X-Git-Url: http://git.megacz.com/?a=blobdiff_plain;f=ghc%2Fdriver%2Fmangler%2Fghc-asm.lprl;h=760175a5751c22f47fe5e305db24f1ccec8af787;hb=6f917d9600e7e5ba63a33f4079bcbc6ebbdb10fb;hp=cd142dbad32184f472ecb2371aab1730d2acf38d;hpb=4302b12e6fd876a190ce6091e6ce14dbeb15bc00;p=ghc-hetmet.git

diff --git a/ghc/driver/mangler/ghc-asm.lprl b/ghc/driver/mangler/ghc-asm.lprl
index cd142db..760175a 100644
--- a/ghc/driver/mangler/ghc-asm.lprl
+++ b/ghc/driver/mangler/ghc-asm.lprl
@@ -160,7 +160,7 @@ sub init_TARGET_STUFF {
     $T_HDR_vector   = "\.text\n\t\.align 2\n"; # NB: requires padding
 
     #--------------------------------------------------------#
-    } elsif ( $TargetPlatform =~ /^i386-.*-(solaris2|linux|gnu|freebsd|netbsd|openbsd)$/ ) {
+    } elsif ( $TargetPlatform =~ /^i386-.*-(solaris2|linux|gnu|freebsd|netbsd|openbsd|kfreebsdgnu)$/ ) {
 
     $T_STABBY	    = 0; # 1 iff .stab things (usually if a.out format)
     $T_US	    = ''; # _ if symbols have an underscore on the front
@@ -400,8 +400,8 @@ sub init_TARGET_STUFF {
     $T_CONST_LBL    = '^\.LLC(\d+):$'; # regexp for what such a lbl looks like
     $T_POST_LBL	    = ':';
 
-    $T_MOVE_DIRVS   = '^((\s+\.align\s+\d+|\s+\.proc\s+\d+|\s+\.global\s+\S+|\.text|\.data|\.stab.*|\s*\.section.*|\s+\.type.*|\s+\.size.*)\n)';
-    $T_COPY_DIRVS   = '\.(global|proc|stab)';
+    $T_MOVE_DIRVS   =  '^((\s+\.align\s+\d+|\s+\.proc\s+\d+|\s+\.global\s+\S+|\s+\.local\s+\S+|\.text|\.data|\.stab.*|\s*\.section.*|\s+\.type.*|\s+\.size.*)\n)';
+    $T_COPY_DIRVS   = '\.(global|local|proc|stab)';
 
     $T_DOT_WORD	    = '\.(long|word|byte|half|skip|uahalf|uaword)';
     $T_DOT_GLOBAL   = '^\t\.global';
@@ -822,23 +822,27 @@ sub mangle_asm {
 			}
 		    }
 
-		    $p =~ s/^\tpushl\s+\%edi\n//;
-		    $p =~ s/^\tpushl\s+\%esi\n//;
-		    $p =~ s/^\tpushl\s+\%ebx\n//;
-		    $p =~ s/^\tmovl\s+\%esi,\s*\d*\(\%esp\)\n//;
-		    $p =~ s/^\tmovl\s+\%edi,\s*\d*\(\%esp\)\n//;
+		# gcc 3.4.3 puts this kind of stuff in the prologue, eg.
+		# when compiling PrimOps.cmm with -optc-O2:
+		#        xorl    %ecx, %ecx
+		#        xorl    %edx, %edx
+		#        movl    %ecx, 16(%esp)
+		#        movl    %edx, 20(%esp)
+		# but then the code of the function doesn't assume
+		# anything about the contnets of these stack locations.
+		# I think it's to do with the use of inline functions for
+		# PK_Word64() and friends, where gcc is initialising the
+		# contents of the struct to zero, and failing to optimise
+		# away the initialisation.  Let's live dangerously and
+		# discard these initalisations.
+
+		    $p =~ s/^\tpushl\s+\%e(di|si|bx)\n//g;
+		    $p =~ s/^\txorl\s+\%e(ax|cx|dx),\s*\%e(ax|cx|dx)\n//g;
+		    $p =~ s/^\tmovl\s+\%e(ax|cx|dx|si|di),\s*\d*\(\%esp\)\n//g;
+		    $p =~ s/^\tmovl\s+\$\d+,\s*\d*\(\%esp\)\n//g;
 		    $p =~ s/^\tsubl\s+\$\d+,\s*\%esp\n//;
                     $p =~ s/^\tmovl\s+\$\d+,\s*\%eax\n\tcall\s+__alloca\n// if ($TargetPlatform =~ /^.*-(cygwin32|mingw32)/);
 
-		    # GCC 3.1 is in the habit of adding spurious writes to the
-		    # stack in the prologue.  Just to be on the safe side,
-		    # chuck these over the fence into the main code.
-		    while ($p =~ /^\tmovl\s+\$\d+,\s*\d*\(\%esp\)\n/) {
-			  # print "Spurious instruction: $&";
-			  $p = $` . $';
-			  $r = $& . $r;
-		    }
-
                     if ($TargetPlatform =~ /^i386-apple-darwin/) {
                         $pcrel_label = $p;
                         $pcrel_label =~ s/(.|\n)*^(\"?L\d+\$pb\"?):\n(.|\n)*/$2/ or $pcrel_label = "";
@@ -1430,12 +1434,25 @@ sub hppa_mash_prologue { # OK, epilogue, too
 sub print_doctored {
     local($_, $need_fallthru_patch) = @_;
 
+    if ( $TargetPlatform =~ /^x86_64-/ ) {
+	    # Catch things like
+	    #	
+	    #    movq -4(%ebp), %rax
+	    #    jmp  *%rax
+	    # 
+	    # and optimise:
+	    #
+	    s/^\tmovq\s+(-?\d*\(\%r(bx|bp|13)\)),\s*(\%r(ax|cx|dx|10|11))\n\tjmp\s+\*\3/\tjmp\t\*$1/g;
+	    s/^\tmovl\s+\$${T_US}(.*),\s*(\%e(ax|cx|si|di))\n\tjmp\s+\*\%r\3/\tjmp\t$T_US$1/g;
+    }
+
     if ( $TargetPlatform !~ /^i386-/ 
       || ! /^\t[a-z]/  # no instructions in here, apparently
       || /^${T_US}__stginit_[A-Za-z0-9_]+${T_POST_LBL}/) {
 	print OUTASM $_;
 	return;
     }
+
     # OK, must do some x86 **HACKING**
 
     local($entry_patch)	= '';