X-Git-Url: http://repo.macrolet.net/gitweb/?a=blobdiff_plain;f=OPTIMIZATIONS;h=b0c8f47fe343d475fa73a9392c955dd31969ca9c;hb=eed9254936fe91e36dd4dbca02c342021917eeb1;hp=99d40ea18241b3e569326c90198055f1cdd8f1df;hpb=37496d2b1c2adb6bd77b2c6c90329af871e97dd5;p=sbcl.git

diff --git a/OPTIMIZATIONS b/OPTIMIZATIONS
index 99d40ea..b0c8f47 100644
--- a/OPTIMIZATIONS
+++ b/OPTIMIZATIONS
@@ -11,9 +11,6 @@
 
 * On X86 I is represented as a tagged integer.
 
-* EQL uses "CMP reg,reg" instead of "CMP reg,im". This causes
-  allocation of an extra register and an extra move.
-
 * Unnecessary move:
   3: SLOT S!11[EDX] {SB-C::VECTOR-LENGTH 1 7} => t23[EAX]
   4: MOVE t23[EAX] => t24[EBX]
@@ -65,11 +62,6 @@ VOP DATA-VECTOR-SET/SIMPLE-STRING V2!14[EDI] t32[EAX] t30[S2]>t33[CL]
 
 * And why two moves?
 --------------------------------------------------------------------------------
-#5
-(loop repeat 1.5)
-
-uses generic arithmetic
---------------------------------------------------------------------------------
 #6
 09:49:05 <jtra> I have found a case in those where suboptimal code is
   generate with nested loops, it might be moderately easy to fix that
@@ -80,7 +72,6 @@ uses generic arithmetic
   memory location for iteration variable
 
 ;;; -*- mode: lisp -*-
-;;; $Id$
 ;;; http://www.bagley.org/~doug/shootout/
 ;;; from Friedrich Dominicus
 
@@ -99,21 +90,14 @@ uses generic arithmetic
                 (incf x)))))))
    (format t "~A~%" x)))
 --------------------------------------------------------------------------------
-#7
-(defun foo (x)
-  (declare (optimize speed (debug 0)))
-  (if (< x 0) x (foo (1- x))))
-
-SBCL generates a full call of FOO (but CMUCL does not).
---------------------------------------------------------------------------------
 #8
 (defun foo (d)
   (declare (optimize (speed 3) (safety 0) (debug 0)))
   (declare (type (double-float 0d0 1d0) d))
   (loop for i fixnum from 1 to 5
-     for x1 double-float = (sin d) ;;; !!!
-     do (loop for j fixnum from 1 to 4
-             sum x1 double-float)))
+        for x1 double-float = (sin d) ;;; !!!
+        do (loop for j fixnum from 1 to 4
+                 sum x1 double-float)))
 
 Without the marked declaration Python will use boxed representation for X1.
 
@@ -158,3 +142,92 @@ It could be optimized to
 
 (if Y were used only once, the current compiler would optimize it)
 --------------------------------------------------------------------------------
+#12
+(typep (truly-the (simple-array * (*)) x) 'simple-vector)
+
+tests lowtag.
+--------------------------------------------------------------------------------
+#13
+FAST-+/FIXNUM and similar should accept unboxed arguments in interests
+of representation selection. Problem: inter-TN dependencies.
+--------------------------------------------------------------------------------
+#14
+The derived type of (/ (THE (DOUBLE-FLOAT (0D0)) X) (THE (DOUBLE-FLOAT
+1D0) Y)) is (DOUBLE-FLOAT 0.0d0). While it might be reasonable, it is
+better to derive (OR (MEMBER 0.0d0) (DOUBLE-FLOAT (0.0d0))).
+--------------------------------------------------------------------------------
+#15
+On the alpha, the system is reluctant to refer directly to a constant bignum,
+preferring to load a large constant through a slow sequence of instructions,
+then cons up a bignum for it:
+
+(LAMBDA (A)
+  (DECLARE (OPTIMIZE (SAFETY 1) (SPEED 3) (DEBUG 1))
+           (TYPE (INTEGER -10000 10000) A)
+           (IGNORABLE A))
+  (CASE A
+    ((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).