Hello!
Attached patch introduces __FP_FRAC_ADDI_4 to improve 32bit soft-fp
code a bit. The effect can be seen in a couple of places, for example
in divtf3 the part of code changes from:
70f: 83 c0 04 add $0x4,%eax
712: 89 84 24 90 00 00 00 mov %eax,0x90(%esp)
719: 83 f8 03 cmp $0x3,%eax
71c: 8b 84 24 94 00 00 00 mov 0x94(%esp),%eax
723: 0f 96 c2 setbe %dl
726: 0f b6 d2 movzbl %dl,%edx
729: 01 d0 add %edx,%eax
72b: 39 c2 cmp %eax,%edx
72d: 89 84 24 94 00 00 00 mov %eax,0x94(%esp)
734: 8b 84 24 98 00 00 00 mov 0x98(%esp),%eax
73b: 0f 97 c2 seta %dl
73e: 0f b6 d2 movzbl %dl,%edx
741: 01 d0 add %edx,%eax
743: 39 c2 cmp %eax,%edx
745: 89 84 24 98 00 00 00 mov %eax,0x98(%esp)
74c: 0f 97 c0 seta %al
74f: 0f b6 c0 movzbl %al,%eax
752: 03 84 24 9c 00 00 00 add 0x9c(%esp),%eax
759: 89 84 24 9c 00 00 00 mov %eax,0x9c(%esp)
to:
71b: 8b b4 24 9c 00 00 00 mov 0x9c(%esp),%esi
722: 8b 8c 24 98 00 00 00 mov 0x98(%esp),%ecx
729: 8b 94 24 94 00 00 00 mov 0x94(%esp),%edx
730: 83 c0 04 add $0x4,%eax
733: 83 d2 00 adc $0x0,%edx
736: 83 d1 00 adc $0x0,%ecx
739: 83 d6 00 adc $0x0,%esi
73c: 89 b4 24 9c 00 00 00 mov %esi,0x9c(%esp)
743: 89 8c 24 98 00 00 00 mov %ecx,0x98(%esp)
74a: 89 94 24 94 00 00 00 mov %edx,0x94(%esp)
751: 89 84 24 90 00 00 00 mov %eax,0x90(%esp)
2013-11-28 Uros Bizjak <ubiz...@gmail.com>
* config/i386/32/sfp-machine.h (__FP_FRAC_ADDI_4): New macro.
Tested on x86_64-pc-linux-gnu {,-m32} and committed to mainline SVN.
Uros.
Index: config/i386/32/sfp-machine.h
===================================================================
--- config/i386/32/sfp-machine.h (revision 205474)
+++ config/i386/32/sfp-machine.h (working copy)
@@ -63,6 +63,16 @@
"g" ((USItype) (y1)), \
"2" ((USItype) (x0)), \
"g" ((USItype) (y0)))
+#define __FP_FRAC_ADDI_4(x3,x2,x1,x0,i) \
+ __asm__ ("add{l} {%4,%3|%3,%4}\n\t" \
+ "adc{l} {$0,%2|%2,0}\n\t" \
+ "adc{l} {$0,%1|%1,0}\n\t" \
+ "adc{l} {$0,%0|%0,0}" \
+ : "+r" ((USItype) (x3)), \
+ "+&r" ((USItype) (x2)), \
+ "+&r" ((USItype) (x1)), \
+ "+&r" ((USItype) (x0)) \
+ : "g" ((USItype) (i)))
#define _FP_MUL_MEAT_S(R,X,Y) \
