Productive, portable, and performant GPU programming in Python.
APACHE-2.0 License
Bot releases are hidden (Show)
Published by yuanming-hu over 4 years ago
Highlights:
ti.core.toggle_advanced_optimization(True/False)
(#927) (by Yuanming Hu)Full changelog:
ti.core.toggle_advanced_optimization(True/False)
(#927) (by Yuanming Hu)frontend_ir.h
(#919) (by Ye Kuang)Published by yuanming-hu over 4 years ago
Highlights:
example/bitmasked.py
(#905) (by 彭于斌)Full changelog:
frontend_ir.h
(#916) (by Ye Kuang)FrontendAtomicStmt
(#907) (by Ye Kuang)current_block
(#908) (by Ye Kuang)Expression::flatten()
(#901) (by Ye Kuang)Published by archibate over 4 years ago
Highlights:
Full changelog:
UnaryOpType::cast
into cast_value
and cast_bits
(#892) (by 彭于斌)has_global_side_effect
to false
for some statements (#898) (by xumingkuan)Ident
alias (#895) (by Ye Kuang)Published by yuanming-hu over 4 years ago
Highlights:
sdf2d.py
(#835) (by 彭于斌)quadtree.py
(#824) (by 彭于斌)ti.init
and support arch=ti.gpu
(#843) (by 彭于斌)with_opengl()
(#864) (by 彭于斌)Full changelog:
with_opengl()
(#864) (by 彭于斌)pbf2d.py
's initialization to use np.float32 (#873) (by Ye Kuang)PyTaichi
(#870) (by Yuxin Wu)ti test -na opengl
to exclude tests on some archs (#830) (by 彭于斌)linearize
even without advanced optimization (#854) (by xumingkuan)test_tensor_reflection.py
(#850) (by xumingkuan)quadtree.py
(#824) (by 彭于斌)ti.init
and support arch=ti.gpu
(#843) (by 彭于斌)advanced_optimization == false
(#842) (by xumingkuan)WhileControlStmt
with non-zero const conditions (by xumingkuan)backends
folder (#818) (by Yuanming Hu)Published by yuanming-hu over 4 years ago
Highlights:
slim_libdevice.bc
shipping on Windows (#820) (by Yuanming Hu)Full changelog:
slim_libdevice.bc
shipping on Windows (#820) (by Yuanming Hu)SNodeAttr
and decouple SNode
from LLVM (#817) (by Yuanming Hu)mpm128
gravity control (#809) (by 彭于斌)Published by yuanming-hu over 4 years ago
Highlights:
pointer
and dynamic
SNodes (#781) (by Ye Kuang)ti
commands other than ti test
(#783) (by Yuanming Hu)Full changelog:
README.md
(#776) (by Yuanming Hu)loop_var
s and print names for loops (#803) (by xumingkuan)ti
commands other than ti test
(#783) (by Yuanming Hu)pointer
and dynamic
SNodes (#781) (by Ye Kuang)Published by yuanming-hu over 4 years ago
Notable changes:
4x4
matrix inverse and determinant (#763) (by KLozes)ti test --arch ...
(#764) (by 彭于斌)taichi-nightly
to taichi
(#762) (by Yuanming Hu)Full changelog:
TI_GDB_TRIGGER
environment variable (#766) (by 彭于斌)ti test
(#774) (by Yuanming Hu)README.md
(#767) (by Yuanming Hu)ti test --arch ...
