Skip to content

wgan example failed to run on H100 with cuda backend #3079

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
npuichigo opened this issue Apr 25, 2025 · 5 comments
Open

wgan example failed to run on H100 with cuda backend #3079

npuichigo opened this issue Apr 25, 2025 · 5 comments
Labels
bug Something isn't working fusion

Comments

@npuichigo
Copy link

0.17.0 version
H100 with CUDA 12.1

    Finished `release` profile [optimized] target(s) in 3.77s
     Running `/home/yuchao/workspace/burn/target/release/examples/wgan-mnist`

thread '<unnamed>' panicked at /home/yuchao/.cargo/registry/src/index.crates.io-1949cf8c6b5b557f/cubecl-cuda-0.5.0/src/compute/server.rs:682:17:
[Compilation Error] 
    default_program(36): warning #550-D: variable "l_arr_0" was set but never used
      uint32 l_arr_0[4];
             ^
    Remark: The warnings can be suppressed with "-diag-suppress <warning-number>"
    default_program(27): Error: Formal parameter space overflowed (36800 bytes required, max 32764 bytes allowed) in function elemwise_fuse
[Source]  
#include <cuda_runtime.h>
typedef unsigned int uint;
typedef unsigned char uint8;
typedef unsigned short uint16;
typedef unsigned int uint32;
typedef unsigned long long int uint64;
typedef signed char int8;
typedef signed short int16;
typedef signed int int32;
typedef signed long long int int64;

struct __align__(16) float_4 {
    float i_0;
    float i_1;
    float i_2;
    float i_3;
};

...

buffer_1018[idxGlobal] = reinterpret_cast< float_4 const&>(l_18917);
const float_4 l_18918 = l_18337;
buffer_1019[idxGlobal] = reinterpret_cast< float_4 const&>(l_18918);
const float_4 l_18919 = l_18373;
buffer_1020[idxGlobal] = reinterpret_cast< float_4 const&>(l_18919);
const float_4 l_18920 = l_18409;
buffer_1021[idxGlobal] = reinterpret_cast< float_4 const&>(l_18920);
}

}

thread 'main' panicked at /home/yuchao/workspace/burn/crates/burn-core/src/data/dataloader/multithread.rs:231:29:
called `Result::unwrap()` on an `Err` value: RecvError
@amanPradhan05
Copy link

hey, in which branch are you getting this error?

@npuichigo
Copy link
Author

Thanks. I just use the main branch.

@npuichigo
Copy link
Author

Same error on 0.17.0

@laggui laggui added the bug Something isn't working label Apr 28, 2025
@laggui
Copy link
Member

laggui commented Apr 28, 2025

Thanks for the bug report! Will take a look.

/edit: this is clearly a fusion bug

default_program(27): Error: Formal parameter space overflowed (36800 bytes required, max 32764 bytes allowed) in function elemwise_fuse

If you disable the default features (which includes fusion) it should work.

[dependencies]
-burn = { path = "../../crates/burn", features=["train", "vision"] }
+burn = { path = "../../crates/burn", features=["train", "vision", "std"], default-features = false }
image = { workspace = true }

Still a bug though 😅

@laggui laggui added the fusion label Apr 28, 2025
@laggui
Copy link
Member

laggui commented Apr 28, 2025

Looks like we maxed out the parameter space with element-wise fusion.

