pleroy
1a7c1588f6
Add support for the Intel syntax supported by MSVC and ICC
2025-02-02 14:02:16 +01:00
JanLJL
c9e38631d1
Flake8 formatting
2024-05-02 17:00:12 +02:00
stefandesouza
4fd59eb0d0
Black formatting
2024-03-05 12:14:05 +01:00
stefandesouza
1c0708e750
Added updated files
2024-02-27 14:47:55 +01:00
stefandesouza
fa95293cb0
Flags into operand class
2024-02-24 12:11:52 +01:00
stefandesouza
ec798f61b2
More formatting
2024-01-10 13:26:50 +01:00
stefandesouza
339b06bd7f
Linters update
2023-12-10 18:25:00 +01:00
stefandesouza
cac4a0ebf2
flake8 standards
2023-12-03 21:04:58 +01:00
stefandesouza
cef7f8098d
Black formatting
2023-12-03 17:22:11 +01:00
stefandesouza
93ae586745
Fixed semantic and marker tests. Now only dump needs to be adjusted
2023-12-03 16:49:33 +01:00
stefandesouza
2c32ccf37a
pre/post-indexed to pre/post_indexed. Now have use ImmediateOperand type for mem offset. Changed some parser tests also
2023-12-02 16:56:43 +01:00
stefandesouza
26d65750a6
Fixed issue with throughput assignment
2023-10-30 19:32:05 +01:00
stefandesouza
ebb973493b
Added condition operand, adjusted tests to parse it & a few changes to get the kernelDG tests working
2023-10-29 16:36:00 +01:00
stefandesouza
14a2aa0b52
Changed style to conform to PEP-8 conventions; Added source and destination attributes to parent Operand class
2023-10-29 13:52:49 +01:00
stefandesouza
db02359ea2
frontend tests now use new OO style, removed AttrDict usage
2023-10-22 16:43:46 +02:00
stefandesouza
e95278d2a2
Included 'source' and 'destination' attributes when loading isa data
2023-10-16 15:48:47 +02:00
stefandesouza
db899a2709
Changing operand matching for class operand style
2023-09-25 21:35:17 +02:00
stefandesouza
42f96753c1
Black formatting
2023-09-12 12:45:28 +02:00
stefandesouza
7f4f87d192
Changes for operand matching, instruction loading
2023-09-11 18:23:57 +02:00
stefandesouza
615ef82f04
Changes to accomodate the new OO style
2023-08-28 15:19:46 +02:00
stefandesouza
0a32c77751
Added 2 operand types and made changes for attribute usage
2023-08-20 21:01:44 +02:00
JanLJL
d1201ace11
added more dependency analysis for post/pre indexing and condition flags
2023-03-14 17:00:02 +01:00
Qingcai Jiang
71b9a17ab8
fix a bug when longest_path is not integer, try 'ldpw3, w1, [x0, #0x48]' in AArch64
2021-12-30 21:32:29 +08:00
JanLJL
ba45038ad7
add latency of last instruction in CP
2021-11-04 11:58:40 +01:00
JanLJL
5205cb5cc6
fixed formatting with correct line length
2021-10-04 15:00:17 +02:00
JanLJL
e6ce870ca0
black formatting
2021-10-04 14:33:28 +02:00
JanLJL
d418c16f4a
applied flake8 and black rules
2021-08-26 16:58:19 +02:00
JanLJL
d59b100fa8
changed immediate type from str to int
2021-05-10 01:12:30 +02:00
JanLJL
1de644cd62
fixed incompatibilty to py3.6
2021-04-20 13:59:56 +02:00
JanLJL
3f31235f8a
added no timeout option
2021-04-19 10:57:51 +02:00
JanLJL
152360bad2
enhanced LCD analysis by making it parallel and added timeout flag
2021-04-19 00:04:03 +02:00
JanLJL
607d459569
keep dependency paths as generators instead of lists
2021-04-17 12:46:44 +02:00
JanLJL
b033b3b7aa
allow different base with prefix for offset values
2021-04-17 11:06:39 +02:00
Julian
08440ed5e1
Validation ( #71 )
...
Validating of OSACA predictions for IVB, SKX, ZEN1, ZEN2, A64FX and TX2 with different kernels.
build_and_run.py contains the configuration used at RRZE's testcluster and UR's qpace4, Analysis.ipynb contains the analysis script and results. Raw data from measurements (122MB) will be attached to next OSACA release.
For now, find the raw data here: https://hawo.net/~sijuhamm/d/UPIhBOtz/validation-data.tar.gz
The analysis report can be viewed at https://nbviewer.jupyter.org/github/RRZE-HPC/OSACA/blob/validation/validation/Analysis.ipynb
Quite a few changes on OSACA included:
Feature: register change tracking via semantic understanding of operations
Feature: recording LCD latency along path and exposing this to frontend
Feature: support for memory reference aliases
Feature: store throughput scaling (similar to load throughput scaling)
Fix: model importer works with latest uops.info export
Fix: immediate type tracking on ARM now preserves type in internal representaion
Removed unused KerncraftAPI
2021-04-15 14:42:37 +02:00
Julian Hammer
63563ecabc
flake8 to ignore some errors and small style improvements
2021-03-11 12:52:34 +01:00
Julian Hammer
b7625a4a25
making flake8 happy
2021-03-11 12:29:14 +01:00
Julian Hammer
6204c90934
migrate code style to Black
2021-03-11 12:02:45 +01:00
JanLJL
4e73e24b99
added documentation
2020-03-09 16:35:06 +01:00
JanLJL
5574a93a5e
made detection of flag dependencies as opt_in for now
2020-01-29 13:03:43 +01:00
JanLJL
76469f7898
supports hidden operands now (for flags or special instructions)
2020-01-14 20:54:00 +01:00
Julian Hammer
f18a48653f
FIX #46 untangled semantic and non-semantic operand info
2019-11-14 16:43:33 +01:00
JanLJL
22bfcd8020
added visual graph export, YMM LD support for ZEN and support for non-dyn loads in DB
2019-09-27 17:15:04 +02:00
JanLJL
625d814dce
new dynamic tp and lt values for LD instructions
2019-09-26 21:39:56 +02:00
JanLJL
19dbd90849
runnable pmbs version
2019-09-25 13:01:30 +02:00
JanLJL
042c034838
implemented new CP calculation for x86
2019-09-24 19:00:12 +02:00
JanLJL
f278180402
nicer perspective of loop-carried deps
2019-09-18 00:09:26 +02:00
JanLJL
ae5845b944
added tests for loop-carried deps and changed data structure of them to dict
2019-08-30 10:11:51 +02:00
JanLJL
80e741d411
enhanced frontend and added hidable load port
2019-08-29 14:03:16 +02:00
JanLJL
7855166624
fixed loop-carried dependency check and minor fixes in DBs
2019-08-28 13:07:24 +02:00
JanLJL
df8a81bf4d
initial version of loop-carried dependencies checker
2019-08-23 19:01:20 +02:00
