mirror of
https://github.com/exaloop/codon.git
synced 2025-06-03 15:03:52 +08:00
* Add nvptx pass * Fix spaces * Don't change name * Add runtime support * Add init call * Add more runtime functions * Add launch function * Add intrinsics * Fix codegen * Run GPU pass between general opt passes * Set data layout * Create context * Link libdevice * Add function remapping * Fix linkage * Fix libdevice link * Fix linking * Fix personality * Fix linking * Fix linking * Fix linking * Add internalize pass * Add more math conversions * Add more re-mappings * Fix conversions * Fix __str__ * Add decorator attribute for any decorator * Update kernel decorator * Fix kernel decorator * Fix kernel decorator * Fix kernel decorator * Fix kernel decorator * Remove old decorator * Fix pointer calc * Fix fill-in codegen * Fix linkage * Add comment * Update list conversion * Add more conversions * Add dict and set conversions * Add float32 type to IR/LLVM * Add float32 * Add float32 stdlib * Keep required global values in PTX module * Fix PTX module pruning * Fix malloc * Set will-return * Fix name cleanup * Fix access * Fix name cleanup * Fix function renaming * Update dimension API * Fix args * Clean up API * Move GPU transformations to end of opt pipeline * Fix alloc replacements * Fix naming * Target PTX 4.2 * Fix global renaming * Fix early return in static blocks; Add __realized__ function * Format * Add __llvm_name__ for functions * Add vector type to IR * SIMD support [wip] * Update kernel naming * Fix early returns; Fix SIMD calls * Fix kernel naming * Fix IR matcher * Remove module print * Update realloc * Add overloads for 32-bit float math ops * Add gpu.Pointer type for working with raw pointers * Add float32 conversion * Add to_gpu and from_gpu * clang-format * Add f32 reduction support to OpenMP * Fix automatic GPU class conversions * Fix conversion functions * Fix conversions * Rename self * Fix tuple conversion * Fix conversions * Fix conversions * Update PTX filename * Fix filename * Add raw function * Add GPU docs * Allow nested object conversions * Add tests (WIP) * Update SIMD * Add staticrange and statictuple loop support * SIMD updates * Add new Vec constructors * Fix UInt conversion * Fix size-0 allocs * Add more tests * Add matmul test * Rename gpu test file * Add more tests * Add alloc cache * Fix object_to_gpu * Fix frees * Fix str conversion * Fix set conversion * Fix conversions * Fix class conversion * Fix str conversion * Fix byte conversion * Fix list conversion * Fix pointer conversions * Fix conversions * Fix conversions * Update tests * Fix conversions * Fix tuple conversion * Fix tuple conversion * Fix auto conversions * Fix conversion * Fix magics * Update tests * Support GPU in JIT mode * Fix GPU+JIT * Fix kernel filename in JIT mode * Add __static_print__; Add earlyDefines; Various domination bugfixes; SimplifyContext RAII base handling * Fix global static handling * Fix float32 tests * FIx gpu module * Support OpenMP "collapse" option * Add more collapse tests * Capture generics and statics * TraitVar handling * Python exceptions / isinstance [wip; no_ci] * clang-format * Add list comparison operators * Support empty raise in IR * Add dict 'or' operator * Fix repr * Add copy module * Fix spacing * Use sm_30 * Python exceptions * TypeTrait support; Fix defaultDict * Fix earlyDefines * Add defaultdict * clang-format * Fix invalid canonicalizations * Fix empty raise * Fix copyright * Add Python numerics option * Support py-numerics in math module * Update docs * Add static Python division / modulus * Add static py numerics tests * Fix staticrange/tuple; Add KwTuple.__getitem__ * clang-format * Add gpu parameter to par * Fix globals * Don't init loop vars on loop collapse * Add par-gpu tests * Update gpu docs * Fix isinstance check * Remove invalid test * Add -libdevice to set custom path [skip ci] * Add release notes; bump version [skip ci] * Add libdevice docs [skip ci] Co-authored-by: Ibrahim Numanagić <ibrahimpasa@gmail.com>
