* [dpdk-dev] [PATCH v4 1/7] app/bbdev: add explicit ut for latency vs validation
2020-10-23 23:33 [dpdk-dev] [PATCH v4 0/7] BBDEV test updates Nicolas Chautru
@ 2020-10-23 23:33 ` Nicolas Chautru
2020-10-23 23:33 ` [dpdk-dev] [PATCH v4 2/7] app/bbdev: add explicit check for counters Nicolas Chautru
` (5 subsequent siblings)
6 siblings, 0 replies; 8+ messages in thread
From: Nicolas Chautru @ 2020-10-23 23:33 UTC (permalink / raw)
To: dev, akhil.goyal, trix; +Cc: david.marchand, Nicolas Chautru
Adding explicit different ut when testing for validation
or latency (early termination enabled or not).
Signed-off-by: Nicolas Chautru <nicolas.chautru@intel.com>
Acked-by: Aidan Goddard <aidan.goddard@accelercomm.com>
Acked-by: Dave Burley <dave.burley@accelercomm.com>
---
app/test-bbdev/test_bbdev_perf.c | 92 ++++++++++++++++++++++++++++++++++++++--
1 file changed, 88 insertions(+), 4 deletions(-)
diff --git a/app/test-bbdev/test_bbdev_perf.c b/app/test-bbdev/test_bbdev_perf.c
index 6e5535d..3554a77 100644
--- a/app/test-bbdev/test_bbdev_perf.c
+++ b/app/test-bbdev/test_bbdev_perf.c
@@ -3999,12 +3999,14 @@ typedef int (test_case_function)(struct active_device *ad,
return i;
}
+/* Test case for latency/validation for LDPC Decoder */
static int
latency_test_ldpc_dec(struct rte_mempool *mempool,
struct test_buffers *bufs, struct rte_bbdev_dec_op *ref_op,
int vector_mask, uint16_t dev_id, uint16_t queue_id,
const uint16_t num_to_process, uint16_t burst_sz,
- uint64_t *total_time, uint64_t *min_time, uint64_t *max_time)
+ uint64_t *total_time, uint64_t *min_time, uint64_t *max_time,
+ bool disable_et)
{
int ret = TEST_SUCCESS;
uint16_t i, j, dequeued;
@@ -4026,7 +4028,7 @@ typedef int (test_case_function)(struct active_device *ad,
"rte_bbdev_dec_op_alloc_bulk() failed");
/* For latency tests we need to disable early termination */
- if (check_bit(ref_op->ldpc_dec.op_flags,
+ if (disable_et && check_bit(ref_op->ldpc_dec.op_flags,
RTE_BBDEV_LDPC_ITERATION_STOP_ENABLE))
ref_op->ldpc_dec.op_flags -=
RTE_BBDEV_LDPC_ITERATION_STOP_ENABLE;
@@ -4248,7 +4250,7 @@ typedef int (test_case_function)(struct active_device *ad,
TEST_ASSERT_NOT_NULL(op_type_str, "Invalid op type: %u", op_type);
printf("+ ------------------------------------------------------- +\n");
- printf("== test: validation/latency\ndev: %s, burst size: %u, num ops: %u, op type: %s\n",
+ printf("== test: latency\ndev: %s, burst size: %u, num ops: %u, op type: %s\n",
info.dev_name, burst_sz, num_to_process, op_type_str);
if (op_type == RTE_BBDEV_OP_TURBO_DEC)
@@ -4270,7 +4272,83 @@ typedef int (test_case_function)(struct active_device *ad,
iter = latency_test_ldpc_dec(op_params->mp, bufs,
op_params->ref_dec_op, op_params->vector_mask,
ad->dev_id, queue_id, num_to_process,
+ burst_sz, &total_time, &min_time, &max_time,
+ true);
+ else
+ iter = latency_test_enc(op_params->mp, bufs,
+ op_params->ref_enc_op,
+ ad->dev_id, queue_id,
+ num_to_process, burst_sz, &total_time,
+ &min_time, &max_time);
+
+ if (iter <= 0)
+ return TEST_FAILED;
+
+ printf("Operation latency:\n"
+ "\tavg: %lg cycles, %lg us\n"
+ "\tmin: %lg cycles, %lg us\n"
+ "\tmax: %lg cycles, %lg us\n",
+ (double)total_time / (double)iter,
+ (double)(total_time * 1000000) / (double)iter /
+ (double)rte_get_tsc_hz(), (double)min_time,
+ (double)(min_time * 1000000) / (double)rte_get_tsc_hz(),
+ (double)max_time, (double)(max_time * 1000000) /
+ (double)rte_get_tsc_hz());
+
+ return TEST_SUCCESS;
+}
+