(#764) (by 彭于斌)taichi-nightly
to taichi
(#762) (by Yuanming Hu)Published by yuanming-hu over 4 years ago
Notable changes:
taichi-nightly
now covers CUDA 10.X on Windows and Linux (#756) (by Yuanming Hu)game_of_life.py
(#741) (by 彭于斌)examples/regression.py
(#757) (by Quan Wang)ti.GUI.circles
(#755) (by Yuanming Hu)continue
on all backends (#716) (by Ye Kuang)ti.random()
on Metal (#710) (by Ye Kuang)Full changelog:
taichi-nightly
now covers CUDA 10.X on Windows and Linux (#756) (by Yuanming Hu)examples/regression.py
(#757) (by Quan Wang)irpass::analysis
(#754) (by xumingkuan)ti.GUI.circles
(#755) (by Yuanming Hu)syntax.rst
to include ti.sqrt
, ti.asin
, ti.acos
and x ** y
(#753) (by Quan Wang)ti test
to test single cpp file and no cpp test when testing python(s) (#724) (by 彭于斌)check_opengl_error
to prevent potential segfaults (#728) (by 彭于斌)game_of_life.py
(#741) (by 彭于斌)verify
pass to find out illegal IRs, and remove OffloadedStmt::begin_stmt/end_stmt (#731) (by xumingkuan)ti
header message (#715) (by Ye Kuang)compile_to_offloads()
in codegen (#738) (by Ye Kuang)make_adjoint
(#734) (by Yuanming Hu)[format]
included as substrings in commit messages (#725) (by 彭于斌)no_gc
in opengl_codegen.cpp
(#723) (by Ye Kuang)continue
on all backends (#716) (by Ye Kuang)Alloca
s in the constructors of LocalAddress and LocalStoreStmt (by xumingkuan)test_struct_for_branching
run on archs with pointer
(#712) (by Ye Kuang)ti.random()
on Metal (#710) (by Ye Kuang)listgen
for leaf Snode (#699) (by Ye Kuang)taichi/codegen/codegen_llvm.cpp
and outline class member definitions (#702) (by Taichi Gardener)listgen
kernels (#682) (by Ye Kuang)llvm::Value *Stmt::value
(#686) (by Yuanming Hu)Stmt::adjoint
(#685) (by Yuanming Hu)Published by yuanming-hu over 4 years ago
Notable changes:
ti.static(ti.grouped(ti.ndrange(...)))
syntax checker false positive (#680) (by Yuanming Hu)ti test
now supports -t/--threads
for specifying number of testing threads (#674) (by Yuanming Hu)Full changelog:
ti test
now supports -t/--threads
for specifying number of testing threads (#674) (by Yuanming Hu)ti.static(ti.grouped(ti.ndrange(...)))
syntax checker false positive (#680) (by Yuanming Hu)Published by yuanming-hu over 4 years ago
Notable changes:
bitmasked
as the leaf block structure for 1x1x1
masks (#676) (by Yuanming Hu)bitmasked
on Metal (#661) (by Ye Kuang)Full changelog:
misc/make_changelog.py
for automatically generating changelogs (#679) (by Yuanming Hu)bitmasked
as the leaf block structure for 1x1x1
masks (#676) (by Yuanming Hu)bitmasked
on Metal! (#661) (by Ye Kuang)Published by yuanming-hu over 4 years ago
Changes that are visible to users:
Expr.copy_from
(by Yuanming Hu)ti.Vector.unit
to generate unit vectors (by Yuanming Hu)a = ti.static(a_very_long_variable)
for easy aliasing [doc] (#587) (by 彭于斌 and KLozes)ti.atomic_min
, ti.atomic_max
, ti.atomic_bit_or
, ti.atomic_bit_and
, ti.atomic_bit_xor
(CPU and CUDA by KLozes, OpenGL by 彭于斌, Metal by Ye Kuang)ti format
now cover all files from upstream/master to the working tree (#629) (by Ye Kuang)ti test
now uses argparse
for better customizability (#601) (by 彭于斌)examples/mgpcg.py
(#573) (by KLozes)examples/sdf_renderer.py
(by Yuanming Hu)examples/mgpcg_advanced.py
(#573) (by Yuanming Hu)All changes:
ti format
cover all files from upstream/master to the working tree (#629) (by Ye Kuang)ti format
(#616) (by Yuanming Hu)ti test
in taichi/main.py to implement #600 (#601) (by 彭于斌)least_pot_bound
in case of negative snode size (#567) (by xumingkuan)