Skip to content

Run abs kernel on A5 cannsim#167

Draft
zouzias wants to merge 10 commits into
mainfrom
166-kernel-abs-run-using-cannsim
Draft

Run abs kernel on A5 cannsim#167
zouzias wants to merge 10 commits into
mainfrom
166-kernel-abs-run-using-cannsim

Conversation

@zouzias
Copy link
Copy Markdown
Collaborator

@zouzias zouzias commented May 15, 2026

Work in progress for running vector abs on A5 simulation mode.

make run_abs_a5 
Details
cat cannsim_20260519155124_main_abs/cannsim.log 
[vabs] Use default BlockDim: 8
[DRVSTUB_LOG] driver_api.c:2393 halGetSocVersion:halGetSocVersion len:50 soc_version:Ascend950PR_9589
[DRVSTUB_LOG] driver_api.c:2393 halGetSocVersion:halGetSocVersion len:50 soc_version:Ascend950PR_9589
chip type: 0 
core count: 192
thread count: 32
rankId: 0 chipNum: 1
rankId: 1 chipNum: 1
rankId: 0 chipId Base: 0
rankId: 1 chipId Base: 1
rankId: 0 threadNum: 10
rankId: 1 threadNum: 10
WARNING: no l3 cache
WARNING: no media unit
WARNING: no dvpp unit
WARNING: no gpu unit
HHA->DMC load nofile failed
HHA->DMC load nofile failed
HHA->DMC load nofile failed
DDR load checkpoint start, please specify the "DDR_offset_addr", "DDR_CheckPoint_Raw" and "DDR_CheckPoint_Guide"  in confgiuration file: 0x5b7dbb8de3b0
Reading DDR checkpoints! please check: Raw_file:./soft/dynamicmemory-data
 Guide file:./soft/dynamicmemory-root
Warning! Fail reading DDR checkpoints!
 DIE0 HA TOP: 0x5b7d4f25c260
== Loading public model file './parameter/public.ini' ==
== Loading system model file './parameter/bailusystem.ini' ==
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
== Loading device model file './parameter/lpddr5_6400M_bailu.ini' ==
== Unable to load ./parameter/ss_0gb_lpddr5_6400M.ini, DRAM power model not enable ==
== lpddr5 1900 Mbps, 1 Channels, 1 Ranks, Gbuf false, IECC false ==
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
[CORE_WRAPPER] [INFO] [0000000000] init_new_core_cfg (268):: CoreWrapper [DvcCore0] init, mode=CA, core ver=5, config file=./etc/1982_cloud_config.toml
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore0] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore1] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore2] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore3] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore4] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore5] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore6] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore7] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore8] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore9] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore10] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore11] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore12] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore13] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore14] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore15] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
Module STARS_ChiWrapper_0_0_SCHE_Chn0 allocate thread Id : 0
CONFIG STARS SIM_CFG: 1981_sim_ffts_plus.toml
CONFIG STARS LOG_PATH: ./log_ca
[INFO] [0000000000] sim_cfg: 1981_sim_ffts_plus.toml
[INFO] [0000000000] model_cfg: 1981_model.toml
[INFO] [0000000000] stars_cfg: 1981_stars_ffts_plus.toml
[INFO] [0000000000] ffts_cfg: 1981_ffts.toml
Warning: open top case toml file fail
[TmSim]: Run in parallel esl_sim mode, concurrency num is: 32
[TmSim]: Top module clk0 is assigned to thread 0
[TmSim]: Top module core0 is assigned to thread 0
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore0] build, esl_idx=0, log_path=./log_ca
[TmSim]: Top module clk1 is assigned to thread 1
[TmSim]: Top module core1 is assigned to thread 1
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore1] build, esl_idx=1, log_path=./log_ca
[TmSim]: Top module clk2 is assigned to thread 2
[TmSim]: Top module core2 is assigned to thread 2
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore2] build, esl_idx=2, log_path=./log_ca
[TmSim]: Top module clk3 is assigned to thread 3
[TmSim]: Top module core3 is assigned to thread 3
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore3] build, esl_idx=3, log_path=./log_ca
[TmSim]: Top module clk4 is assigned to thread 4
[TmSim]: Top module core4 is assigned to thread 4
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore4] build, esl_idx=4, log_path=./log_ca
[TmSim]: Top module clk5 is assigned to thread 5
[TmSim]: Top module core5 is assigned to thread 5
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore5] build, esl_idx=5, log_path=./log_ca
[TmSim]: Top module clk6 is assigned to thread 6
[TmSim]: Top module core6 is assigned to thread 6
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore6] build, esl_idx=6, log_path=./log_ca
[TmSim]: Top module clk7 is assigned to thread 7
[TmSim]: Top module core7 is assigned to thread 7
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore7] build, esl_idx=7, log_path=./log_ca
[TmSim]: Top module clk8 is assigned to thread 8
[TmSim]: Top module core8 is assigned to thread 8
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore8] build, esl_idx=8, log_path=./log_ca
[TmSim]: Top module clk9 is assigned to thread 9
[TmSim]: Top module core9 is assigned to thread 9
