diff mbox series

[4/4] dispatcher: use alloca instead of vla multi dimensional

Message ID 1712250913-1977-5-git-send-email-roretzla@linux.microsoft.com (mailing list archive)
State Superseded
Headers
Series RFC samples converting VLA to alloca |

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/loongarch-compilation fail ninja build failure
ci/Intel-compilation success Compilation OK
ci/intel-Testing success Testing PASS
ci/github-robot: build fail github build: failed
ci/intel-Functional success Functional PASS
ci/iol-intel-Performance success Performance Testing PASS
ci/iol-mellanox-Performance success Performance Testing PASS
ci/iol-abi-testing success Testing PASS
ci/iol-unit-arm64-testing fail Testing issues
ci/iol-compile-amd64-testing success Testing PASS
ci/iol-compile-arm64-testing fail Testing issues
ci/iol-unit-amd64-testing success Testing PASS
ci/iol-sample-apps-testing success Testing PASS
ci/iol-broadcom-Functional success Functional Testing PASS
ci/iol-broadcom-Performance success Performance Testing PASS
ci/iol-intel-Functional success Functional Testing PASS

Commit Message

Tyler Retzlaff April 4, 2024, 5:15 p.m. UTC 
  RFC sample illustrating conversion of multi-dimensional VLA to use
alloca().

Signed-off-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
---
 lib/dispatcher/rte_dispatcher.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

Comments

Morten Brørup April 6, 2024, 3:49 p.m. UTC | #1 
> From: Tyler Retzlaff [mailto:roretzla@linux.microsoft.com]
> Sent: Thursday, 4 April 2024 19.15
> 
> RFC sample illustrating conversion of multi-dimensional VLA to use
> alloca().
> 
> Signed-off-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
> ---
>  lib/dispatcher/rte_dispatcher.c | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
> 
> diff --git a/lib/dispatcher/rte_dispatcher.c
> b/lib/dispatcher/rte_dispatcher.c
> index 7934917..f154c26 100644
> --- a/lib/dispatcher/rte_dispatcher.c
> +++ b/lib/dispatcher/rte_dispatcher.c
> @@ -119,7 +119,7 @@ struct rte_dispatcher {
>  	struct rte_event *events, uint16_t num_events)
>  {
>  	int i;
> -	struct rte_event bursts[EVD_MAX_HANDLERS][num_events];
> +	struct rte_event *bursts = alloca(sizeof(struct rte_event) *
> EVD_MAX_HANDLERS * num_events);

This is an interesting example, because keeping the allocated memory tight probably has better cache performance than a max sized multi dimensional array, such as bursts[EVD_MAX_HANDLERS][RTE_MAX_EVENT_BURST_SIZE].

And multiplication on modern CPUs are not much slower than left shifting, as they were on CPUs ages ago.

So this suggested solution for multi dimensional arrays seems preferable.

>  	uint16_t burst_lens[EVD_MAX_HANDLERS] = { 0 };
>  	uint16_t drop_count = 0;
>  	uint16_t dispatch_count;
> @@ -136,7 +136,7 @@ struct rte_dispatcher {
>  			continue;
>  		}
> 
> -		bursts[handler_idx][burst_lens[handler_idx]] = *event;
> +		bursts[handler_idx * num_events + burst_lens[handler_idx]]
> = *event;
>  		burst_lens[handler_idx]++;
>  	}
> 
> @@ -152,7 +152,7 @@ struct rte_dispatcher {
>  			continue;
> 
>  		handler->process_fun(dispatcher->event_dev_id, port-
> >port_id,
> -				     bursts[i], len, handler->process_data);
> +				     &bursts[i * num_events], len, handler-
> >process_data);
> 
>  		dispatched += len;
> 
> --
> 1.8.3.1
diff mbox series

Patch

diff --git a/lib/dispatcher/rte_dispatcher.c b/lib/dispatcher/rte_dispatcher.c
index 7934917..f154c26 100644
--- a/lib/dispatcher/rte_dispatcher.c
+++ b/lib/dispatcher/rte_dispatcher.c
@@ -119,7 +119,7 @@  struct rte_dispatcher {
 	struct rte_event *events, uint16_t num_events)
 {
 	int i;
-	struct rte_event bursts[EVD_MAX_HANDLERS][num_events];
+	struct rte_event *bursts = alloca(sizeof(struct rte_event) * EVD_MAX_HANDLERS * num_events);
 	uint16_t burst_lens[EVD_MAX_HANDLERS] = { 0 };
 	uint16_t drop_count = 0;
 	uint16_t dispatch_count;
@@ -136,7 +136,7 @@  struct rte_dispatcher {
 			continue;
 		}
 
-		bursts[handler_idx][burst_lens[handler_idx]] = *event;
+		bursts[handler_idx * num_events + burst_lens[handler_idx]] = *event;
 		burst_lens[handler_idx]++;
 	}
 
@@ -152,7 +152,7 @@  struct rte_dispatcher {
 			continue;
 
 		handler->process_fun(dispatcher->event_dev_id, port->port_id,
-				     bursts[i], len, handler->process_data);
+				     &bursts[i * num_events], len, handler->process_data);
 
 		dispatched += len;