Extend tile reduction operations with additional operators#21

Closed

arhik wants to merge 29 commits into

JuliaGPU:mainfrom

arhik:tilereduce

Commits on Jan 16, 2026

intrinsics: extend reduce operations with mul, min, and, or, xor for both float and integer types
arhik
committed
operations: add axis(i) helper for 1-based to 0-based axis conversion
arhik
committed
make axis public
arhik
committed
make new reduce_{ops} public
arhik
committed
reduce ops update and axis convenience
arhik
committed
reduce ops: add wrapper functions and correct identity values via dispatch
arhik
committed
add IntIdentity type for integer reduce operations
arhik
committed
rename IntIdentity to IntegerIdentity for clarity
arhik
committed
fix: remove AbstractFloat constraint from reduce_sum and reduce_max
arhik
committed
use Number constraint for numeric reduce operations
arhik
committed
add signed field to IntegerIdentity for proper signed/unsigned encoding
arhik
committed
remove unused is_reduce kwarg from encode_tagged_int
arhik
committed
rename ReduceIdentity to OperationIdentity
arhik
committed
rename identity types to IdentityOp hierarchy
arhik
committed
fix is_signed to use proper Julia type hierarchy check
arhik
committed
intrinsics: use -one(T) instead of -1 for signed AND identity
arhik
committed
test: restore codegen and types tests, fix reduce_ops reference
arhik
committed
multiline comment mess in reduce_ops.jl
arhik
committed
intrinsics: rename reduce_identity -> operation_identity
arhik
committed
test: fix CPU reference functions for bitwise ops
arhik
committed
bytecode: fix zigzag encoding for signed varint
arhik
committed
reverting zigzag encoding
arhik
committed
bytecode: fix zigzag encoding for signed varint
arhik
committed
bytecode: remove duplicate encode_signed_varint!
arhik
committed
intrinsics: pass signedness to encode_MinIOp! and encode_MaxIOp!
arhik
committed
reverting original encode_signed_varint
arhik
committed
revert comment inside encode_signed_varint
arhik
committed
Fix SLEB128 zigzag encoding for 64-bit and small integer types
arhik
committed
Simplify reduce_ops.jl tests with broadcasting
arhik
committed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Extend tile reduction operations with additional operators#21

Extend tile reduction operations with additional operators#21
arhik wants to merge 29 commits into
JuliaGPU:mainfrom
arhik:tilereduce

Commits on Jan 16, 2026

intrinsics: extend reduce operations with mul, min, and, or, xor for both float and integer types

operations: add axis(i) helper for 1-based to 0-based axis conversion

make axis public

make new reduce_{ops} public

reduce ops update and axis convenience

reduce ops: add wrapper functions and correct identity values via dispatch

add IntIdentity type for integer reduce operations

rename IntIdentity to IntegerIdentity for clarity

fix: remove AbstractFloat constraint from reduce_sum and reduce_max

use Number constraint for numeric reduce operations

add signed field to IntegerIdentity for proper signed/unsigned encoding

remove unused is_reduce kwarg from encode_tagged_int

rename ReduceIdentity to OperationIdentity

rename identity types to IdentityOp hierarchy

fix is_signed to use proper Julia type hierarchy check

intrinsics: use -one(T) instead of -1 for signed AND identity

test: restore codegen and types tests, fix reduce_ops reference

multiline comment mess in reduce_ops.jl

intrinsics: rename reduce_identity -> operation_identity

test: fix CPU reference functions for bitwise ops

bytecode: fix zigzag encoding for signed varint

reverting zigzag encoding

bytecode: fix zigzag encoding for signed varint

bytecode: remove duplicate encode_signed_varint!

intrinsics: pass signedness to encode_MinIOp! and encode_MaxIOp!

reverting original encode_signed_varint

revert comment inside encode_signed_varint

Fix SLEB128 zigzag encoding for 64-bit and small integer types

Simplify reduce_ops.jl tests with broadcasting