X-Git-Url: http://repo.macrolet.net/gitweb/?a=blobdiff_plain;f=OPTIMIZATIONS;h=d8d018f3f164a5a9d57343e495ce1b445627ca77;hb=d04b59670ab69405c4115ea3caac99fd62a4b7ab;hp=7c51f473ac7e0301e123fa41db6094598db835d1;hpb=8f4ef01b8c9930d7dd0a56a96845a6d84ca5774d;p=sbcl.git diff --git a/OPTIMIZATIONS b/OPTIMIZATIONS index 7c51f47..d8d018f 100644 --- a/OPTIMIZATIONS +++ b/OPTIMIZATIONS @@ -62,34 +62,6 @@ VOP DATA-VECTOR-SET/SIMPLE-STRING V2!14[EDI] t32[EAX] t30[S2]>t33[CL] * And why two moves? -------------------------------------------------------------------------------- -#6 -09:49:05 I have found a case in those where suboptimal code is - generate with nested loops, it might be moderately easy to fix that -09:49:28 see - http://www.bagley.org/~doug/shootout/bench/nestedloop/nestedloop.cmucl -09:50:30 if you add declarations to dotimes, generated code is - almost optimal, but most inner loops run out of registers and use - memory location for iteration variable - -;;; -*- mode: lisp -*- -;;; http://www.bagley.org/~doug/shootout/ -;;; from Friedrich Dominicus - -(defun main () - (let ((n (parse-integer (or (car (last extensions:*command-line-strings*)) "1"))) - (x 0)) - (declare (fixnum n) - (fixnum x) - (optimize (speed 3) (debug 0) (safety 0))) - (dotimes (a n) - (dotimes (b n) - (dotimes (c n) - (dotimes (d n) - (dotimes (e n) - (dotimes (f n) - (incf x))))))) - (format t "~A~%" x))) --------------------------------------------------------------------------------- #8 (defun foo (d) (declare (optimize (speed 3) (safety 0) (debug 0))) @@ -169,3 +141,80 @@ then cons up a bignum for it: ((89 125 16) (ASH A (MIN 18 -706))) (T (DPB -3 (BYTE 30 30) -1)))) -------------------------------------------------------------------------------- +#16 +(do ((i 0 (1+ i))) + ((= i (the (integer 0 100) n))) + ...) + +It is commonly expected for Python to derive (FIXNUMP I). (If ``='' is +replaced with ``>='', Python will do.) +-------------------------------------------------------------------------------- +#17 +Type tests for (ARRAY BIT), (ARRAY T) and similar go through full +%TYPEP, even though it is relatively simple to establish the arrayness +of an object and also to obtain the element type of an array. As of +sbcl-0.8.12.30, this affects at least DUMP-OBJECT through +COMPOUND-OBJECT-P, and (LABELS MAYBE-EMIT-MAKE-LOAD-FORMS GROVEL) +through TYPEP UNBOXED-ARRAY, within the compiler itself. +-------------------------------------------------------------------------------- +#18 +(lambda (x) (declare (null x)) (sxhash x)) goes through SYMBOL-HASH +rather than either constant-folding or manipulating NIL-VALUE or +NULL-TN directly. +-------------------------------------------------------------------------------- +#19 + (let ((dx (if (foo) + (list x) + (list y z)))) + (declare (dynamic-extent dx)) + ...) + +DX is not allocated on stack. +-------------------------------------------------------------------------------- +#20 +(defun-with-dx foo (x) + (flet ((make (x) + (let ((l (list nil nil))) + (setf (first l) x) + (setf (second l) (1- x)) + l))) + (let ((l (make x))) + (declare (dynamic-extent l)) + (mapc #'print l)))) + +Result of MAKE is not stack allocated, which means that +stack-allocation of structures is impossible. +-------------------------------------------------------------------------------- +#21 +(defun-with-dx foo () + (let ((dx (list (list 1 2) (list 3 4)))) + (declare (dynamic-extent dx)) + ...)) + +External list in DX is allocated on stack, but internal are not. +-------------------------------------------------------------------------------- +#22 +IR2 does not perform unused code flushing. +-------------------------------------------------------------------------------- +#23 +Python does not know that &REST lists are LISTs (and cannot derive it). +-------------------------------------------------------------------------------- +#24 +a. Iterations on &REST lists, returning them as VALUES could be + rewritten with &MORE vectors. +b. Implement local unknown-values mv-call (useful for fast type checking). +-------------------------------------------------------------------------------- +#26 +SBCL cannot derive upper bound for I and uses generic arithmetic here: + +(defun foo (l) + (declare (vector l)) + (dotimes (i (length l)) + (if (block nil + (map-foo (lambda (x) (if x (return t))) + l)) + t + nil))) + +(So the constraint propagator or a possible future SSA-convertor +should know the connection between an NLE and its CLEANUP.)