summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2010-01-06gitignore intel_audio_dump and intel_reg_readZhenyu Wang
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
2010-01-06Add 'intel_reg_read' toolZhenyu Wang
This is a handy tool to just check state of one register, which might not bother to be included in intel_reg_dumper tool. And also take in Ben's original full range register dump with '-f' option. Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
2010-01-05gpu_dump: Parse INSTDONE if seen inside a file.Chris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2010-01-05reg: Include INSTPM in dump.Chris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2010-01-05decode/i965: Show byte lengths for buffers.Chris Wilson
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2009-12-15intel_gpu_top: Fix broken clock reporting.Shuang He
Signed-off-by: Eric Anholt <eric@anholt.net>
2009-12-15Replace dolt and shave with using current autotools.Eric Anholt
2009-12-10Limit printing to terminal height in intel_gpu_top.Kenneth Graunke
When using intel_gpu_top in a small terminal, the most important information (ring idle/busy units) scrolls off the top of the screen. This patch limits the number of lines printed to the terminal height so that the most idle units (at the bottom) are truncated instead. Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
2009-11-30decode: Split decoder and reuse outside of intel_gpu_dumpChris Wilson
Introduce a second decoder that simpler operates on a file so that it can be run on dumped batchbuffers independent of the gpu. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2009-11-06Add: tools/intel_audio_dumpWu Fengguang
Signed-off-by: Zhenyu Wang <zhenyu.z.wang@intel.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
2009-10-08Add: tools/intel_gpu_timeChris Wilson
A simple variant on time crossed with intel_gpu_top to estimate the amount of GPU activity during a program's execution time. The resource usage (sys+user, i.e. CPU %) is for the child, but the GPU measure is global. Hmm. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
2009-10-06Add intel_gpu_dump from the 2D driver.Eric Anholt
2009-09-21Bump to 1.0.2 for release.Eric Anholt
2009-09-17Print unmatched opcode value for all 3D UNKNOWN messagesCarl Worth
This just simplifies one step for fixing up an incompletely-parsed dump.
2009-09-08Add support for new chipsXiang, Haihao
Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com>
2009-09-08CS FENCE in URB_FENCE is 11-bits wideXiang, Haihao
Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com>
2009-09-08Fix the length of CONSTANT_BUFFERXiang, Haihao
Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com>
2009-09-04intel_gpu_dump: Don't pretend we understand vertex formats on 8xx.Eric Anholt
2009-09-04intel_gpu_dump: Parse LOAD_STATE_IMMEDIATE_2 for 830.Eric Anholt
2009-09-04intel_gpu_dump: Add IPEIR and PGTBL_ER to output.Eric Anholt
2009-09-04Add INSTDONE bits for 830-865.Eric Anholt
2009-09-04intel_gpu_dump: Fix decode for LOAD_STATE_IMMEDIATE_1 with S8 set.Eric Anholt
2009-09-04Add a manpage for intel_reg_writeEric Anholt
2009-09-03dump: Minor typoChris Wilson
2009-09-01Add gem_fence_thrash testChris Wilson
This is a test case that overcommits fence registers between threads, which are copying from one fenced bo to another. In earlier versions of the driver this would cause excessive spinning as the first inactive (i.e. not in use by the GPU) would be used to service the next page. After all the fence registers had been allocated, in effect only the very first fence would then be used for all subsequent faults.
2009-07-07Add CS_USB_STATE decodingBen Gamari
2009-07-07Add CONSTANT_BUFFER decodingBen Gamari
2009-07-07Fix gs_fence output in URB_FENCE outputBen Gamari
2009-07-07add realloc bits to URB_FENCE decodingBen Gamari
2009-07-07Fix error message for case of kernel prior to 2.6.30Carl Worth
The error message was falsely claiming that a debugfs directory didn't exist, when it was supposed to report that the ringbuffer file did not exist within that directory.
2009-06-30.gitignore: catch up to intel_reg_write additionEric Anholt
2009-06-30intel_gpu_dump: Add instdone register values and decoding.Eric Anholt
2009-06-30intel_gpu_top: Move instdone bit definitions to lib to share with _dump.Eric Anholt
2009-06-23intel_gpu_dump: Use the correct IPEHR on pre-965.Eric Anholt
2009-06-23intel_gpu_dump: Add details on URB_FENCE.Eric Anholt
2009-06-23Oops, fix up printed hw offset since the HEAD pointer fixupEric Anholt
2009-06-23Add more 965 INSTDONE bits.Eric Anholt
This shows off the units that are stuck busy in the ut2004 hang.
2009-06-23Correctly flag the acthd when it points within a packet.Eric Anholt
2009-06-23Add the acthd to the GPU dump.Eric Anholt
2009-06-23Add register writing toolBen Gamari
Signed-off-by: Eric Anholt <eric@anholt.net>
2009-06-18Four new tests for error handlingJesse Barnes
Add four new tests for error the error handling cases: - gem_bad_address - store to a bad address, should generate a protection or page table error - gem_bad_batch - try to execute a bad batch, should generate a protection, invalid instruction or page table error - gem_bad_blit - blit to an invalid location, should generated a protection or page table error - gem_hang - hang the GPU on an event that will never happen, test hang detection & recovery code
2009-06-09Make the precentage bars fit in 80 columns.Eric Anholt
Signed-off-by: Eric Anholt <eric@anholt.net>
2009-06-09A pedantic addition of a format string to a printf callRobert Bragg
The printf used to clear the screen didn't have a format string, this adds one to avoid a compiler warning. Signed-off-by: Eric Anholt <eric@anholt.net>
2009-06-09Adds unicode bars for quickly visualizing the busy percentagesRobert Bragg
It can be a bit easier to digest the percentages with bar graphs than by scanning continually changing numbers. Signed-off-by: Eric Anholt <eric@anholt.net>
2009-06-09Increases the sample frequency from 100/sec to 10,000/secRobert Bragg
For a typical vsync locked application running at 60fps, sampling at just under twice a frame doesn't seem to give very stable lists of relevent hardware units because there are a number of units involved that may not be sampled one second to the next. This bumps the sample rate to 10,000 instead which is ~ 170 samples per frame so we tend to hit all the units involved. It also changes the report threshold to a sample count >= 1, so you don't see as many units with a percentage of 0. Signed-off-by: Eric Anholt <eric@anholt.net>
2009-06-09Revert "intel_gpu_top:print a visual clue on how big a certain use is"Robert Bragg
This reverts commit 5e13b98da1e7e31cffba84fd257002357d5f2682. We can print prettier graphs using unicode Signed-off-by: Eric Anholt <eric@anholt.net>
2009-06-04intel_gpu_top: Print GPU clock information, which seems interesting.Eric Anholt
2009-06-04intel_gpu_top:print a visual clue on how big a certain use isArjan van de Ven
humans are pretty bad at reading percentages quicky; this patch adds a histogram capability to make it more visually clear as to which lines are big ticket items
2009-05-19Bump version to 1.0.1 for release.Eric Anholt
2009-05-19intel_gpu_dump: Stop decoding batchbuffers after MI_BATCH_BUFFER_END.Eric Anholt
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-28 15:15:00 +0000