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore9] build, esl_idx=9, log_path=./log_ca
[TmSim]: Top module clk10 is assigned to thread 10
[TmSim]: Top module core10 is assigned to thread 10
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore10] build, esl_idx=10, log_path=./log_ca
[TmSim]: Top module clk11 is assigned to thread 11
[TmSim]: Top module core11 is assigned to thread 11
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore11] build, esl_idx=11, log_path=./log_ca
[TmSim]: Top module clk12 is assigned to thread 12
[TmSim]: Top module core12 is assigned to thread 12
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore12] build, esl_idx=12, log_path=./log_ca
[TmSim]: Top module clk13 is assigned to thread 13
[TmSim]: Top module core13 is assigned to thread 13
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore13] build, esl_idx=13, log_path=./log_ca
[TmSim]: Top module clk14 is assigned to thread 14
[TmSim]: Top module core14 is assigned to thread 14
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore14] build, esl_idx=14, log_path=./log_ca
[TmSim]: Top module clk15 is assigned to thread 15
[TmSim]: Top module core15 is assigned to thread 15
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore15] build, esl_idx=15, log_path=./log_ca
Start to build SMMU Page !
SMMU Page build finished!
Start simulation with m_socCycle: 0
SoC unit rank0_chip0_die0 Created
HHA->DMC load nofile failed
HHA->DMC load nofile failed
HHA->DMC load nofile failed
DDR load checkpoint start, please specify the "DDR_offset_addr", "DDR_CheckPoint_Raw" and "DDR_CheckPoint_Guide"  in confgiuration file: 0x5b7e6ba98e10
Reading DDR checkpoints! please check: Raw_file:./soft/dynamicmemory-data
 Guide file:./soft/dynamicmemory-root
Warning! Fail reading DDR checkpoints!
 DIE1 HA TOP: 0x5b7dff411500
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
WARNING: UNKNOWN KEY 'TIMEOUT_SID_ENBALE' IN INI FILE
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore16] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore17] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore18] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore19] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore20] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore21] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore22] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore23] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore24] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore25] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore26] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore27] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore28] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore29] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore30] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
[CORE_WRAPPER] [INFO] [0000000000]         init (113):: CoreWrapper [DvcCore31] init, cube_subcore=1, vec_subccore=2, eff_cube_subcore=0, ref_period=0.40, self_period=0.61, debug_flags=1
Module STARS_ChiWrapper_0_1_SCHE_Chn0 allocate thread Id : 1
CONFIG STARS SIM_CFG: 1981_sim_ffts_plus.toml
CONFIG STARS LOG_PATH: ./log_ca
Warning: open top case toml file fail
[TmSim]: Top module clk16 is assigned to thread 16
[TmSim]: Top module core16 is assigned to thread 16
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore16] build, esl_idx=17, log_path=./log_ca
[TmSim]: Top module clk17 is assigned to thread 17
[TmSim]: Top module core17 is assigned to thread 17
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore17] build, esl_idx=18, log_path=./log_ca
[TmSim]: Top module clk18 is assigned to thread 18
[TmSim]: Top module core18 is assigned to thread 18
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore18] build, esl_idx=19, log_path=./log_ca
[TmSim]: Top module clk19 is assigned to thread 19
[TmSim]: Top module core19 is assigned to thread 19
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore19] build, esl_idx=20, log_path=./log_ca
[TmSim]: Top module clk20 is assigned to thread 20
[TmSim]: Top module core20 is assigned to thread 20
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore20] build, esl_idx=21, log_path=./log_ca
[TmSim]: Top module clk21 is assigned to thread 21
[TmSim]: Top module core21 is assigned to thread 21
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore21] build, esl_idx=22, log_path=./log_ca
[TmSim]: Top module clk22 is assigned to thread 22
[TmSim]: Top module core22 is assigned to thread 22
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore22] build, esl_idx=23, log_path=./log_ca
[TmSim]: Top module clk23 is assigned to thread 23
[TmSim]: Top module core23 is assigned to thread 23
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore23] build, esl_idx=24, log_path=./log_ca
[TmSim]: Top module clk24 is assigned to thread 24
[TmSim]: Top module core24 is assigned to thread 24
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore24] build, esl_idx=25, log_path=./log_ca
[TmSim]: Top module clk25 is assigned to thread 25
[TmSim]: Top module core25 is assigned to thread 25
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore25] build, esl_idx=26, log_path=./log_ca
[TmSim]: Top module clk26 is assigned to thread 26
[TmSim]: Top module core26 is assigned to thread 26
