resolve conflicts

2 files changed, 99 insertions, 22 deletions

diff --git a/src/lib/libcrypto/bn/asm/bn-586.pl b/src/lib/libcrypto/bn/asm/bn-586.pl
index c4de4a2bee..26c2685a72 100644
--- a/src/lib/libcrypto/bn/asm/bn-586.pl
+++ b/src/lib/libcrypto/bn/asm/bn-586.pl
@@ -5,13 +5,18 @@ require "x86asm.pl";
 
 &asm_init($ARGV[0],$0);
 
+$sse2=0;
+for (@ARGV) { $sse2=1 if (/-DOPENSSL_IA32_SSE2/); }
+
+&external_label("OPENSSL_ia32cap_P") if ($sse2);
+
 &bn_mul_add_words("bn_mul_add_words");
 &bn_mul_words("bn_mul_words");
 &bn_sqr_words("bn_sqr_words");
 &bn_div_words("bn_div_words");
 &bn_add_words("bn_add_words");
 &bn_sub_words("bn_sub_words");
-#&bn_sub_part_words("bn_sub_part_words");
+&bn_sub_part_words("bn_sub_part_words");
 
 &asm_finish();
 
@@ -19,7 +24,7 @@ sub bn_mul_add_words
         {
         local($name)=@_;
 
-        &function_begin($name,"");
+        &function_begin($name,$sse2?"EXTRN\t_OPENSSL_ia32cap_P:DWORD":"");
 
         &comment("");
         $Low="eax";
@@ -42,6 +47,83 @@ sub bn_mul_add_words
 
         &jz(&label("maw_finish"));
 
+        if ($sse2) {
+                &picmeup("eax","OPENSSL_ia32cap_P");
+                &bt(&DWP(0,"eax"),26);
+                &jnc(&label("maw_loop"));
+
+                &movd("mm0",$w);                # mm0 = w
+                &pxor("mm1","mm1");             # mm1 = carry_in
+
+                &set_label("maw_sse2_loop",0);
+                &movd("mm3",&DWP(0,$r,"",0));   # mm3 = r[0]
+                &paddq("mm1","mm3");            # mm1 = carry_in + r[0]
+                &movd("mm2",&DWP(0,$a,"",0));   # mm2 = a[0]
+                &pmuludq("mm2","mm0");          # mm2 = w*a[0]
+                &movd("mm4",&DWP(4,$a,"",0));   # mm4 = a[1]
+                &pmuludq("mm4","mm0");          # mm4 = w*a[1]
+                &movd("mm6",&DWP(8,$a,"",0));   # mm6 = a[2]
+                &pmuludq("mm6","mm0");          # mm6 = w*a[2]
+                &movd("mm7",&DWP(12,$a,"",0));  # mm7 = a[3]
+                &pmuludq("mm7","mm0");          # mm7 = w*a[3]
+                &paddq("mm1","mm2");            # mm1 = carry_in + r[0] + w*a[0]
+                &movd("mm3",&DWP(4,$r,"",0));   # mm3 = r[1]
+                &paddq("mm3","mm4");            # mm3 = r[1] + w*a[1]
+                &movd("mm5",&DWP(8,$r,"",0));   # mm5 = r[2]
+                &paddq("mm5","mm6");            # mm5 = r[2] + w*a[2]
+                &movd("mm4",&DWP(12,$r,"",0));  # mm4 = r[3]
+                &paddq("mm7","mm4");            # mm7 = r[3] + w*a[3]
+                &movd(&DWP(0,$r,"",0),"mm1");
+                &movd("mm2",&DWP(16,$a,"",0));  # mm2 = a[4]
+                &pmuludq("mm2","mm0");          # mm2 = w*a[4]
+                &psrlq("mm1",32);               # mm1 = carry0
+                &movd("mm4",&DWP(20,$a,"",0));  # mm4 = a[5]
+                &pmuludq("mm4","mm0");          # mm4 = w*a[5]
+                &paddq("mm1","mm3");            # mm1 = carry0 + r[1] + w*a[1]
+                &movd("mm6",&DWP(24,$a,"",0));  # mm6 = a[6]
+                &pmuludq("mm6","mm0");          # mm6 = w*a[6]
+                &movd(&DWP(4,$r,"",0),"mm1");
+                &psrlq("mm1",32);               # mm1 = carry1
+                &movd("mm3",&DWP(28,$a,"",0));  # mm3 = a[7]
+                &add($a,32);
+                &pmuludq("mm3","mm0");          # mm3 = w*a[7]
+                &paddq("mm1","mm5");            # mm1 = carry1 + r[2] + w*a[2]
+                &movd("mm5",&DWP(16,$r,"",0));  # mm5 = r[4]
+                &paddq("mm2","mm5");            # mm2 = r[4] + w*a[4]
+                &movd(&DWP(8,$r,"",0),"mm1");
+                &psrlq("mm1",32);               # mm1 = carry2
+                &paddq("mm1","mm7");            # mm1 = carry2 + r[3] + w*a[3]
+                &movd("mm5",&DWP(20,$r,"",0));  # mm5 = r[5]
+                &paddq("mm4","mm5");            # mm4 = r[5] + w*a[5]
+                &movd(&DWP(12,$r,"",0),"mm1");
+                &psrlq("mm1",32);               # mm1 = carry3
+                &paddq("mm1","mm2");            # mm1 = carry3 + r[4] + w*a[4]
+                &movd("mm5",&DWP(24,$r,"",0));  # mm5 = r[6]
+                &paddq("mm6","mm5");            # mm6 = r[6] + w*a[6]
+                &movd(&DWP(16,$r,"",0),"mm1");
+                &psrlq("mm1",32);               # mm1 = carry4
+                &paddq("mm1","mm4");            # mm1 = carry4 + r[5] + w*a[5]
+                &movd("mm5",&DWP(28,$r,"",0));  # mm5 = r[7]
+                &paddq("mm3","mm5");            # mm3 = r[7] + w*a[7]
+                &movd(&DWP(20,$r,"",0),"mm1");
+                &psrlq("mm1",32);               # mm1 = carry5
+                &paddq("mm1","mm6");            # mm1 = carry5 + r[6] + w*a[6]
+                &movd(&DWP(24,$r,"",0),"mm1");
+                &psrlq("mm1",32);               # mm1 = carry6
+                &paddq("mm1","mm3");            # mm1 = carry6 + r[7] + w*a[7]
+                &movd(&DWP(28,$r,"",0),"mm1");
+                &add($r,32);
+                &psrlq("mm1",32);               # mm1 = carry_out
+
+                &sub("ecx",8);
+                &jnz(&label("maw_sse2_loop"));
+
+                &movd($c,"mm1");                # c = carry_out
+                &emms();
+
+                &jmp(&label("maw_finish"));
+        }
+
         &set_label("maw_loop",0);
 
