All of lore.kernel.org
 help / color / mirror / Atom feed
From: <eagostini@nvidia.com>
To: <dev@dpdk.org>
Cc: Elena Agostini <eagostini@nvidia.com>
Subject: [PATCH v2 2/3] app/test-gpudev: test aligned memory allocation
Date: Sat, 8 Jan 2022 00:20:02 +0000	[thread overview]
Message-ID: <20220108002003.21153-2-eagostini@nvidia.com> (raw)
In-Reply-To: <20220108002003.21153-1-eagostini@nvidia.com>

From: Elena Agostini <eagostini@nvidia.com>

Update gpudev app to test GPU memory aligned allocation.

Signed-off-by: Elena Agostini <eagostini@nvidia.com>
---
 app/test-gpudev/main.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/app/test-gpudev/main.c b/app/test-gpudev/main.c
index 5c1aa3d52f..f36f46cbca 100644
--- a/app/test-gpudev/main.c
+++ b/app/test-gpudev/main.c
@@ -69,11 +69,12 @@ alloc_gpu_memory(uint16_t gpu_id)
 	void *ptr_2 = NULL;
 	size_t buf_bytes = 1024;
 	int ret;
+	unsigned align = 4096;
 
 	printf("\n=======> TEST: Allocate GPU memory\n\n");
 
-	/* Alloc memory on GPU 0 */
-	ptr_1 = rte_gpu_mem_alloc(gpu_id, buf_bytes);
+	/* Alloc memory on GPU 0 without any specific alignment */
+	ptr_1 = rte_gpu_mem_alloc(gpu_id, buf_bytes, 0);
 	if (ptr_1 == NULL) {
 		fprintf(stderr, "rte_gpu_mem_alloc GPU memory returned error\n");
 		goto error;
@@ -81,7 +82,8 @@ alloc_gpu_memory(uint16_t gpu_id)
 	printf("GPU memory allocated at 0x%p size is %zd bytes\n",
 			ptr_1, buf_bytes);
 
-	ptr_2 = rte_gpu_mem_alloc(gpu_id, buf_bytes);
+	/* Alloc memory on GPU 0 with 4kB alignment */
+	ptr_2 = rte_gpu_mem_alloc(gpu_id, buf_bytes, align);
 	if (ptr_2 == NULL) {
 		fprintf(stderr, "rte_gpu_mem_alloc GPU memory returned error\n");
 		goto error;
@@ -89,6 +91,11 @@ alloc_gpu_memory(uint16_t gpu_id)
 	printf("GPU memory allocated at 0x%p size is %zd bytes\n",
 			ptr_2, buf_bytes);
 
+	if (((uintptr_t)ptr_2) % align) {
+		fprintf(stderr, "Memory address 0x%p is not aligned to %u\n", ptr_2, align);
+		goto error;
+	}
+
 	ret = rte_gpu_mem_free(gpu_id, (uint8_t *)(ptr_1)+0x700);
 	if (ret < 0) {
 		printf("GPU memory 0x%p NOT freed: GPU driver didn't find this memory address internally.\n",
-- 
2.17.1


  reply	other threads:[~2022-01-07 16:10 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-04  1:47 [PATCH v1 0/3] GPU memory aligned eagostini
2022-01-04  1:47 ` [PATCH v1 1/3] gpudev: mem alloc aligned memory eagostini
2022-01-04  1:47 ` [PATCH v1 2/3] app/test-gpudev: test aligned memory allocation eagostini
2022-01-04  1:47 ` [PATCH v1 3/3] gpu/cuda: mem alloc aligned memory eagostini
2022-01-03 18:05   ` Stephen Hemminger
2022-01-03 18:15     ` Elena Agostini
2022-01-03 18:17       ` Stephen Hemminger
2022-01-03 18:22         ` Elena Agostini
2022-01-08  0:20 ` [PATCH v2 1/3] gpudev: " eagostini
2022-01-08  0:20   ` eagostini [this message]
2022-01-08  0:20   ` [PATCH v2 3/3] gpu/cuda: " eagostini
2022-01-21 10:34   ` [PATCH v2 1/3] gpudev: " Thomas Monjalon

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220108002003.21153-2-eagostini@nvidia.com \
    --to=eagostini@nvidia.com \
    --cc=dev@dpdk.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.