arm64: disassemble shifted immediates directly
View Changes

arm64: optimize simd-character-string-utf8-length some more
View Changes

arm64: optimize simd-character-string-utf8-length
View Changes

amr64: encode movi immediates without requiring manual shifting
View Changes

arm64: implement simd-character-string-utf8-length using NEON
View Changes

Speed up output-to-c-string/utf-8/lf
View Changes

Fix interpreted calls to c-string-to-string
View Changes

Don't cons SAPs for sb-alien::c-string-to-string for :utf-8
View Changes

Optimize read-from-c-string/utf-8/lf
View Changes

Optimize sb-thread:barrier for arm64
View Changes

arm64: restore bic, orn disassembly
View Changes

Derive the type of (coerce n `(simple-array ,e (*)))
View Changes

arm64: add uqsub
View Changes

arm64: implement FMOV <xd>, <vn>.D[1]
View Changes</vn></xd>

arm64: better umaxv disassembly
View Changes

arm64: always require vector sizes for simd instructions
View Changes

arm64: remove the remaining s- prefixes
View Changes

Fix do-conset-elements
View Changes

Fix CONSET-ADJOIN and CONSET-UNION
View Changes

Speed up DO-CONSET-ELEMENTS using CTZ if available
View Changes

arm64: unify some neon and ordinary instructions
View Changes

arm64: add neon shl
View Changes

sb-introspect:function-lambda-list: employ sb-ext:unencapsulated-function
View Changes

describe: call unencapsulated-function
View Changes

Don't change :test for subst based on the sequence type
View Changes

Don't cons a new list for (length (intersection a b))
View Changes

Return constant string from NATURALIZE if length is 0
View Changes