = 0; j < num_ops; ++j) + ops_enq[j]->opaque_data = (void *)(uintptr_t)j; + + for (i = 0; i < 1; ++i) { /* Could add more iterations */ + for (j = 0; j < num_ops; ++j) { + mbuf_reset( + ops_enq[j]->turbo_dec.hard_output.data); + } + + start_time = rte_rdtsc_precise(); + + for (enq = 0, deq = 0; enq < num_ops;) { + num_to_enq = burst_sz; + + if (unlikely(num_ops - enq < num_to_enq)) + num_to_enq = num_ops - enq; + + enq += rte_bbdev_enqueue_dec_ops(tp->dev_id, + queue_id, &ops_enq[enq], num_to_enq); + + deq += rte_bbdev_dequeue_dec_ops(tp->dev_id, + queue_id, &ops_deq[deq], enq - deq); + } + + /* dequeue the remaining */ + while (deq < enq) { + deq += rte_bbdev_dequeue_dec_ops(tp->dev_id, + queue_id, &ops_deq[deq], enq - deq); + } + + total_time += rte_rdtsc_precise() - start_time; + } + + tp->iter_count = 0; + tp->iter_average = 0; + /* get the max of iter_count for all dequeued ops */ + for (i = 0; i < num_ops; ++i) { + tp->iter_count = RTE_MAX(ops_enq[i]->turbo_dec.iter_count, + tp->iter_count); + tp->iter_average += (double) ops_enq[i]->turbo_dec.iter_count; + } + + tp->iter_average /= num_ops; + tp->bler = (double) validate_turbo_bler(ops_deq, num_ops) / num_ops; + + rte_bbdev_dec_op_free_bulk(ops_enq, num_ops); + + double tb_len_bits = calc_dec_TB_size(ref_op); + tp->ops_per_sec = ((double)num_ops * 1) / + ((double)total_time / (double)rte_get_tsc_hz()); + tp->mbps = (((double)(num_ops * 1 * tb_len_bits)) / + 1000000.0) / ((double)total_time / + (double)rte_get_tsc_hz()); + printf("TBS %.0f Time %.0f\n", tb_len_bits, 1000000.0 * + ((double)total_time / (double)rte_get_tsc_hz())); + + return TEST_SUCCESS; +} + static int throughput_pmd_lcore_ldpc_dec(void *arg) { @@ -4195,7 +4372,7 @@ print_dec_bler(struct thread_params *t_params, unsigned int used_cores) total_bler /= used_cores; total_iter /= used_cores; - printf("SNR %.2f BLER %.1f %% - Iterations %.1f %d - Tp %.1f Mbps %s\n", + printf("SNR %.2f BLER %.1f %% - Iterations %.1f %d - Tp %.3f Mbps %s\n", snr, total_bler * 100, total_iter, get_iter_max(), total_mbps, get_vector_filename()); } @@ -4247,6 +4424,10 @@ bler_test(struct active_device *ad, && !check_bit(test_vector.ldpc_dec.op_flags, RTE_BBDEV_LDPC_LLR_COMPRESSION)) bler_function = bler_pmd_lcore_ldpc_dec; + else if ((test_vector.op_type == RTE_BBDEV_OP_TURBO_DEC) && + !check_bit(test_vector.turbo_dec.op_flags, + RTE_BBDEV_TURBO_SOFT_OUTPUT)) + bler_function = bler_pmd_lcore_turbo_dec; else return TEST_SKIPPED;