elemwise_fuse def
extern "C" __global__ void elemwise_fuse (
    float_4 buffer_0[], float_4 buffer_1[], float_4 buffer_2[], float_4 buffer_3[], 
float_4 buffer_4[], float_4 buffer_5[], float_4 buffer_6[], float_4 buffer_7[], float_4 
buffer_8[], float_4 buffer_9[], float_4 buffer_10[], float_4 buffer_11[], float_4 
buffer_12[], float_4 buffer_13[], float_4 buffer_14[], float_4 buffer_15[], float_4 
buffer_16[], float_4 buffer_17[], float_4 buffer_18[], float_4 buffer_19[], float_4 
buffer_20[], float_4 buffer_21[], float_4 buffer_22[], float_4 buffer_23[], float_4 
buffer_24[], float_4 buffer_25[], float_4 buffer_26[], float_4 buffer_27[], float_4 
buffer_28[], float_4 buffer_29[], float_4 buffer_30[], float_4 buffer_31[], float_4 
buffer_32[], float_4 buffer_33[], float_4 buffer_34[], float_4 buffer_35[], float_4 
buffer_36[], float_4 buffer_37[], float_4 buffer_38[], float_4 buffer_39[], float_4 
buffer_40[], float_4 buffer_41[], float_4 buffer_42[], float_4 buffer_43[], float_4 
buffer_44[], float_4 buffer_45[], float_4 buffer_46[], float_4 buffer_47[], float_4 
buffer_48[], float_4 buffer_49[], float_4 buffer_50[], float_4 buffer_51[], float_4 
buffer_52[], float_4 buffer_53[], float_4 buffer_54[], float_4 buffer_55[], float_4 
buffer_56[], float_4 buffer_57[], float_4 buffer_58[], float_4 buffer_59[], float_4 
buffer_60[], float_4 buffer_61[], float_4 buffer_62[], float_4 buffer_63[], float_4 
buffer_64[], float_4 buffer_65[], float_4 buffer_66[], float_4 buffer_67[], float_4 
buffer_68[], float_4 buffer_69[], float_4 buffer_70[], float_4 buffer_71[], float_4 
buffer_72[], float_4 buffer_73[], float_4 buffer_74[], float_4 buffer_75[], float_4 
buffer_76[], float_4 buffer_77[], float_4 buffer_78[], float_4 buffer_79[], float_4 
buffer_80[], float_4 buffer_81[], float_4 buffer_82[], float_4 buffer_83[], float_4 
buffer_84[], float_4 buffer_85[], float_4 buffer_86[], float_4 buffer_87[], float_4 
buffer_88[], float_4 buffer_89[], float_4 buffer_90[], float_4 buffer_91[], float_4 
buffer_92[], float_4 buffer_93[], float_4 buffer_94[], float_4 buffer_95[], float_4 
buffer_96[], float_4 buffer_97[], float_4 buffer_98[], float_4 buffer_99[], float_4 
buffer_100[], float_4 buffer_101[], float_4 buffer_102[], float_4 buffer_103[], float_4 
buffer_104[], float_4 buffer_105[], float_4 buffer_106[], float_4 buffer_107[], float_4 
buffer_108[], float_4 buffer_109[], float_4 buffer_110[], float_4 buffer_111[], float_4 
buffer_112[], float_4 buffer_113[], float_4 buffer_114[], float_4 buffer_115[], float_4 
buffer_116[], float_4 buffer_117[], float_4 buffer_118[], float_4 buffer_119[], float_4 
buffer_120[], float_4 buffer_121[], float_4 buffer_122[], float_4 buffer_123[], float_4 
buffer_124[], float_4 buffer_125[], float_4 buffer_126[], float_4 buffer_127[], float_4 
buffer_128[], float_4 buffer_129[], float_4 buffer_130[], float_4 buffer_131[], float_4 
buffer_132[], float_4 buffer_133[], float_4 buffer_134[], float_4 buffer_135[], float_4 
buffer_136[], float_4 buffer_137[], float_4 buffer_138[], float_4 buffer_139[], float_4 
buffer_140[], float_4 buffer_141[], float_4 buffer_142[], float_4 buffer_143[], float_4 
buffer_144[], float_4 buffer_145[], float_4 buffer_146[], float_4 buffer_147[], float_4 
