Bartosz Taudul
e30608afbf
Store and pass AddrStat data in one data structure.
2021-07-18 15:00:22 +02:00
Bartosz Taudul
9c7a122d94
Implement counting relative hw samples data.
...
This exploits the fact that AddrStat has two data fields (local and ext) to
store branch and cache information.
2021-07-18 15:00:22 +02:00
Bartosz Taudul
8c78af4d00
Drop limitView from GatherIpHwStats interface.
2021-07-18 15:00:21 +02:00
Bartosz Taudul
a5e655d1ee
Add relative hw samples checkbox.
2021-07-18 15:00:21 +02:00
Bartosz Taudul
b4c1313a2e
Make hw stats cost a parameter.
2021-07-18 02:03:29 +02:00
Bartosz Taudul
50f7deb1a3
Merge pull request #243 from benvanik/patch-4
...
Indenting empty GPU zone tree nodes when grouped to keep zones aligned.
2021-07-17 20:48:43 +02:00
Ben Vanik
ba185b18f9
Indenting empty grouped CPU/GPU zone tree nodes to keep things aligned.
2021-07-17 11:46:29 -07:00
Ben Vanik
e3165c333b
Fixing unbalanced tree pop in grouped GPU zones.
2021-07-17 09:25:44 -07:00
Bartosz Taudul
edae542a48
Allow selecting image name for filtering from a list.
2021-07-11 19:43:51 +02:00
Bartosz Taudul
b6db644ac6
Add hasher and comparator for StringIdx.
2021-07-11 19:43:40 +02:00
Terence Rokop
68ec7abdf4
Move responsibility for spacing of combo box
...
Thereby fix a spurious horizontal separator bar.
2021-06-26 11:51:57 -07:00
Terence Rokop
d6fd252ce4
Add more spacing to pre-existing options
2021-06-26 10:41:24 -07:00
Terence Rokop
e105d2d96c
Aesthetic fixes to accumulation mode combo box
...
Shorter text fields and more spacing.
2021-06-26 10:41:23 -07:00
Terence Rokop
1dd117533e
Avoid non-reentrant option in sampling/symbol view
2021-06-26 10:41:23 -07:00
Terence Rokop
f000dce73f
Replace "enum class" switches with explicit casts
2021-06-26 08:30:15 -07:00
Terence Rokop
b392671a7a
Make time accumulation mode use combo box
2021-06-25 21:27:45 -07:00
Bartosz Taudul
9a22b8e83c
Cosmetics.
2021-06-23 20:43:46 +02:00
Bartosz Taudul
913463635a
Cosmetics.
2021-06-23 20:37:14 +02:00
Terence Rokop
9366e58d12
Introduce "Non-reentrant time" radio button
...
Add to the statistics view an option for "Non-reentrant
time", which displays the count of and time spent in zone
events which were the only appearances (at that time) of
their zones on their threads' stacks.
Besides the GUI changes, this involves:
- Introducing a tri-state accumulation mode to replace the
boolean "self time": now there's "Self time only",
"Child time", and "Non-reentrant time".
- Removing the separate "selfTotal" from SrcLocZonesSlim,
making "total" represent whichever of the now three options
is active, which in turn requires keeping track of the
accumulation mode in StatisticsCache and invalidating that
cache when the accumulation mode changes.
2021-06-20 17:56:15 -07:00
Terence Rokop
66053e37f7
Add non-reentrant stats to SourceLocationZones
...
Extend SourceLocationZones with fields to track the count
and time of non-reentrant zone events -- that is, zone
events which were the only appearances (at the time) of
those zones on their threads' stacks.
2021-06-20 17:56:15 -07:00
Terence Rokop
c90e39e06e
Keep track of zone appearances on thread stacks
...
Start keeping track, using the previously-introduced
SrcLocCountMap, of the number of appearances of each zone
on each thread's stack at a given time.
2021-06-20 17:56:15 -07:00
Terence Rokop
1f0b4656f4
Introduce SrcLocCountMap
...
Add to ThreadData a map from source location to a counter,
which will be used to keep track of the number of
appearances of zones with the corresponding source locations
on each thread's stack.
2021-06-20 17:56:14 -07:00
Terence Rokop
0a8ec09566
Introduce View::IsZoneReentry()
...
These two methods can search a timeline to determine whether
a given ZoneEvent is the only appearance of the given zone
on the current thread stack, or a re-entry.