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore26] build, esl_idx=27, log_path=./log_ca
[TmSim]: Top module clk27 is assigned to thread 27
[TmSim]: Top module core27 is assigned to thread 27
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore27] build, esl_idx=28, log_path=./log_ca
[TmSim]: Top module clk28 is assigned to thread 28
[TmSim]: Top module core28 is assigned to thread 28
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore28] build, esl_idx=29, log_path=./log_ca
[TmSim]: Top module clk29 is assigned to thread 29
[TmSim]: Top module core29 is assigned to thread 29
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore29] build, esl_idx=30, log_path=./log_ca
[TmSim]: Top module clk30 is assigned to thread 30
[TmSim]: Top module core30 is assigned to thread 30
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore30] build, esl_idx=31, log_path=./log_ca
[TmSim]: Top module clk31 is assigned to thread 31
[TmSim]: Top module core31 is assigned to thread 31
[CORE_WRAPPER] [INFO] [0000000000]        build (159):: CoreWrapper [DvcCore31] build, esl_idx=32, log_path=./log_ca
Start to build SMMU Page !
SMMU Page build finished!
Start simulation with m_socCycle: 0
SoC unit rank0_chip0_die1 Created
can not find accessable port: 9 in chip: 0, die: 2
Start simulation with m_socCycle: 0
SoC unit rank0_chip0_die2 Created
can not find accessable port: 9 in chip: 0, die: 3
Start simulation with m_socCycle: 0
SoC unit rank0_chip0_die3 Created
Multi SoC in one chip Created
SLLC CONNECT : 600 +++++  10609
SLLC CONNECT : 601 +++++  10608
SLLC CONNECT : 602 +++++  10607
SLLC CONNECT : 604 +++++  10605
SLLC CONNECT : 605 +++++  10604
SLLC CONNECT : 607 +++++  10602
SLLC CONNECT : 608 +++++  10601
SLLC CONNECT : 609 +++++  10600
SLLC CONNECT : 60a +++++  2060c
SLLC CONNECT : 60b +++++  2060b
SLLC CONNECT : 60c +++++  2060a
SLLC CONNECT : 1060a +++++  3060c
SLLC CONNECT : 1060b +++++  3060b
SLLC CONNECT : 1060c +++++  3060a
rank0_chip0 created!
All Chip In Rank0 created!
[Esl Top] Number of concurrent threads: 32
[DRVSTUB_LOG] driver_api.c:601 sendSwapBuf:swapbuf_base_addr:9000000000
[DRVSTUB_LOG] driver_api.c:602 sendSwapBuf:sq:0 swapbuf_addr:9000000000
[DRVSTUB_LOG] driver_api.c:601 sendSwapBuf:swapbuf_base_addr:9000000000
[DRVSTUB_LOG] driver_api.c:602 sendSwapBuf:sq:1 swapbuf_addr:9000000080
[DRVSTUB_LOG] driver_api.c:2393 halGetSocVersion:halGetSocVersion len:50 soc_version:Ascend950PR_9589
[DRVSTUB_LOG] driver_api.c:2393 halGetSocVersion:halGetSocVersion len:50 soc_version:Ascend950PR_9589
[DRVSTUB_LOG] driver_api.c:601 sendSwapBuf:swapbuf_base_addr:9000000000
[DRVSTUB_LOG] driver_api.c:602 sendSwapBuf:sq:2 swapbuf_addr:9000000100
[DRVSTUB_LOG] driver_api.c:601 sendSwapBuf:swapbuf_base_addr:9000000000
[DRVSTUB_LOG] driver_api.c:602 sendSwapBuf:sq:3 swapbuf_addr:9000000180
[DRVSTUB_LOG] driver_api.c:2393 halGetSocVersion:halGetSocVersion len:50 soc_version:Ascend950PR_9589
==========================================
Input X
 54.781250-12.226562 71.750000 39.468750-81.187500 95.125000 52.218750 57.218750-74.375000 -9.921875-25.843750 85.375000 28.765625 64.562500-11.320312-54.562500
	...
 45.250000 -7.781250 31.984375 19.937500 -5.441406 90.000000-31.453125-64.562500 35.625000 69.187500-91.937500-10.070312 78.500000 49.937500 98.375000  6.281250
==========================================
Init vabs_fp16 kernel
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[0]: 0x80000
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[1]: 0x0
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[2]: 0x40002
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[3]: 0x3fd0000
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[4]: 0xb5ad200
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[5]: 0x90
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[6]: 0x90800
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[7]: 0x2120000
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[8]: 0xd0d000
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[9]: 0xd0d100
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[10]: 0x900090
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[11]: 0x40000
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[12]: 0x22c000
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[13]: 0x90
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[14]: 0x22c000
[DRVSTUB_LOG] driver_queue.c:118 sendStarsSQE:RTSQ_3 sqe_payload[15]: 0x90
[DRVSTUB_LOG] driver_queue.c:120 sendStarsSQE:sq_addr: 900b94d800
SoC sub 0 2 all tasks are finished!
[Hardware] parallel simulation finish. sim time: 1.132946s, cycle: 420, speed: 0.370715KHz
SoC sub 0 3 all tasks are finished!
[Hardware] parallel simulation finish. sim time: 0.818320s, cycle: 420, speed: 0.513247KHz
==========================================
Output
 54.781250 12.226562 71.750000 39.468750 81.187500 95.125000 52.218750 57.218750 74.375000  9.921875 25.843750 85.375000 28.765625 64.562500 11.320312 54.562500
	...
 45.250000  7.781250 31.984375 19.937500  5.441406 90.000000 31.453125 64.562500 35.625000 69.187500 91.937500 10.070312 78.500000 49.937500 98.375000  6.281250
==========================================
Parallel Simulation: All threads are joined.
ESL_TOP: parallel threads joined
ESL_TOP: system destructed
[INFO] Model stopped successfully.