buffer_148[], float_4 buffer_149[], float_4 buffer_150[], float_4 buffer_151[], float_4 
buffer_152[], float_4 buffer_153[], float_4 buffer_154[], float_4 buffer_155[], float_4 
buffer_156[], float_4 buffer_157[], float_4 buffer_158[], float_4 buffer_159[], float_4 
buffer_160[], float_4 buffer_161[], float_4 buffer_162[], float_4 buffer_163[], float_4 
buffer_164[], float_4 buffer_165[], float_4 buffer_166[], float_4 buffer_167[], float_4 
buffer_168[], float_4 buffer_169[], float_4 buffer_170[], float_4 buffer_171[], float_4 
buffer_172[], float_4 buffer_173[], float_4 buffer_174[], float_4 buffer_175[], float_4 
buffer_176[], float_4 buffer_177[], float_4 buffer_178[], float_4 buffer_179[], float_4 
buffer_180[], float_4 buffer_181[], float_4 buffer_182[], float_4 buffer_183[], float_4 
buffer_184[], float_4 buffer_185[], float_4 buffer_186[], float_4 buffer_187[], float_4 
buffer_188[], float_4 buffer_189[], float_4 buffer_190[], float_4 buffer_191[], float_4 
buffer_192[], float_4 buffer_193[], float_4 buffer_194[], float_4 buffer_195[], float_4 
buffer_196[], float_4 buffer_197[], float_4 buffer_198[], float_4 buffer_199[], float_4 
buffer_200[], float_4 buffer_201[], float_4 buffer_202[], float_4 buffer_203[], float_4 
buffer_204[], float_4 buffer_205[], float_4 buffer_206[], float_4 buffer_207[], float_4 
buffer_208[], float_4 buffer_209[], float_4 buffer_210[], float_4 buffer_211[], float_4 
buffer_212[], float_4 buffer_213[], float_4 buffer_214[], float_4 buffer_215[], float_4 
buffer_216[], float_4 buffer_217[], float_4 buffer_218[], float_4 buffer_219[], float_4 
buffer_220[], float_4 buffer_221[], float_4 buffer_222[], float_4 buffer_223[], float_4 
buffer_224[], float_4 buffer_225[], float_4 buffer_226[], float_4 buffer_227[], float_4 
buffer_228[], float_4 buffer_229[], float_4 buffer_230[], float_4 buffer_231[], float_4 
buffer_232[], float_4 buffer_233[], float_4 buffer_234[], float_4 buffer_235[], float_4 
buffer_236[], float_4 buffer_237[], float_4 buffer_238[], float_4 buffer_239[], float_4 
buffer_240[], float_4 buffer_241[], float_4 buffer_242[], float_4 buffer_243[], float_4 
buffer_244[], float_4 buffer_245[], float_4 buffer_246[], float_4 buffer_247[], float_4 
buffer_248[], float_4 buffer_249[], float_4 buffer_250[], float_4 buffer_251[], float_4 
buffer_252[], float_4 buffer_253[], float_4 buffer_254[], float_4 buffer_255[], float_4 
buffer_256[], float_4 buffer_257[], float_4 buffer_258[], float_4 buffer_259[], float_4 
buffer_260[], float_4 buffer_261[], float_4 buffer_262[], float_4 buffer_263[], float_4 
buffer_264[], float_4 buffer_265[], float_4 buffer_266[], float_4 buffer_267[], float_4 
buffer_268[], float_4 buffer_269[], float_4 buffer_270[], float_4 buffer_271[], float_4 
buffer_272[], float_4 buffer_273[], float_4 buffer_274[], float_4 buffer_275[], float_4 
buffer_276[], float_4 buffer_277[], float_4 buffer_278[], float_4 buffer_279[], float_4 
buffer_280[], float_4 buffer_281[], float_4 buffer_282[], float_4 buffer_283[], float_4 
buffer_284[], float_4 buffer_285[], float_4 buffer_286[], float_4 buffer_287[], float_4 
buffer_288[], float_4 buffer_289[], float_4 buffer_290[], float_4 buffer_291[], float_4 
buffer_292[], float_4 buffer_293[], float_4 buffer_294[], float_4 buffer_295[], float_4 
