<html> <head> <meta http-equiv="Content-Type" content="text/html; charset=utf-8"> </head> <body text="#000000" bgcolor="#FFFFFF"> <div class="moz-cite-prefix">On 12/7/2017 1:32 AM, Lionel Landwerlin wrote: </div> <blockquote type="cite" cite="mid:314be081-8216-9410-aefd-605d80beaf44@intel.com">I've put together some trival IGT tests : <a class="moz-txt-link-freetext" href="https://github.com/djdeath/intel-gpu-tools/commits/wip/djdeath/cpu-timestamps">https://github.com/djdeath/intel-gpu-tools/commits/wip/djdeath/cpu-timestamps</a> With a few changes which I pointed in the review : <a class="moz-txt-link-freetext" href="https://github.com/djdeath/linux/commit/d0e4cf4d3f464491b4ffe97d112284d1ce73656d">https://github.com/djdeath/linux/commit/d0e4cf4d3f464491b4ffe97d112284d1ce73656d</a> Put together it seems to work relatively well. There is still a small drift happening between the 2 timestamps. I've noticed over a 160ms of OA reports, there is a accumulated difference of ~35us between the GPU timestamp and cpu timestamps. I may be doing something wrong with the scaling in the tests, or maybe there is an issue in the kernel, or both. </blockquote> Went through the testcase. scaled_gpu_delta calculation is same as what timecounter does in kernel for calculating system_time corresponding to gpu timestamp hence we don't see much of delta between these two times/time deltas. Ideally we should be testing the system time delta by sampling system time and gpu timestamp atomically (which isn't feasible unless we do some precise adjustments) I have attempted to check these two times/delta by sampling them in debugfs and reading over variable periods manually and checking the delta. <a class="moz-txt-link-freetext" href="https://github.com/sakamble/i915-timestamp-support/commit/03be3056752d7b05a02cd01f5c20b3fcfcf18395">https://github.com/sakamble/i915-timestamp-support/commit/03be3056752d7b05a02cd01f5c20b3fcfcf18395</a> It is showing that delta is less than 10us in most cases for 30min and occasionally around 20-30us. Again this delta might be because of initial time setting as well. timecounter initializing system time and gpu clocks as pair should be highly accurate for which I have currently taken 350us start offset. I think gpu timestamp clock is highly stable as seen in my testing on SKL. I think this clock is used for calculations in GuC too so will be good to get confirmation about the stability of this clock from them and HW team. <address> systemd-udevd-169 [001] .... 3.035812: i915_driver_load: sys start time: 1512308011156099790</address> <address> systemd-udevd-169 [001] d... 3.036012: i915_cyclecounter_read: 52025098974</address> <address> cat-1654 [001] .... 52.407957: i915_cyclecounter_read: 52617562292</address> <address> cat-1654 [001] .... 52.407958: i915_timestamp_info: sys time: 1512308060527894638</address> <address> cat-1654 [001] .... 52.407958: i915_timestamp_info: ts: 52617562292 device time: 1512308060528043050</address> <address> cat-1684 [001] .... 177.239733: i915_cyclecounter_read: 54115543581</address> <address> cat-1684 [001] .... 177.239736: i915_timestamp_info: sys time: 1512308185359666602</address> <address> cat-1684 [001] .... 177.239737: i915_timestamp_info: ts: 54115543581 device time: 1512308185359817372</address> <address> cat-1693 [001] .... 329.820374: i915_cyclecounter_read: 55946511277</address> <address> cat-1693 [001] .... 329.820377: i915_timestamp_info: sys time: 1512308337940301732</address> <address> cat-1693 [001] .... 329.820378: i915_timestamp_info: ts: 55946511277 device time: 1512308337940458996</address> <address> <delta between system time delta and gpu time delta for above two samples (177, 329) = 6494ns></address> <address> cat-1702 [001] .... 506.980313: i915_cyclecounter_read: 58072430542</address> <address> cat-1702 [001] .... 506.980315: i915_timestamp_info: sys time: 1512308515100233102</address> <address> cat-1702 [001] .... 506.980317: i915_timestamp_info: ts: 58072430542 device time: 1512308515100398084</address> <address> </address> <address><delta between system time delta and gpu time delta for above two samples (329, 506) = 6494ns></address> <blockquote type="cite" cite="mid:314be081-8216-9410-aefd-605d80beaf44@intel.com"> I'll build the GPUTop parts and see if the results make sense. Thanks!, - Lionel On 15/11/17 12:13, Sagar Arun Kamble wrote: <blockquote type="cite">We can compute system time corresponding to GPU timestamp by taking a reference point (CPU monotonic time, GPU timestamp) and then adding delta time computed using timecounter/cyclecounter support in kernel. We have to configure cyclecounter with the GPU timestamp frequency. Earlier approach that was based on cross-timestamp is not needed. It was being used to approximate the frequency based on invalid assumptions (possibly drift was being seen in the time due to precision issue). The precision of time from GPU clocks is already in ns and timecounter takes care of it as verified over variable durations. This series adds base timecounter/cyclecounter changes and changes to get GPU and CPU timestamps in OA samples. Sagar Arun Kamble (1): drm/i915/perf: Add support to correlate GPU timestamp with system time Sourab Gupta (3): drm/i915/perf: Add support for collecting 64 bit timestamps with OA reports drm/i915/perf: Extract raw GPU timestamps from OA reports drm/i915/perf: Send system clock monotonic time in perf samples drivers/gpu/drm/i915/i915_drv.h | 11 ++++ drivers/gpu/drm/i915/i915_perf.c | 124 ++++++++++++++++++++++++++++++++++++++- drivers/gpu/drm/i915/i915_reg.h | 6 ++ include/uapi/drm/i915_drm.h | 14 +++++ 4 files changed, 154 insertions(+), 1 deletion(-) </blockquote> </blockquote> </body> </html>