[UR] fix: synchronize resubmission of the same command buffer #18566

EuphoricThinking · 2025-05-20T12:54:13Z

unified-runtime/source/adapters/level_zero/v2/command_list_manager.cpp

Xewar313 · 2025-05-20T13:20:37Z

unified-runtime/test/conformance/exp_command_buffer/fixtures.h

    ur_exp_command_buffer_desc_t desc{UR_STRUCTURE_TYPE_EXP_COMMAND_BUFFER_DESC,
-                                      nullptr, false, false, false};
+                                      nullptr, false, true /* WAS: false */, false};


Why change the buffer to in order?

In order to extend the time of the buffer execution, but as @pbalcer mentioned, I'll revert this to out-of-order

Xewar313 · 2025-05-20T13:20:59Z

unified-runtime/test/conformance/exp_command_buffer/fixtures.h

@@ -112,6 +113,7 @@ struct urCommandBufferExpExecutionTest : uur::urKernelExecutionTest {
  }

  ur_exp_command_buffer_handle_t cmd_buf_handle = nullptr;
+  ur_exp_command_buffer_handle_t cmd_buf_in_order = nullptr;


Where is it used?

In the interest of time, and knowing that right now there's no difference between the two, I suggest not adding in order cmd buf here for now, and just testing out of order for now (both should exhibit the issue we are trying to solve).

unified-runtime/test/conformance/exp_command_buffer/enqueue.cpp

pbalcer

lgtm, just a few nits.

unified-runtime/source/adapters/level_zero/v2/queue_immediate_in_order.cpp

pbalcer · 2025-05-29T12:30:19Z

unified-runtime/test/conformance/exp_command_buffer/fixtures.h

@@ -98,7 +98,7 @@ struct urCommandBufferExpExecutionTest : uur::urKernelExecutionTest {
    UUR_RETURN_ON_FATAL_FAILURE(checkCommandBufferSupport(device));

    ur_exp_command_buffer_desc_t desc{UR_STRUCTURE_TYPE_EXP_COMMAND_BUFFER_DESC,
-                                      nullptr, false, false, false};
+                                      nullptr, false, false /* WAS: false */, false};


Suggested change

nullptr, false, false /* WAS: false */, false};

nullptr, false, false, false};

unified-runtime/test/conformance/exp_command_buffer/enqueue.cpp

EwanC

LGTM

EwanC · 2025-05-30T08:13:09Z

unified-runtime/test/conformance/exp_command_buffer/enqueue.cpp


 // Tests that the same command-buffer submitted across different in-order
 // queues has an implicit dependency on first submission
 TEST_P(urEnqueueCommandBufferExpTest, SerializeAcrossQueues) {
  // Execute command-buffer to first in-order queue (created by parent
-  // urQueueTest fixture)
+  // urQueueTestWithParam fixture)
  ASSERT_SUCCESS(
      urEnqueueCommandBufferExp(queue, cmd_buf_handle, 0, nullptr, nullptr));

  // Execute command-buffer to second in-order queue, should have implicit


Suggested change

// Execute command-buffer to second in-order queue, should have implicit

// Execute command-buffer to second queue, should have implicit

unified-runtime/source/adapters/level_zero/v2/queue_immediate_in_order.cpp

unified-runtime/test/conformance/exp_command_buffer/enqueue.cpp

This reverts commit 80a1ff0.