buffer_296[], float_4 buffer_297[], float_4 buffer_298[], float_4 buffer_299[], float_4 
buffer_300[], float_4 buffer_301[], float_4 buffer_302[], float_4 buffer_303[], float_4 
buffer_304[], float_4 buffer_305[], float_4 buffer_306[], float_4 buffer_307[], float_4 
buffer_308[], float_4 buffer_309[], float_4 buffer_310[], float_4 buffer_311[], float_4 
buffer_312[], float_4 buffer_313[], float_4 buffer_314[], float_4 buffer_315[], float_4 
buffer_316[], float_4 buffer_317[], float_4 buffer_318[], float_4 buffer_319[], float_4 
buffer_320[], float_4 buffer_321[], float_4 buffer_322[], float_4 buffer_323[], float_4 
buffer_324[], float_4 buffer_325[], float_4 buffer_326[], float_4 buffer_327[], float_4 
buffer_328[], float_4 buffer_329[], float_4 buffer_330[], float_4 buffer_331[], float_4 
buffer_332[], float_4 buffer_333[], float_4 buffer_334[], float_4 buffer_335[], float_4 
buffer_336[], float_4 buffer_337[], float_4 buffer_338[], float_4 buffer_339[], float_4 
buffer_340[], float_4 buffer_341[], float_4 buffer_342[], float_4 buffer_343[], float_4 
buffer_344[], float_4 buffer_345[], float_4 buffer_346[], float_4 buffer_347[], float_4 
buffer_348[], float_4 buffer_349[], float_4 buffer_350[], float_4 buffer_351[], float_4 
buffer_352[], float_4 buffer_353[], float_4 buffer_354[], float_4 buffer_355[], float_4 
buffer_356[], float_4 buffer_357[], float_4 buffer_358[], float_4 buffer_359[], float_4 
buffer_360[], float_4 buffer_361[], float_4 buffer_362[], float_4 buffer_363[], float_4 
buffer_364[], float_4 buffer_365[], float_4 buffer_366[], float_4 buffer_367[], float_4 
buffer_368[], float_4 buffer_369[], float_4 buffer_370[], float_4 buffer_371[], float_4 
buffer_372[], float_4 buffer_373[], float_4 buffer_374[], float_4 buffer_375[], float_4 
buffer_376[], float_4 buffer_377[], float_4 buffer_378[], float_4 buffer_379[], float_4 
buffer_380[], float_4 buffer_381[], float_4 buffer_382[], float_4 buffer_383[], float_4 
buffer_384[], float_4 buffer_385[], float_4 buffer_386[], float_4 buffer_387[], float_4 
buffer_388[], float_4 buffer_389[], float_4 buffer_390[], float_4 buffer_391[], float_4 
buffer_392[], float_4 buffer_393[], float_4 buffer_394[], float_4 buffer_395[], float_4 
buffer_396[], float_4 buffer_397[], float_4 buffer_398[], float_4 buffer_399[], float_4 
buffer_400[], float_4 buffer_401[], float_4 buffer_402[], float_4 buffer_403[], float_4 
buffer_404[], float_4 buffer_405[], float_4 buffer_406[], float_4 buffer_407[], float_4 
buffer_408[], float_4 buffer_409[], float_4 buffer_410[], float_4 buffer_411[], float_4 
buffer_412[], float_4 buffer_413[], float_4 buffer_414[], float_4 buffer_415[], float_4 
buffer_416[], float_4 buffer_417[], float_4 buffer_418[], float_4 buffer_419[], float_4 
buffer_420[], float_4 buffer_421[], float_4 buffer_422[], float_4 buffer_423[], float_4 
buffer_424[], float_4 buffer_425[], float_4 buffer_426[], float_4 buffer_427[], float_4 
buffer_428[], float_4 buffer_429[], float_4 buffer_430[], float_4 buffer_431[], float_4 
buffer_432[], float_4 buffer_433[], float_4 buffer_434[], float_4 buffer_435[], float_4 
buffer_436[], float_4 buffer_437[], float_4 buffer_438[], float_4 buffer_439[], float_4 
buffer_440[], float_4 buffer_441[], float_4 buffer_442[], float_4 buffer_443[], float_4 