Interesting fact

LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:$(pwd)/build/lib/ ./main_abs 
[vabs] Use default BlockDim: 8
==========================================
Input X
   54.7812  -12.2266     71.75   39.4688  -81.1875    95.125   52.2188   57.2188   -74.375  -9.92188  -25.8438    85.375   28.7656   64.5625  -11.3203  -54.5625

	...
     45.25  -7.78125   31.9844   19.9375  -5.44141        90  -31.4531  -64.5625    35.625   69.1875  -91.9375  -10.0703      78.5   49.9375    98.375   6.28125

==========================================
Init vabs_fp16 kernel
==========================================
Output
   54.7812   12.2266     71.75   39.4688   81.1875    95.125   52.2188   57.2188    74.375   9.92188   25.8438    85.375   28.7656   64.5625   11.3203   54.5625

	...
     45.25   7.78125   31.9844   19.9375   5.44141        90   31.4531   64.5625    35.625   69.1875   91.9375   10.0703      78.5   49.9375    98.375   6.28125

==========================================

@zouzias zouzias linked an issue May 15, 2026 that may be closed by this pull request
anastasios added 2 commits May 15, 2026 13:30
@zouzias zouzias changed the title WIP Run abs kernel on A5 cannsim May 15, 2026
@zouzias zouzias added the A5 label May 16, 2026
@learning-chip
Copy link
Copy Markdown
Collaborator

learning-chip commented May 18, 2026

Could you add torch wrapper and run the torch script by:

# inside CANN 9.0.0-950 image with torch-npu
export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/tools/simulator/Ascend950PR_9599/lib:$LD_LIBRARY_PATH

ulimit -n 65535
msprof op simulator --soc-version=Ascend950PR_9599 \
  python ./minimum_run.py

Where minimum_run.py is a simple python script that invokes custom compiled kernel.

@learning-chip
Copy link
Copy Markdown
Collaborator

Could you add torch wrapper and run the torch script by:

# inside CANN 9.0.0-950 image with torch-npu
export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/tools/simulator/Ascend950PR_9599/lib:$LD_LIBRARY_PATH

ulimit -n 65535
msprof op simulator --soc-version=Ascend950PR_9599 \
  python ./minimum_run.py

Where minimum_run.py is a simple python script that invokes custom compiled kernel.

Update: done in #169

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Kernel abs run using cannsim

2 participants