This reverts commit 99389f8.

add new test fixture test serialization of the command buffer execution in an in-order queue

synchronization implemented as the host thread waiting for an event to be signalled after the completion of the command buffer execution

pbalcer · 2025-06-03T13:20:36Z

@intel/llvm-gatekeepers please merge

PR #18566 fixes the DG2 SYCL-Graph E2E tests fails seen on DG2 for the V2 adapter. Re-enable tests and add a new test with a reduced version of `buffer_ordering.cpp` that also exposed the bug. See: * #18668 * #18579

EuphoricThinking temporarily deployed to WindowsCILock May 20, 2025 12:54 — with GitHub Actions Inactive

pbalcer reviewed May 20, 2025

View reviewed changes

unified-runtime/source/adapters/level_zero/v2/command_list_manager.cpp Outdated Show resolved Hide resolved

EuphoricThinking temporarily deployed to WindowsCILock May 20, 2025 13:17 — with GitHub Actions Inactive

Xewar313 reviewed May 20, 2025

View reviewed changes

pbalcer mentioned this pull request May 22, 2025

[UR][L0 v2] urEnqueueCommandBufferExpTest.SerializeAcrossQueues flaky on PVC #18610

Closed

EwanC reviewed May 22, 2025

View reviewed changes

unified-runtime/test/conformance/exp_command_buffer/enqueue.cpp Outdated Show resolved Hide resolved

pbalcer reviewed May 22, 2025

View reviewed changes

unified-runtime/test/conformance/exp_command_buffer/enqueue.cpp Outdated Show resolved Hide resolved

EuphoricThinking force-pushed the serialize_cmdbuff_pr branch from 0cc9c9e to f9c9545 Compare May 29, 2025 12:13

EuphoricThinking had a problem deploying to WindowsCILock May 29, 2025 12:13 — with GitHub Actions Error

EuphoricThinking force-pushed the serialize_cmdbuff_pr branch from f9c9545 to d7bff7e Compare May 29, 2025 12:16

EuphoricThinking had a problem deploying to WindowsCILock May 29, 2025 12:16 — with GitHub Actions Error

EuphoricThinking force-pushed the serialize_cmdbuff_pr branch from d7bff7e to b4f49fd Compare May 29, 2025 12:33

EuphoricThinking had a problem deploying to WindowsCILock May 29, 2025 12:34 — with GitHub Actions Error

pbalcer approved these changes May 29, 2025

View reviewed changes

EuphoricThinking force-pushed the serialize_cmdbuff_pr branch from b4f49fd to 277615b Compare May 29, 2025 12:37

EuphoricThinking had a problem deploying to WindowsCILock May 29, 2025 12:38 — with GitHub Actions Error

EuphoricThinking force-pushed the serialize_cmdbuff_pr branch from 277615b to 0752cac Compare May 29, 2025 12:48

EuphoricThinking had a problem deploying to WindowsCILock May 29, 2025 12:49 — with GitHub Actions Error

EuphoricThinking marked this pull request as ready for review May 29, 2025 12:51

EuphoricThinking requested review from a team as code owners May 29, 2025 12:51

EuphoricThinking requested a review from fabiomestre May 29, 2025 12:51

EuphoricThinking force-pushed the serialize_cmdbuff_pr branch from 0752cac to e2b3ff4 Compare May 29, 2025 13:01

EuphoricThinking temporarily deployed to WindowsCILock May 29, 2025 13:02 — with GitHub Actions Inactive

EuphoricThinking temporarily deployed to WindowsCILock May 29, 2025 13:21 — with GitHub Actions Inactive

pbalcer reviewed May 29, 2025

View reviewed changes

unified-runtime/test/conformance/exp_command_buffer/enqueue.cpp Outdated Show resolved Hide resolved

EwanC reviewed May 29, 2025

View reviewed changes

EuphoricThinking force-pushed the serialize_cmdbuff_pr branch from e2b3ff4 to 2aac6c4 Compare May 30, 2025 01:33

EuphoricThinking had a problem deploying to WindowsCILock May 30, 2025 01:34 — with GitHub Actions Error

EuphoricThinking force-pushed the serialize_cmdbuff_pr branch from 2aac6c4 to cb047e5 Compare May 30, 2025 01:42

EuphoricThinking had a problem deploying to WindowsCILock May 30, 2025 01:43 — with GitHub Actions Error

EuphoricThinking force-pushed the serialize_cmdbuff_pr branch from cb047e5 to 49dfd0a Compare May 30, 2025 01:55