buffer_444[], float_4 buffer_445[], float_4 buffer_446[], float_4 buffer_447[], float_4 
buffer_448[], float_4 buffer_449[], float_4 buffer_450[], float_4 buffer_451[], float_4 
buffer_452[], float_4 buffer_453[], float_4 buffer_454[], float_4 buffer_455[], float_4 
buffer_456[], float_4 buffer_457[], float_4 buffer_458[], float_4 buffer_459[], float_4 
buffer_460[], float_4 buffer_461[], float_4 buffer_462[], float_4 buffer_463[], float_4 
buffer_464[], float_4 buffer_465[], float_4 buffer_466[], float_4 buffer_467[], float_4 
buffer_468[], float_4 buffer_469[], float_4 buffer_470[], float_4 buffer_471[], float_4 
buffer_472[], float_4 buffer_473[], float_4 buffer_474[], float_4 buffer_475[], float_4 
buffer_476[], float_4 buffer_477[], float_4 buffer_478[], float_4 buffer_479[], float_4 
buffer_480[], float_4 buffer_481[], float_4 buffer_482[], float_4 buffer_483[], float_4 
buffer_484[], float_4 buffer_485[], float_4 buffer_486[], float_4 buffer_487[], float_4 
buffer_488[], float_4 buffer_489[], float_4 buffer_490[], float_4 buffer_491[], float_4 
buffer_492[], float_4 buffer_493[], float_4 buffer_494[], float_4 buffer_495[], float_4 
buffer_496[], float_4 buffer_497[], float_4 buffer_498[], float_4 buffer_499[], float_4 
buffer_500[], float_4 buffer_501[], float_4 buffer_502[], float_4 buffer_503[], float_4 
buffer_504[], float_4 buffer_505[], float_4 buffer_506[], float_4 buffer_507[], float_4 
buffer_508[], float_4 buffer_509[], float_4 buffer_510[], float_4 buffer_511[], float_4 
buffer_512[], float_4 buffer_513[], float_4 buffer_514[], float_4 buffer_515[], float_4 
buffer_516[], float_4 buffer_517[], float_4 buffer_518[], float_4 buffer_519[], float_4 
buffer_520[], float_4 buffer_521[], float_4 buffer_522[], float_4 buffer_523[], float_4 
buffer_524[], float_4 buffer_525[], float_4 buffer_526[], float_4 buffer_527[], float_4 
buffer_528[], float_4 buffer_529[], float_4 buffer_530[], float_4 buffer_531[], float_4 
buffer_532[], float_4 buffer_533[], float_4 buffer_534[], float_4 buffer_535[], float_4 
buffer_536[], float_4 buffer_537[], float_4 buffer_538[], float_4 buffer_539[], float_4 
buffer_540[], float_4 buffer_541[], float_4 buffer_542[], float_4 buffer_543[], float_4 
buffer_544[], float_4 buffer_545[], float_4 buffer_546[], float_4 buffer_547[], float_4 
buffer_548[], float_4 buffer_549[], float_4 buffer_550[], float_4 buffer_551[], float_4 
buffer_552[], float_4 buffer_553[], float_4 buffer_554[], float_4 buffer_555[], float_4 
buffer_556[], float_4 buffer_557[], float_4 buffer_558[], float_4 buffer_559[], float_4 
buffer_560[], float_4 buffer_561[], float_4 buffer_562[], float_4 buffer_563[], float_4 
buffer_564[], float_4 buffer_565[], float_4 buffer_566[], float_4 buffer_567[], float_4 
buffer_568[], float_4 buffer_569[], float_4 buffer_570[], float_4 buffer_571[], float_4 
buffer_572[], float_4 buffer_573[], float_4 buffer_574[], float_4 buffer_575[], float_4 
buffer_576[], float_4 buffer_577[], float_4 buffer_578[], float_4 buffer_579[], float_4 
buffer_580[], float_4 buffer_581[], float_4 buffer_582[], float_4 buffer_583[], float_4 
buffer_584[], float_4 buffer_585[], float_4 buffer_586[], float_4 buffer_587[], float_4 
buffer_588[], float_4 buffer_589[], float_4 buffer_590[], float_4 buffer_591[], float_4 