2021-06-20 17:53:38 -07:00
Bartosz Taudul
0e0692b7f7
Don't display hw samples as time in selected lines summary.
2021-06-20 16:01:19 +02:00
Bartosz Taudul
e9aca02880
Make hw sample cost in source files relative to whole symbol.
2021-06-20 15:55:21 +02:00
Bartosz Taudul
846bde1a11
Narrow down search range.
2021-06-20 14:37:56 +02:00
Bartosz Taudul
15b42039bd
Add very early exit test.
2021-06-20 14:34:47 +02:00
Bartosz Taudul
d4b92e0fbe
Add early exit conditions.
2021-06-20 14:33:08 +02:00
Bartosz Taudul
a10d71b766
Switch loop order for better cache locality on the slow path.
2021-06-20 14:30:55 +02:00
Bartosz Taudul
a9a16b4d94
Narrow down search region.
2021-06-20 14:24:42 +02:00
Bartosz Taudul
22352dd29b
Select optimized path before entering loop.
2021-06-20 14:22:14 +02:00
Bartosz Taudul
5d86002f82
Calculate all CPU usage values in one go.
2021-06-20 14:19:18 +02:00
Bartosz Taudul
5efc03cdf9
Move cycles up in cost combo selector.
2021-06-20 12:50:13 +02:00
Bartosz Taudul
7e17c8643c
Don't show hw events as time.
2021-06-20 01:08:18 +02:00
Bartosz Taudul
bc4016e97c
Don't depend on callstack frames to match hw samples to source.
2021-06-20 01:01:29 +02:00
Bartosz Taudul
2f3ee594f0
Use square root to make slow branches and cache less spiky.
2021-06-20 00:50:14 +02:00
Bartosz Taudul
3305ea2775
Keep raw hw sample data visually separate.
2021-06-20 00:46:29 +02:00
Bartosz Taudul
07fe0a5447
Use enum for cost selection.
2021-06-20 00:45:39 +02:00
Bartosz Taudul
3cc69b221e
Select Zstd compression when Zstd level is changed.
2021-06-20 00:25:30 +02:00
Bartosz Taudul
80e1b0c2cf
Don't display hw samples as time in files list.
2021-06-20 00:14:19 +02:00
Bartosz Taudul
52708268fe
Store 64-bit integers in AddrStat.
2021-06-20 00:08:25 +02:00
Bartosz Taudul
4e6a1bae22
Don't display time for hw samples.
2021-06-20 00:04:08 +02:00
Bartosz Taudul
326a2a70d8
Add indirect hw statistics.
2021-06-20 00:01:37 +02:00
Bartosz Taudul
ad2b6e932b
Don't scroll cost combo list.
2021-06-20 00:01:21 +02:00
Bartosz Taudul
a5991036dc
Add more hw stats as cost.
2021-06-19 23:43:46 +02:00
Bartosz Taudul
c7b3d42852
Calculating cost in cycles and retirements.
2021-06-19 23:39:33 +02:00
Bartosz Taudul
90149641df
Reset cost selection when no samples.
2021-06-19 23:17:24 +02:00
Bartosz Taudul
8d52d2acfd
Disable inline context if no inline symbols available.
2021-06-19 21:40:30 +02:00
Bartosz Taudul
2e3241ba54
Restrict hardware samples to inline function context.
2021-06-19 20:50:06 +02:00
Bartosz Taudul
6cc844abee
Display inline symbol address.
2021-06-19 20:20:52 +02:00
Bartosz Taudul
748c22df8e
Darken assembly instructions which aren't in current context.
2021-06-19 20:11:53 +02:00
Bartosz Taudul
53111f9dd9
Save/load code symbol map.
2021-06-19 19:58:16 +02:00
Bartosz Taudul
8045ceee5d
Display function assigned to assembly line.
2021-06-19 19:52:33 +02:00
Bartosz Taudul
ec3ee09f09
Add inline symbols map accessors.
2021-06-19 19:13:34 +02:00
Bartosz Taudul
654331a8c8
Create code address -> symbol map.
2021-06-19 19:07:57 +02:00
Bartosz Taudul
cc0ca341bb
Add cost criteria selection UI.
2021-06-19 18:16:11 +02:00
Bartosz Taudul
7ad9cafefb
Add child call samples hints to the UI.
2021-06-19 17:41:29 +02:00
Bartosz Taudul
6e8d57bc98
Update context switches look.