+static int
+validation_test(struct active_device *ad,
+ struct test_op_params *op_params)
+{
+ int iter;
+ uint16_t burst_sz = op_params->burst_sz;
+ const uint16_t num_to_process = op_params->num_to_process;
+ const enum rte_bbdev_op_type op_type = test_vector.op_type;
+ const uint16_t queue_id = ad->queue_ids[0];
+ struct test_buffers *bufs = NULL;
+ struct rte_bbdev_info info;
+ uint64_t total_time, min_time, max_time;
+ const char *op_type_str;
+
+ total_time = max_time = 0;
+ min_time = UINT64_MAX;
+
+ TEST_ASSERT_SUCCESS((burst_sz > MAX_BURST),
+ "BURST_SIZE should be <= %u", MAX_BURST);
+
+ rte_bbdev_info_get(ad->dev_id, &info);
+ bufs = &op_params->q_bufs[GET_SOCKET(info.socket_id)][queue_id];
+
+ op_type_str = rte_bbdev_op_type_str(op_type);
+ TEST_ASSERT_NOT_NULL(op_type_str, "Invalid op type: %u", op_type);
+
+ printf("+ ------------------------------------------------------- +\n");
+ printf("== test: validation\ndev: %s, burst size: %u, num ops: %u, op type: %s\n",
+ info.dev_name, burst_sz, num_to_process, op_type_str);
+
+ if (op_type == RTE_BBDEV_OP_TURBO_DEC)
+ iter = latency_test_dec(op_params->mp, bufs,
+ op_params->ref_dec_op, op_params->vector_mask,
+ ad->dev_id, queue_id, num_to_process,
burst_sz, &total_time, &min_time, &max_time);
+ else if (op_type == RTE_BBDEV_OP_TURBO_ENC)
+ iter = latency_test_enc(op_params->mp, bufs,
+ op_params->ref_enc_op, ad->dev_id, queue_id,
+ num_to_process, burst_sz, &total_time,
+ &min_time, &max_time);
+ else if (op_type == RTE_BBDEV_OP_LDPC_ENC)
+ iter = latency_test_ldpc_enc(op_params->mp, bufs,
+ op_params->ref_enc_op, ad->dev_id, queue_id,
+ num_to_process, burst_sz, &total_time,
+ &min_time, &max_time);
+ else if (op_type == RTE_BBDEV_OP_LDPC_DEC)
+ iter = latency_test_ldpc_dec(op_params->mp, bufs,
+ op_params->ref_dec_op, op_params->vector_mask,
+ ad->dev_id, queue_id, num_to_process,
+ burst_sz, &total_time, &min_time, &max_time,
+ false);
else
iter = latency_test_enc(op_params->mp, bufs,
op_params->ref_enc_op,
@@ -4930,6 +5008,12 @@ typedef int (test_case_function)(struct active_device *ad,
}
static int
+validation_tc(void)
+{
+ return run_test_case(validation_test);
+}
+
+static int
interrupt_tc(void)
{
return run_test_case(throughput_test);
@@ -4960,7 +5044,7 @@ typedef int (test_case_function)(struct active_device *ad,
.setup = testsuite_setup,
.teardown = testsuite_teardown,
.unit_test_cases = {
- TEST_CASE_ST(ut_setup, ut_teardown, latency_tc),
+ TEST_CASE_ST(ut_setup, ut_teardown, validation_tc),
TEST_CASES_END() /**< NULL terminate unit test array */
}
};
--
1.8.3.1
^ permalink raw reply [flat|nested] 8+ messages in thread* [dpdk-dev] [PATCH v4 3/7] app/bbdev: include explict HARQ preloading
2020-10-23 23:33 [dpdk-dev] [PATCH v4 0/7] BBDEV test updates Nicolas Chautru
2020-10-23 23:33 ` [dpdk-dev] [PATCH v4 1/7] app/bbdev: add explicit ut for latency vs validation Nicolas Chautru
2020-10-23 23:33 ` [dpdk-dev] [PATCH v4 2/7] app/bbdev: add explicit check for counters Nicolas Chautru
@ 2020-10-23 23:33 ` Nicolas Chautru
2020-10-23 23:33 ` [dpdk-dev] [PATCH v4 4/7] app/bbdev: define wait for offload Nicolas Chautru
` (3 subsequent siblings)
6 siblings, 0 replies; 8+ messages in thread
From: Nicolas Chautru @ 2020-10-23 23:33 UTC (permalink / raw)
To: dev, akhil.goyal, trix; +Cc: david.marchand, Nicolas Chautru
Run preloading explictly for unit tests. Load each code block
by reusing existing input op then restore for the actual test.