EuphoricThinking had a problem deploying to WindowsCILock May 30, 2025 01:56 — with GitHub Actions Error

EuphoricThinking force-pushed the serialize_cmdbuff_pr branch from 49dfd0a to 232146b Compare May 30, 2025 02:14

EuphoricThinking temporarily deployed to WindowsCILock May 30, 2025 02:15 — with GitHub Actions Inactive

EuphoricThinking temporarily deployed to WindowsCILock May 30, 2025 02:38 — with GitHub Actions Inactive

EwanC approved these changes May 30, 2025

View reviewed changes

pbalcer approved these changes May 30, 2025

View reviewed changes

pbalcer requested changes May 30, 2025

View reviewed changes

unified-runtime/source/adapters/level_zero/v2/queue_immediate_in_order.cpp Outdated Show resolved Hide resolved

unified-runtime/test/conformance/exp_command_buffer/enqueue.cpp Show resolved Hide resolved

aelovikov-intel changed the title ~~fix: synchronize resubmission of the same command buffer~~ [UR] fix: synchronize resubmission of the same command buffer May 30, 2025

EwanC mentioned this pull request Jun 2, 2025

[SYCL][Graph][L0 v2] Re-enable DG2 E2E tests #18754

Merged

EuphoricThinking force-pushed the serialize_cmdbuff_pr branch from 232146b to ae27d66 Compare June 3, 2025 11:43

EuphoricThinking temporarily deployed to WindowsCILock June 3, 2025 11:43 — with GitHub Actions Inactive

pbalcer approved these changes Jun 3, 2025

View reviewed changes

EuphoricThinking temporarily deployed to WindowsCILock June 3, 2025 12:25 — with GitHub Actions Inactive

EuphoricThinking added 4 commits June 3, 2025 12:36

Revert "[UR][Graph] Disable flaky CTS test on L0 v2 (intel#18636)"

a941c51

This reverts commit 80a1ff0.

Revert "[UR][Graph] Disable flaky CTS test on L0 v2 (intel#18611)"

95802f4

This reverts commit 99389f8.

add a test for serialization of command buffers

b5b6500

add new test fixture test serialization of the command buffer execution in an in-order queue

fix: synchronize resubmission of the same command buffer

ae27d66

synchronization implemented as the host thread waiting for an event to be signalled after the completion of the command buffer execution

kbenzie merged commit 29a2502 into intel:sycl Jun 3, 2025
53 of 58 checks passed

This was referenced Jun 6, 2025

[L0 v2] Flaky graph tests failing on Intel Arc A-Series Graphics #18668

Closed

[L0 v2] Graph/RecordReplay/buffer_ordering.cpp and Graph/Explicit/buffer_ordering.cpp failing on DG2 with new driver #18579

Closed

	nullptr, false, false /* WAS: false */, false};
	nullptr, false, false, false};

	// Execute command-buffer to second in-order queue, should have implicit
	// Execute command-buffer to second queue, should have implicit

[UR] fix: synchronize resubmission of the same command buffer #18566

[UR] fix: synchronize resubmission of the same command buffer #18566

Uh oh!

Conversation

EuphoricThinking commented May 20, 2025 • edited by pbalcer Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Xewar313 May 20, 2025

Choose a reason for hiding this comment

Uh oh!

EuphoricThinking May 26, 2025

Choose a reason for hiding this comment

Uh oh!

Xewar313 May 20, 2025

Choose a reason for hiding this comment

Uh oh!

pbalcer May 22, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

pbalcer left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

pbalcer May 29, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

EwanC left a comment

Choose a reason for hiding this comment

Uh oh!

EwanC May 30, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

pbalcer commented Jun 3, 2025

Uh oh!

Uh oh!

Uh oh!

EuphoricThinking commented May 20, 2025 •

edited by pbalcer

Loading

pbalcer May 22, 2025 •

edited

Loading