2021-06-19 16:50:25 +02:00
Bartosz Taudul
c17a913cf5
Update zones look.
2021-06-19 16:43:56 +02:00
Bartosz Taudul
b91cd9148d
Add 2-segment line drawing wrapper.
2021-06-19 16:22:50 +02:00
Bartosz Taudul
188320db48
Simplify zone color data retrieval.
2021-06-19 16:20:35 +02:00
Bartosz Taudul
5e582ef057
Omit line number from source locations, if not known.
2021-06-19 12:47:55 +02:00
Bartosz Taudul
91f1845d92
Add LocationToString() helper.
2021-06-19 12:33:23 +02:00
Bartosz Taudul
c69cf5bd3f
Cosmetics.
2021-06-19 12:33:16 +02:00
Bartosz Taudul
8e5a53a191
Merge remote-tracking branch 'origin/master' into hw
2021-06-19 12:19:10 +02:00
Andrey Voroshilov
d4d77006ac
Fix a crash in Worker c-tor when converting certain JSON files
2021-06-19 01:12:41 -07:00
Bartosz Taudul
e1b68232dc
Better describe kernel ghost zones.
2021-06-19 01:40:05 +02:00
Bartosz Taudul
a96410547b
Display thread kernel time.
2021-06-17 01:56:16 +02:00
Bartosz Taudul
d49da69972
Count kernel samples.
2021-06-17 01:47:19 +02:00
Bartosz Taudul
d2ebe341f2
Allow filtering out kernel symbols from statistics view.
2021-06-16 01:43:09 +02:00
Bartosz Taudul
f145ca5897
Fix assert.
2021-06-16 01:39:43 +02:00
Bartosz Taudul
48fe6550a6
Kernel code is unreachable from user space.
2021-06-15 21:40:08 +02:00
Bartosz Taudul
5b642cad01
Implement combining sample callstacks.
...
This is required, because Windows will send two callstacks with the same
timestamp, one for kernel-space, second for user-space.
2021-06-15 02:25:12 +02:00
Bartosz Taudul
db1dc311b0
Add Int48 clearing function.
2021-06-15 02:04:32 +02:00
Bartosz Taudul
0fdd5ab01b
Extract callstack sample processing implementation.
2021-06-15 01:59:49 +02:00
Bartosz Taudul
891e1ac280
Read combine samples flag on server.
2021-06-15 01:33:43 +02:00
Bartosz Taudul
06dcdd342f
Combine flags in welcome message.
2021-06-15 01:26:50 +02:00
Bartosz Taudul
004681b02b
Merge remote-tracking branch 'origin/master' into hw
2021-06-14 23:54:34 +02:00
Bartosz Taudul
39e317f36d
Fix display of messages with newlines.
2021-06-14 23:51:41 +02:00
Bartosz Taudul
2d2a5c92fd
Increase symbol retrieval size limit to 128 KB.
2021-06-13 01:16:29 +02:00
Bartosz Taudul
f773e18375
Different color for kernel frames in callstacks.
2021-06-12 16:16:56 +02:00
Bartosz Taudul
0c13889589
Distinguish kernel symbols on statistics list.
2021-06-12 16:09:44 +02:00
Bartosz Taudul
be07ccc1d3
Kernel symbols don't have parents.
2021-06-12 16:09:43 +02:00
Bartosz Taudul
3968945e6a
Display kernel ghost zones with a different color.
2021-06-12 15:35:44 +02:00
Bartosz Taudul
ff54c29913
Save/load GPU timer overflow information.
2021-06-09 21:12:50 +02:00
Bartosz Taudul
9e28f441c8
Cosmetics.
2021-06-09 21:12:42 +02:00
Bartosz Taudul
27e61b8204
Remove not needed check.
2021-06-09 21:08:48 +02:00
Bartosz Taudul
7aa575fd2e
Display GPU timer overflow notification.
2021-06-09 21:08:48 +02:00
Bartosz Taudul
de2ca9b22a
Change check for showing GPU timestamp accuracy.
2021-06-09 21:08:48 +02:00
Bartosz Taudul
b7b9912b10
Handle GPU timer overflows with heuristics.
2021-06-09 21:08:47 +02:00
Bartosz Taudul
90b51568e9
Add common lzcnt implementation.
...
Not really tested, so fingers crossed.
2021-06-09 20:29:43 +02:00
Bartosz Taudul
9c2ea8a71f
Specify minimum length of subframe skip in one place.