Signed-off-by: Nicolas Chautru <nicolas.chautru@intel.com>
Acked-by: Liu Tianjiao <tianjiao.liu@intel.com>
---
app/test-bbdev/main.h | 1 +
app/test-bbdev/test_bbdev_perf.c | 51 +++++++++++++++++++++-------------------
2 files changed, 28 insertions(+), 24 deletions(-)
diff --git a/app/test-bbdev/main.h b/app/test-bbdev/main.h
index fb3dec8..dc10a50 100644
--- a/app/test-bbdev/main.h
+++ b/app/test-bbdev/main.h
@@ -17,6 +17,7 @@
#define TEST_SKIPPED 1
#define MAX_BURST 512U
+#define MAX_OPS 1024U
#define DEFAULT_BURST 32U
#define DEFAULT_OPS 64U
#define DEFAULT_ITER 6U
diff --git a/app/test-bbdev/test_bbdev_perf.c b/app/test-bbdev/test_bbdev_perf.c
index b62848e..f30cbdb 100644
--- a/app/test-bbdev/test_bbdev_perf.c
+++ b/app/test-bbdev/test_bbdev_perf.c
@@ -2513,20 +2513,20 @@ typedef int (test_case_function)(struct active_device *ad,
bool preload)
{
uint16_t j;
- int ret;
- uint32_t harq_offset = (uint32_t) queue_id * HARQ_INCR * 1024;
- struct rte_bbdev_op_data save_hc_in, save_hc_out;
- struct rte_bbdev_dec_op *ops_deq[MAX_BURST];
+ int deq;
+ uint32_t harq_offset = (uint32_t) queue_id * HARQ_INCR * MAX_OPS;
+ struct rte_bbdev_op_data save_hc_in[MAX_OPS], save_hc_out[MAX_OPS];
+ struct rte_bbdev_dec_op *ops_deq[MAX_OPS];
uint32_t flags = ops[0]->ldpc_dec.op_flags;
bool mem_in = flags & RTE_BBDEV_LDPC_INTERNAL_HARQ_MEMORY_IN_ENABLE;
bool hc_in = flags & RTE_BBDEV_LDPC_HQ_COMBINE_IN_ENABLE;
bool mem_out = flags & RTE_BBDEV_LDPC_INTERNAL_HARQ_MEMORY_OUT_ENABLE;
bool hc_out = flags & RTE_BBDEV_LDPC_HQ_COMBINE_OUT_ENABLE;
bool h_comp = flags & RTE_BBDEV_LDPC_HARQ_6BIT_COMPRESSION;
- for (j = 0; j < n; ++j) {
- if ((mem_in || hc_in) && preload) {
- save_hc_in = ops[j]->ldpc_dec.harq_combined_input;
- save_hc_out = ops[j]->ldpc_dec.harq_combined_output;
+ if ((mem_in || hc_in) && preload) {
+ for (j = 0; j < n; ++j) {
+ save_hc_in[j] = ops[j]->ldpc_dec.harq_combined_input;
+ save_hc_out[j] = ops[j]->ldpc_dec.harq_combined_output;
ops[j]->ldpc_dec.op_flags =
RTE_BBDEV_LDPC_INTERNAL_HARQ_MEMORY_LOOPBACK +
RTE_BBDEV_LDPC_INTERNAL_HARQ_MEMORY_OUT_ENABLE;
@@ -2536,16 +2536,23 @@ typedef int (test_case_function)(struct active_device *ad,
ops[j]->ldpc_dec.harq_combined_output.offset =
harq_offset;
ops[j]->ldpc_dec.harq_combined_input.offset = 0;
- rte_bbdev_enqueue_ldpc_dec_ops(dev_id, queue_id,
- &ops[j], 1);
- ret = 0;
- while (ret == 0)
- ret = rte_bbdev_dequeue_ldpc_dec_ops(
- dev_id, queue_id, &ops_deq[j], 1);
+ harq_offset += HARQ_INCR;
+ }
+ rte_bbdev_enqueue_ldpc_dec_ops(dev_id, queue_id, &ops[0], n);
+ deq = 0;
+ while (deq != n)
+ deq += rte_bbdev_dequeue_ldpc_dec_ops(
+ dev_id, queue_id, &ops_deq[deq],
+ n - deq);
+ /* Restore the operations */
+ for (j = 0; j < n; ++j) {
ops[j]->ldpc_dec.op_flags = flags;
- ops[j]->ldpc_dec.harq_combined_input = save_hc_in;
- ops[j]->ldpc_dec.harq_combined_output = save_hc_out;
+ ops[j]->ldpc_dec.harq_combined_input = save_hc_in[j];
+ ops[j]->ldpc_dec.harq_combined_output = save_hc_out[j];
}
+ }
+ harq_offset = (uint32_t) queue_id * HARQ_INCR * MAX_OPS;
+ for (j = 0; j < n; ++j) {
/* Adjust HARQ offset when we reach external DDR */
if (mem_in || hc_in)
ops[j]->ldpc_dec.harq_combined_input.offset
@@ -3231,11 +3238,9 @@ typedef int (test_case_function)(struct active_device *ad,
mbuf_reset(
ops_enq[j]->ldpc_dec.harq_combined_output.data);