buffer_592[], float_4 buffer_593[], float_4 buffer_594[], float_4 buffer_595[], float_4 
buffer_596[], float_4 buffer_597[], float_4 buffer_598[], float_4 buffer_599[], float_4 
buffer_600[], float_4 buffer_601[], float_4 buffer_602[], float_4 buffer_603[], float_4 
buffer_604[], float_4 buffer_605[], float_4 buffer_606[], float_4 buffer_607[], float_4 
buffer_608[], float_4 buffer_609[], float_4 buffer_610[], float_4 buffer_611[], float_4 
buffer_612[], float_4 buffer_613[], float_4 buffer_614[], float_4 buffer_615[], float_4 
buffer_616[], float_4 buffer_617[], float_4 buffer_618[], float_4 buffer_619[], float_4 
buffer_620[], float_4 buffer_621[], float_4 buffer_622[], float_4 buffer_623[], float_4 
buffer_624[], float_4 buffer_625[], float_4 buffer_626[], float_4 buffer_627[], float_4 
buffer_628[], float_4 buffer_629[], float_4 buffer_630[], float_4 buffer_631[], float_4 
buffer_632[], float_4 buffer_633[], float_4 buffer_634[], float_4 buffer_635[], float_4 
buffer_636[], float_4 buffer_637[], float_4 buffer_638[], float_4 buffer_639[], float_4 
buffer_640[], float_4 buffer_641[], float_4 buffer_642[], float_4 buffer_643[], float_4 
buffer_644[], float_4 buffer_645[], float_4 buffer_646[], float_4 buffer_647[], float_4 
buffer_648[], float_4 buffer_649[], float_4 buffer_650[], float_4 buffer_651[], float_4 
buffer_652[], float_4 buffer_653[], float_4 buffer_654[], float_4 buffer_655[], float_4 
buffer_656[], float_4 buffer_657[], float_4 buffer_658[], float_4 buffer_659[], float_4 
buffer_660[], float_4 buffer_661[], float_4 buffer_662[], float_4 buffer_663[], float_4 
buffer_664[], float_4 buffer_665[], float_4 buffer_666[], float_4 buffer_667[], float_4 
buffer_668[], float_4 buffer_669[], float_4 buffer_670[], float_4 buffer_671[], float_4 
buffer_672[], float_4 buffer_673[], float_4 buffer_674[], float_4 buffer_675[], float_4 
buffer_676[], float_4 buffer_677[], float_4 buffer_678[], float_4 buffer_679[], float_4 
buffer_680[], float_4 buffer_681[], float_4 buffer_682[], float_4 buffer_683[], float_4 
buffer_684[], float_4 buffer_685[], float_4 buffer_686[], float_4 buffer_687[], float_4 
buffer_688[], float_4 buffer_689[], float_4 buffer_690[], float_4 buffer_691[], float_4 
buffer_692[], float_4 buffer_693[], float_4 buffer_694[], float_4 buffer_695[], float_4 
buffer_696[], float_4 buffer_697[], float_4 buffer_698[], float_4 buffer_699[], float_4 
buffer_700[], float_4 buffer_701[], float_4 buffer_702[], float_4 buffer_703[], float_4 
buffer_704[], float_4 buffer_705[], float_4 buffer_706[], float_4 buffer_707[], float_4 
buffer_708[], float_4 buffer_709[], float_4 buffer_710[], float_4 buffer_711[], float_4 
buffer_712[], float_4 buffer_713[], float_4 buffer_714[], float_4 buffer_715[], float_4 
buffer_716[], float_4 buffer_717[], float_4 buffer_718[], float_4 buffer_719[], float_4 
buffer_720[], float_4 buffer_721[], float_4 buffer_722[], float_4 buffer_723[], float_4 
buffer_724[], float_4 buffer_725[], float_4 buffer_726[], float_4 buffer_727[], float_4 
buffer_728[], float_4 buffer_729[], float_4 buffer_730[], float_4 buffer_731[], float_4 
buffer_732[], float_4 buffer_733[], float_4 buffer_734[], float_4 buffer_735[], float_4 
buffer_736[], float_4 buffer_737[], float_4 buffer_738[], float_4 buffer_739[], float_4 