2021-06-09 02:13:00 +02:00
Bartosz Taudul
85da04bcc4
Add hw samples line part to source view.
2021-06-09 00:19:17 +02:00
Bartosz Taudul
def9570eda
Extract rendering hw samples line part.
2021-06-09 00:19:17 +02:00
Bartosz Taudul
18cace42ca
Display hw samples tooltip for source lines.
2021-06-08 23:46:30 +02:00
Bartosz Taudul
82bfee5127
Move helper functions to top of the file.
2021-06-08 23:46:29 +02:00
Bartosz Taudul
2eb50bcf42
Hardware sample data was already queried.
2021-06-08 23:46:29 +02:00
Bartosz Taudul
66318bdb3b
Display target FPS also as time available.
2021-06-08 22:56:06 +02:00
Bartosz Taudul
b68c23fc64
Update x86 CPU models list.
2021-06-04 18:59:41 +02:00
Bartosz Taudul
4316d48bea
Add a note about CPUID list.
2021-06-04 18:48:01 +02:00
Bartosz Taudul
7c378cd0a9
Add Rocket Lake uarch data.
2021-06-04 18:40:37 +02:00
Bartosz Taudul
cc831e8192
Description is not supposed to be formatted.
2021-06-04 15:29:08 +02:00
Bartosz Taudul
0b05587b05
Don't need to format const string.
2021-06-04 15:27:23 +02:00
Bartosz Taudul
cb849ee14c
Capitalize Tracy name.
2021-06-04 15:17:20 +02:00
Bartosz Taudul
3c076ddb6f
Opening unsupported trace gives option to download update.
2021-06-04 15:17:20 +02:00
Bartosz Taudul
39cf98f98c
Move OpenWebpage() to a separate source file.
2021-06-04 15:17:14 +02:00
Bartosz Taudul
86510c48e0
Use proper type.
2021-06-04 15:16:44 +02:00
Bartosz Taudul
3c31fb56a8
Allow range-limiting hardware samples.
2021-06-04 13:58:00 +02:00
Bartosz Taudul
a1acea0c50
Support hw sample times on server.
2021-06-04 13:38:45 +02:00
Bartosz Taudul
b7c5939bb8
Merge remote-tracking branch 'origin/master' into hw
2021-06-02 01:12:28 +02:00
Bartosz Taudul
94ec6a0d9d
Move TracyYield.hpp to common.
2021-05-31 02:19:35 +02:00
Bartosz Taudul
f8ccd8c40d
Move TracyStackFrames to common.
2021-05-23 23:51:56 +02:00
Bartosz Taudul
a6011cd1ad
Ignore intrinsic wrappers in callstack frames.
...
With gcc/clang the wrapper functions for intrinsics are annoyingly inserted at
top level of stack traces, making it hard to see the call site. Filter out all
known instrinsic headers.
2021-05-23 23:22:45 +02:00
Bartosz Taudul
c13611cf0c
Make unreliable hw stats darker.
2021-05-23 21:32:48 +02:00
Bartosz Taudul
19c41b94c0
Add glow to hotness indicators on lines.
2021-05-23 13:52:38 +02:00
Bartosz Taudul
a6f85bd061
Color hardware samples stats.
2021-05-23 13:13:38 +02:00
Bartosz Taudul
48ab346835
Add goodness color table accessor.
2021-05-23 12:49:40 +02:00
Bartosz Taudul
1b589855e8
Adjust hotness color scaling.
2021-05-23 12:29:48 +02:00
Bartosz Taudul
815cf7d00a
Display hardware counter statistics in asm line columns.
2021-05-23 02:39:31 +02:00
Bartosz Taudul
77c33327f4
Merge remote-tracking branch 'origin/master' into hw
2021-05-23 01:01:21 +02:00
Bartosz Taudul
5f7225ce32
Merge pull request #224 from keur/external_trace_use_file_and_line
...
Use file:line when comparing traces
2021-05-22 12:36:05 +02:00
Kevin Kuehler
871d41be1f
Implement FindMatchingZone(..)
...
Sets m_compare to the matched index. It supports multiple flags. It can
be run by comparing function name, source file, line number, and any
combination thereof. When searching for a match, we do 3 runs, quitting
out if any of them succeed.
1. Look for zone with same function same, source file, line number.
2. Look for zone with same function same, source file.
3. Look for zone with same function same.
2021-05-22 01:33:06 -07:00
Bartosz Taudul
306055ebfa
Cosmetics.
