Reorganisation of the source tree

[ghc-hetmet.git] / rts / gmp / mpn / pa64w / umul_ppmm.S

diff --git a/rts/gmp/mpn/pa64w/umul_ppmm.S b/rts/gmp/mpn/pa64w/umul_ppmm.S
new file mode 100644 (file)
index 0000000..d9fb92b
--- /dev/null
+++ b/rts/gmp/mpn/pa64w/umul_ppmm.S
@@ -0,0 +1,72 @@
+; Copyright (C) 1999, 2000 Free Software Foundation, Inc.
+
+; This file is part of the GNU MP Library.
+
+; The GNU MP Library is free software; you can redistribute it and/or modify
+; it under the terms of the GNU Lesser General Public License as published by
+; the Free Software Foundation; either version 2.1 of the License, or (at your
+; option) any later version.
+
+; The GNU MP Library is distributed in the hope that it will be useful, but
+; WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+; or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
+; License for more details.
+
+; You should have received a copy of the GNU Lesser General Public License
+; along with the GNU MP Library; see the file COPYING.LIB.  If not, write to
+; the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
+; MA 02111-1307, USA.
+
+#define p0     %r28
+#define p1     %r29
+#define t32    %r19
+#define t0     %r20
+#define t1     %r21
+#define x      %r22
+#define m0     %r23
+#define m1     %r24
+       .level  2.0w
+       .code
+       .export __gmpn_umul_ppmm,entry
+__gmpn_umul_ppmm
+       .proc
+       .callinfo frame=128,no_calls
+       .entry
+       ldo             128(%r30),%r30
+       std             %r26,-64(%r30)
+       std             %r25,-56(%r30)
+
+       copy            %r24,%r31
+
+        fldd           -64(%r30),%fr4
+        fldd           -56(%r30),%fr5
+
+       xmpyu           %fr5R,%fr4R,%fr6
+       fstd            %fr6,-128(%r30)
+       xmpyu           %fr5R,%fr4L,%fr7
+       fstd            %fr7,-120(%r30)
+       xmpyu           %fr5L,%fr4R,%fr8
+       fstd            %fr8,-112(%r30)
+       xmpyu           %fr5L,%fr4L,%fr9
+       fstd            %fr9,-104(%r30)
+
+       depdi,z         1,31,1,t32              ; t32 = 2^32
+
+       ldd             -128(%r30),p0           ; lo = low 64 bit of product
+       ldd             -120(%r30),m0           ; m0 = mid0 64 bit of product
+       ldd             -112(%r30),m1           ; m1 = mid1 64 bit of product
+       ldd             -104(%r30),p1           ; hi = high 64 bit of product
+
+       add,l,*nuv      m0,m1,x                 ; x = m1+m0
+        add,l          t32,p1,p1               ; propagate carry to mid of p1
+       depd,z          x,31,32,t0              ; lo32(m1+m0)
+       add             t0,p0,p0
+       extrd,u         x,31,32,t1              ; hi32(m1+m0)
+       add,dc          t1,p1,p1
+
+       std             p0,0(%r31)              ; store low half of product
+       copy            p1,%r28                 ; return high half of product
+       bve             (%r2)
+       .exit
+       ldo             -128(%r30),%r30
+       .procend