buffer_740[], float_4 buffer_741[], float_4 buffer_742[], float_4 buffer_743[], float_4 
buffer_744[], float_4 buffer_745[], float_4 buffer_746[], float_4 buffer_747[], float_4 
buffer_748[], float_4 buffer_749[], float_4 buffer_750[], float_4 buffer_751[], float_4 
buffer_752[], float_4 buffer_753[], float_4 buffer_754[], float_4 buffer_755[], float_4 
buffer_756[], float_4 buffer_757[], float_4 buffer_758[], float_4 buffer_759[], float_4 
buffer_760[], float_4 buffer_761[], float_4 buffer_762[], float_4 buffer_763[], float_4 
buffer_764[], float_4 buffer_765[], float_4 buffer_766[], float_4 buffer_767[], float_4 
buffer_768[], float_4 buffer_769[], float_4 buffer_770[], float_4 buffer_771[], float_4 
buffer_772[], float_4 buffer_773[], float_4 buffer_774[], float_4 buffer_775[], float_4 
buffer_776[], float_4 buffer_777[], float_4 buffer_778[], float_4 buffer_779[], float_4 
buffer_780[], float_4 buffer_781[], float_4 buffer_782[], float_4 buffer_783[], float_4 
buffer_784[], float_4 buffer_785[], float_4 buffer_786[], float_4 buffer_787[], float_4 
buffer_788[], float_4 buffer_789[], float_4 buffer_790[], float_4 buffer_791[], float_4 
buffer_792[], float_4 buffer_793[], float_4 buffer_794[], float_4 buffer_795[], float_4 
buffer_796[], float_4 buffer_797[], float_4 buffer_798[], float_4 buffer_799[], float_4 
buffer_800[], float_4 buffer_801[], float_4 buffer_802[], float_4 buffer_803[], float_4 
buffer_804[], float_4 buffer_805[], float_4 buffer_806[], float_4 buffer_807[], float_4 
buffer_808[], float_4 buffer_809[], float_4 buffer_810[], float_4 buffer_811[], float_4 
buffer_812[], float_4 buffer_813[], float_4 buffer_814[], float_4 buffer_815[], float_4 
buffer_816[], float_4 buffer_817[], float_4 buffer_818[], float_4 buffer_819[], float_4 
buffer_820[], float_4 buffer_821[], float_4 buffer_822[], float_4 buffer_823[], float_4 
buffer_824[], float_4 buffer_825[], float_4 buffer_826[], float_4 buffer_827[], float_4 
buffer_828[], float_4 buffer_829[], float_4 buffer_830[], float_4 buffer_831[], float_4 
buffer_832[], float_4 buffer_833[], float_4 buffer_834[], float_4 buffer_835[], float_4 
buffer_836[], float_4 buffer_837[], float_4 buffer_838[], float_4 buffer_839[], float_4 
buffer_840[], float_4 buffer_841[], float_4 buffer_842[], float_4 buffer_843[], float_4 
buffer_844[], float_4 buffer_845[], float_4 buffer_846[], float_4 buffer_847[], float_4 
buffer_848[], float_4 buffer_849[], float_4 buffer_850[], float_4 buffer_851[], float_4 
buffer_852[], float_4 buffer_853[], float_4 buffer_854[], float_4 buffer_855[], float_4 
buffer_856[], float_4 buffer_857[], float_4 buffer_858[], float_4 buffer_859[], float_4 
buffer_860[], float_4 buffer_861[], float_4 buffer_862[], float_4 buffer_863[], float_4 
buffer_864[], float_4 buffer_865[], float_4 buffer_866[], float_4 buffer_867[], float_4 
buffer_868[], float_4 buffer_869[], float_4 buffer_870[], float_4 buffer_871[], float_4 
buffer_872[], float_4 buffer_873[], float_4 buffer_874[], float_4 buffer_875[], float_4 
buffer_876[], float_4 buffer_877[], float_4 buffer_878[], float_4 buffer_879[], float_4 
buffer_880[], float_4 buffer_881[], float_4 buffer_882[], float_4 buffer_883[], float_4 
buffer_884[], float_4 buffer_885[], float_4 buffer_886[], float_4 buffer_887[], float_4 
