From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id B908A41D3B; Wed, 22 Feb 2023 11:48:12 +0100 (CET) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 52B1040693; Wed, 22 Feb 2023 11:48:12 +0100 (CET) Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by mails.dpdk.org (Postfix) with ESMTP id B254040689 for ; Wed, 22 Feb 2023 11:48:11 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1677062891; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=amnLfJYZQqVwewAWPTsGFTPzLlHiqvlxYXnUMnQSrzs=; b=KzU0xwHEn3FM519wvDvqWcnYD/hji2ghj+njkjDL0sK0yNAZRrDqB20N5skiQubfxe55lP CmYvgGn6pT41UAZhIsh6j2IkTjfNIkNYH9g/2qsiDoKD/GUC+W2lO/BKGiaI6/Ua+lM0Zz d02sREdJrPNmU/56rVJFHMjQvPh2YdQ= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-98-4Z2Ti26uPhydh7sdOKMktQ-1; Wed, 22 Feb 2023 05:48:07 -0500 X-MC-Unique: 4Z2Ti26uPhydh7sdOKMktQ-1 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id A7FF087B2A4; Wed, 22 Feb 2023 10:48:06 +0000 (UTC) Received: from [10.39.208.21] (unknown [10.39.208.21]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 35AEB492C3C; Wed, 22 Feb 2023 10:48:05 +0000 (UTC) Message-ID: Date: Wed, 22 Feb 2023 11:48:03 +0100 MIME-Version: 1.0 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101 Thunderbird/102.7.1 Subject: Re: [PATCH v2 08/16] test/bbdev: add support for BLER for 4G To: Hernan Vargas , dev@dpdk.org, gakhil@marvell.com, trix@redhat.com Cc: nicolas.chautru@intel.com, qi.z.zhang@intel.com References: <20230215170949.60569-1-hernan.vargas@intel.com> <20230215170949.60569-9-hernan.vargas@intel.com> From: Maxime Coquelin In-Reply-To: <20230215170949.60569-9-hernan.vargas@intel.com> X-Scanned-By: MIMEDefang 3.1 on 10.11.54.9 X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-Language: en-US Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit 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 On 2/15/23 18:09, Hernan Vargas wrote: > 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); Please check my reply on v1. > + } > + > + /* 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; >