785 lines
7.3 KiB
Python
785 lines
7.3 KiB
Python
# (c) 2022 Exaloop Inc. All rights reserved.
|
|
|
|
# runtime functions
|
|
from C import seq_print(str)
|
|
from C import seq_print_full(str, cobj)
|
|
|
|
|
|
@pure
|
|
@C
|
|
def seq_strdup(a: cobj) -> str:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def seq_stdin() -> cobj:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def seq_stdout() -> cobj:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def seq_stderr() -> cobj:
|
|
pass
|
|
|
|
|
|
@no_side_effect
|
|
@C
|
|
def seq_env() -> Ptr[cobj]:
|
|
pass
|
|
|
|
|
|
@no_side_effect
|
|
@C
|
|
def seq_time() -> int:
|
|
pass
|
|
|
|
|
|
@no_side_effect
|
|
@C
|
|
def seq_time_monotonic() -> int:
|
|
pass
|
|
|
|
|
|
@no_side_effect
|
|
@C
|
|
def seq_time_highres() -> int:
|
|
pass
|
|
|
|
|
|
@no_side_effect
|
|
@C
|
|
def seq_localtime(a: int, b: cobj) -> bool:
|
|
pass
|
|
|
|
|
|
@no_side_effect
|
|
@C
|
|
def seq_gmtime(a: int, b: cobj) -> bool:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def seq_mktime(a: cobj) -> int:
|
|
pass
|
|
|
|
|
|
from C import seq_sleep(float)
|
|
|
|
|
|
@pure
|
|
@C
|
|
def seq_pid() -> int:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def seq_lock_new() -> cobj:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def seq_lock_acquire(a: cobj, b: bool, c: float) -> bool:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def seq_lock_release(a: cobj) -> None:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def seq_rlock_new() -> cobj:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def seq_rlock_acquire(a: cobj, b: bool, c: float) -> bool:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def seq_rlock_release(a: cobj) -> None:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def seq_i32_to_float(a: i32) -> float:
|
|
pass
|
|
|
|
|
|
# <ctype.h>
|
|
@pure
|
|
@C
|
|
def isdigit(a: int) -> int:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def isspace(a: int) -> int:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def isupper(a: int) -> int:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def islower(a: int) -> int:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def toupper(a: int) -> int:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def tolower(a: int) -> int:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def isalnum(a: int) -> int:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def isalpha(a: int) -> int:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def istitle(a: int) -> int:
|
|
pass
|
|
|
|
|
|
# <math.h>
|
|
@pure
|
|
@C
|
|
def ceil(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def floor(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def fabs(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def fmod(a: float, b: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def exp(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def expm1(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def ldexp(a: float, b: i32) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def log(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def log2(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def log10(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def sqrt(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def pow(a: float, b: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def round(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def acos(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def asin(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def atan(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def atan2(a: float, b: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def cos(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def sin(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def tan(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def cosh(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def sinh(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def tanh(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def acosh(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def asinh(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def atanh(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def copysign(a: float, b: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def log1p(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def trunc(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def log2(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def erf(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def erfc(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def tgamma(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def lgamma(a: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def remainder(a: float, b: float) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def hypot(a: float, b: float) -> float:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def frexp(a: float, b: Ptr[Int[32]]) -> float:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def modf(a: float, b: Ptr[float]) -> float:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def ceilf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def floorf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def fabsf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def fmodf(a: float32, b: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def expf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def expm1f(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def ldexpf(a: float32, b: i32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def logf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def log2f(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def log10f(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def sqrtf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def powf(a: float32, b: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def roundf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def acosf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def asinf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def atanf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def atan2f(a: float32, b: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def cosf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def sinf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def tanf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def coshf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def sinhf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def tanhf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def acoshf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def asinhf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def atanhf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def copysignf(a: float32, b: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def log1pf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def truncf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def log2f(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def erff(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def erfcf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def tgammaf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def lgammaf(a: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def remainderf(a: float32, b: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def hypotf(a: float32, b: float32) -> float32:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def frexpf(a: float32, b: Ptr[Int[32]]) -> float32:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def modff(a: float32, b: Ptr[float32]) -> float32:
|
|
pass
|
|
|
|
|
|
# <stdio.h>
|
|
@pure
|
|
@C
|
|
def ferror(a: cobj) -> i32:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def fgetc(a: cobj) -> i32:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def fopen(a: cobj, b: cobj) -> cobj:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def fdopen(a: int, b: cobj) -> cobj:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def fclose(a: cobj) -> int:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def fread(a: cobj, b: int, c: int, d: cobj) -> int:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def fwrite(a: cobj, b: int, c: int, d: cobj) -> int:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def ftell(a: cobj) -> int:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def fseek(a: cobj, b: int, c: i32) -> i32:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def fgets(a: cobj, b: int, c: cobj) -> cobj:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def fflush(a: cobj) -> None:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def getline(a: Ptr[cobj], b: Ptr[int], c: cobj) -> int:
|
|
pass
|
|
|
|
|
|
# <stdlib.h>
|
|
from C import exit(int)
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def system(a: cobj) -> int:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def free(a: cobj) -> None:
|
|
pass
|
|
|
|
|
|
@pure
|
|
@C
|
|
def atoi(a: cobj) -> int:
|
|
pass
|
|
|
|
|
|
# <zlib.h>
|
|
@nocapture
|
|
@C
|
|
def gzopen(a: cobj, b: cobj) -> cobj:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def gzerror(a: cobj, b: Ptr[i32]) -> cobj:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def gzgetc(a: cobj) -> i32:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def gzgets(a: cobj, b: cobj, c: i32) -> cobj:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def gzclose(a: cobj) -> int:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def gzread(a: cobj, b: cobj, c: u32) -> i32:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def gzwrite(a: cobj, b: cobj, c: u32) -> i32:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def gztell(a: cobj) -> int:
|
|
pass
|
|
|
|
|
|
@nocapture
|
|
@C
|
|
def gzseek(a: cobj, b: int, c: i32) -> int:
|
|
pass
|