}
- if (extDdr) {
- bool preload = i == (TEST_REPETITIONS - 1);
+ if (extDdr)
preload_harq_ddr(tp->dev_id, queue_id, ops_enq,
- num_ops, preload);
- }
+ num_ops, true);
start_time = rte_rdtsc_precise();
for (enq = 0, deq = 0; enq < num_ops;) {
@@ -3362,11 +3367,9 @@ typedef int (test_case_function)(struct active_device *ad,
mbuf_reset(
ops_enq[j]->ldpc_dec.harq_combined_output.data);
}
- if (extDdr) {
- bool preload = i == (TEST_REPETITIONS - 1);
+ if (extDdr)
preload_harq_ddr(tp->dev_id, queue_id, ops_enq,
- num_ops, preload);
- }
+ num_ops, true);
start_time = rte_rdtsc_precise();
for (enq = 0, deq = 0; enq < num_ops;) {
--
1.8.3.1
^ permalink raw reply [flat|nested] 8+ messages in thread* [dpdk-dev] [PATCH v4 7/7] app/bbdev: update offload test to dequeue full ring
2020-10-23 23:33 [dpdk-dev] [PATCH v4 0/7] BBDEV test updates Nicolas Chautru
` (5 preceding siblings ...)
2020-10-23 23:33 ` [dpdk-dev] [PATCH v4 6/7] app/bbdev: reduce duration of throughput test Nicolas Chautru
@ 2020-10-23 23:33 ` Nicolas Chautru
6 siblings, 0 replies; 8+ messages in thread
From: Nicolas Chautru @ 2020-10-23 23:33 UTC (permalink / raw)
To: dev, akhil.goyal, trix; +Cc: david.marchand, Nicolas Chautru
update offload dequeue to retrieve the full ring to be
agnostic of implementation.
Signed-off-by: Nicolas Chautru <nicolas.chautru@intel.com>
Acked-by: Aidan Goddard <aidan.goddard@accelercomm.com>
Acked-by: Dave Burley <dave.burley@accelercomm.com>
---
app/test-bbdev/test_bbdev_perf.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/app/test-bbdev/test_bbdev_perf.c b/app/test-bbdev/test_bbdev_perf.c
index b5dc536..a6884c5 100644
--- a/app/test-bbdev/test_bbdev_perf.c
+++ b/app/test-bbdev/test_bbdev_perf.c
@@ -4463,8 +4463,8 @@ typedef int (test_case_function)(struct active_device *ad,
/* Dequeue one operation */
do {
deq += rte_bbdev_dequeue_dec_ops(dev_id, queue_id,
- &ops_deq[deq], 1);
- } while (unlikely(deq != 1));
+ &ops_deq[deq], enq);
+ } while (unlikely(deq == 0));
deq_last_time = rte_rdtsc_precise() - deq_start_time;
time_st->deq_max_time = RTE_MAX(time_st->deq_max_time,
@@ -4554,8 +4554,8 @@ typedef int (test_case_function)(struct active_device *ad,
/* Dequeue one operation */
do {
deq += rte_bbdev_dequeue_ldpc_dec_ops(dev_id, queue_id,
- &ops_deq[deq], 1);
- } while (unlikely(deq != 1));
+ &ops_deq[deq], enq);
+ } while (unlikely(deq == 0));
deq_last_time = rte_rdtsc_precise() - deq_start_time;
time_st->deq_max_time = RTE_MAX(time_st->deq_max_time,
@@ -4642,8 +4642,8 @@ typedef int (test_case_function)(struct active_device *ad,
/* Dequeue one operation */
do {
deq += rte_bbdev_dequeue_enc_ops(dev_id, queue_id,
- &ops_deq[deq], 1);
- } while (unlikely(deq != 1));
+ &ops_deq[deq], enq);
+ } while (unlikely(deq == 0));
deq_last_time = rte_rdtsc_precise() - deq_start_time;
time_st->deq_max_time = RTE_MAX(time_st->deq_max_time,
@@ -4725,8 +4725,8 @@ typedef int (test_case_function)(struct active_device *ad,
/* Dequeue one operation */
do {
deq += rte_bbdev_dequeue_ldpc_enc_ops(dev_id, queue_id,
- &ops_deq[deq], 1);
- } while (unlikely(deq != 1));
+ &ops_deq[deq], enq);
+ } while (unlikely(deq == 0));
deq_last_time = rte_rdtsc_precise() - deq_start_time;
time_st->deq_max_time = RTE_MAX(time_st->deq_max_time,
--
1.8.3.1
^ permalink raw reply [flat|nested] 8+ messages in thread