2021-05-22 00:46:11 +02:00
Kevin Kuehler
5ab84d0c3f
Use file:line when comparing traces
...
When comparing traces, where multiple classes share the same zone
names, the behavior prior to this patch was to auto-select the first
matching zone name in the other trace. Instead, find the most correct
zone by using filename and line number.
2021-05-21 15:25:26 -07:00
Bartosz Taudul
ea5a9ee83b
Merge remote-tracking branch 'origin/master' into hw
2021-05-20 20:56:16 +02:00
Bartosz Taudul
87cff004a4
Show hw samples tooltip when there are no samples.
2021-05-20 20:10:27 +02:00
Bartosz Taudul
3ba82ba4d6
Separate IPC, cache and branch data in tooltip.
2021-05-20 19:56:23 +02:00
Bartosz Taudul
c6f071a66a
Save and load hardware sample data.
2021-05-20 19:37:51 +02:00
xavier
28e5aae17e
build with gcc 11
2021-05-20 17:30:54 +02:00
Bartosz Taudul
df50eb890f
Fix printing percentage.
2021-05-20 02:53:49 +02:00
Bartosz Taudul
5a7e9cdbdd
0% miss rates are fine too.
2021-05-20 02:31:00 +02:00
Bartosz Taudul
9b4716c49e
Display cache and branch miss rates.
2021-05-20 02:26:02 +02:00
Bartosz Taudul
227a8d1aee
Process additional hardware sample data.
2021-05-20 02:19:11 +02:00
Bartosz Taudul
24b5e16718
Display hw sampling stats in tooltip.
2021-05-20 01:37:59 +02:00
Bartosz Taudul
3a0e12043d
Differentiate hw samples from code addresses.
2021-05-19 23:29:27 +02:00
Bartosz Taudul
28cc72a69c
Display hardware samples count.
2021-05-19 23:05:58 +02:00
Bartosz Taudul
3228e20c2e
Add hardware samples accessors.
2021-05-19 23:05:50 +02:00
Bartosz Taudul
373a2b66c6
Collect hardware sample data.
2021-05-19 23:05:33 +02:00
Bartosz Taudul
64ed3d057d
Add no-op dispatch of HW samples.
2021-05-19 21:09:55 +02:00
Bartosz Taudul
efc1777051
Implement range limit for child samples.
2021-05-19 20:26:50 +02:00
Bartosz Taudul
5ec1313af1
Drop legacy code for reading long unsupported traces.
2021-05-18 02:24:56 +02:00
Giulio Eulisse
aace8ac317
Update TracyView.cpp
2021-05-17 12:09:14 +02:00
Giulio Eulisse
2cdc3abba2
Update TracyImGui.hpp
2021-05-17 12:07:35 +02:00
Giulio Eulisse
4ab706d538
Update TracyMouse.cpp
2021-05-17 12:07:06 +02:00
Giulio Eulisse
bcb250aaab
Update TracySourceView.cpp
2021-05-17 12:06:37 +02:00
Giulio Eulisse
63e2c16e74
Do not use relative include path for ImGUI.h
...
#pragma once gets confused by `../../imgui/imgui.h` and `imgui.h` on macOS with XCode 12.5.
2021-05-17 12:05:14 +02:00
Bartosz Taudul
8219a0e4ca
Fix shift.
2021-05-15 18:39:01 +02:00
Bartosz Taudul
c91c7a7fd5
Use zstd dict for packing/unpacking frame images.
...
This only affects run-time memory usage and needs an offline calculation of
the dictionary. Results vary depending on similarity of image blocks.
agora 34.96 MB -> 28.21 MB
agora2 40.75 MB -> 34.14 MB
android-vk 36.21 MB -> 18.44 MB
astar3 44.72 MB -> 43.38 MB
clipper1 134.36 MB -> 52.16 MB
fi 50.82 MB -> 40.79 MB
fi-big 537.74 MB -> 469.54 MB
test 23.26 MB -> 1.87 MB
2021-05-15 18:06:44 +02:00
Bartosz Taudul
d555256546
Don't use separate texture compression context.
...
Previously it was needed, as saving could be made at the same time the UI was
active. Currently saving blocks UI access to data structures, as it possibly
may need to sort unsorted vectors.
2021-05-15 18:04:14 +02:00
Bartosz Taudul
925a23a053
Add texture packer with zstd dict support.
2021-05-15 18:04:14 +02:00