buffer_888[], float_4 buffer_889[], float_4 buffer_890[], float_4 buffer_891[], float_4 
buffer_892[], float_4 buffer_893[], float_4 buffer_894[], float_4 buffer_895[], float_4 
buffer_896[], float_4 buffer_897[], float_4 buffer_898[], float_4 buffer_899[], float_4 
buffer_900[], float_4 buffer_901[], float_4 buffer_902[], float_4 buffer_903[], float_4 
buffer_904[], float_4 buffer_905[], float_4 buffer_906[], float_4 buffer_907[], float_4 
buffer_908[], float_4 buffer_909[], float_4 buffer_910[], float_4 buffer_911[], float_4 
buffer_912[], float_4 buffer_913[], float_4 buffer_914[], float_4 buffer_915[], float_4 
buffer_916[], float_4 buffer_917[], float_4 buffer_918[], float_4 buffer_919[], float_4 
buffer_920[], float_4 buffer_921[], float_4 buffer_922[], float_4 buffer_923[], float_4 
buffer_924[], float_4 buffer_925[], float_4 buffer_926[], float_4 buffer_927[], float_4 
buffer_928[], float_4 buffer_929[], float_4 buffer_930[], float_4 buffer_931[], float_4 
buffer_932[], float_4 buffer_933[], float_4 buffer_934[], float_4 buffer_935[], float_4 
buffer_936[], float_4 buffer_937[], float_4 buffer_938[], float_4 buffer_939[], float_4 
buffer_940[], float_4 buffer_941[], float_4 buffer_942[], float_4 buffer_943[], float_4 
buffer_944[], float_4 buffer_945[], float_4 buffer_946[], float_4 buffer_947[], float_4 
buffer_948[], float_4 buffer_949[], float_4 buffer_950[], float_4 buffer_951[], float_4 
buffer_952[], float_4 buffer_953[], float_4 buffer_954[], float_4 buffer_955[], float_4 
buffer_956[], float_4 buffer_957[], float_4 buffer_958[], float_4 buffer_959[], float_4 
buffer_960[], float_4 buffer_961[], float_4 buffer_962[], float_4 buffer_963[], float_4 
buffer_964[], float_4 buffer_965[], float_4 buffer_966[], float_4 buffer_967[], float_4 
buffer_968[], float_4 buffer_969[], float_4 buffer_970[], float_4 buffer_971[], float_4 
buffer_972[], float_4 buffer_973[], float_4 buffer_974[], float_4 buffer_975[], float_4 
buffer_976[], float_4 buffer_977[], float_4 buffer_978[], float_4 buffer_979[], float_4 
buffer_980[], float_4 buffer_981[], float_4 buffer_982[], float_4 buffer_983[], float_4 
buffer_984[], float_4 buffer_985[], float_4 buffer_986[], float_4 buffer_987[], float_4 
buffer_988[], float_4 buffer_989[], float_4 buffer_990[], float_4 buffer_991[], float_4 
buffer_992[], float_4 buffer_993[], float_4 buffer_994[], float_4 buffer_995[], float_4 
buffer_996[], float_4 buffer_997[], float_4 buffer_998[], float_4 buffer_999[], float_4 
buffer_1000[], float_4 buffer_1001[], float_4 buffer_1002[], float_4 buffer_1003[], 
float_4 buffer_1004[], float_4 buffer_1005[], float_4 buffer_1006[], float_4 
buffer_1007[], float_4 buffer_1008[], float_4 buffer_1009[], float_4 buffer_1010[], 
float_4 buffer_1011[], float_4 buffer_1012[], float_4 buffer_1013[], float_4 
buffer_1014[], float_4 buffer_1015[], float_4 buffer_1016[], float_4 buffer_1017[], 
float_4 buffer_1018[], float_4 buffer_1019[], float_4 buffer_1020[], float_4 
buffer_1021[], const uint32* __restrict__ info, const __grid_constant__ metadata_st 
static_info, const __grid_constant__ scalars_uint32_st scalars_uint32
)

CC'ing @nathanielsimard

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working fusion
Projects
None yet
Development

No branches or pull requests

3 participants