         &mov(&swtmp(0),"ecx");  #
diff --git a/src/lib/libcrypto/bn/asm/ia64.S b/src/lib/libcrypto/bn/asm/ia64.S
index 7b82b820e6..951abc53ea 100644
--- a/src/lib/libcrypto/bn/asm/ia64.S
+++ b/src/lib/libcrypto/bn/asm/ia64.S
@@ -171,21 +171,21 @@
 .skip   32      // makes the loop body aligned at 64-byte boundary
 bn_add_words:
         .prologue
-        .fframe 0
         .save   ar.pfs,r2
 { .mii; alloc           r2=ar.pfs,4,12,0,16
         cmp4.le         p6,p0=r35,r0    };;
 { .mfb; mov             r8=r0                   // return value
 (p6)    br.ret.spnt.many        b0      };;
 
-        .save   ar.lc,r3
 { .mib; sub             r10=r35,r0,1
+        .save   ar.lc,r3
         mov             r3=ar.lc
         brp.loop.imp    .L_bn_add_words_ctop,.L_bn_add_words_cend-16
                                         }
-        .body
 { .mib; ADDP            r14=0,r32               // rp
+        .save   pr,r9
         mov             r9=pr           };;
+        .body
 { .mii; ADDP            r15=0,r33               // ap
         mov             ar.lc=r10
         mov             ar.ec=6         }
@@ -224,21 +224,21 @@ bn_add_words:
 .skip   32      // makes the loop body aligned at 64-byte boundary
 bn_sub_words:
         .prologue
-        .fframe 0
         .save   ar.pfs,r2
 { .mii; alloc           r2=ar.pfs,4,12,0,16
         cmp4.le         p6,p0=r35,r0    };;
 { .mfb; mov             r8=r0                   // return value
 (p6)    br.ret.spnt.many        b0      };;
 
-        .save   ar.lc,r3
 { .mib; sub             r10=r35,r0,1
+        .save   ar.lc,r3
         mov             r3=ar.lc
         brp.loop.imp    .L_bn_sub_words_ctop,.L_bn_sub_words_cend-16
                                         }
-        .body
 { .mib; ADDP            r14=0,r32               // rp
+        .save   pr,r9
         mov             r9=pr           };;
+        .body
 { .mii; ADDP            r15=0,r33               // ap
         mov             ar.lc=r10
         mov             ar.ec=6         }
@@ -283,7 +283,6 @@ bn_sub_words:
 .skip   32      // makes the loop body aligned at 64-byte boundary
 bn_mul_words:
         .prologue
-        .fframe 0
         .save   ar.pfs,r2
 #ifdef XMA_TEMPTATION
 { .mfi; alloc           r2=ar.pfs,4,0,0,0       };;
@@ -294,9 +293,10 @@ bn_mul_words:
         cmp4.le         p6,p0=r34,r0
 (p6)    br.ret.spnt.many        b0              };;
 
-        .save   ar.lc,r3
 { .mii; sub     r10=r34,r0,1
+        .save   ar.lc,r3
         mov     r3=ar.lc
+        .save   pr,r9
         mov     r9=pr                   };;
 
         .body
@@ -397,22 +397,21 @@ bn_mul_words:
 .skip   48      // makes the loop body aligned at 64-byte boundary
 bn_mul_add_words:
         .prologue
-        .fframe 0
         .save   ar.pfs,r2
-        .save   ar.lc,r3
-        .save   pr,r9
 { .mmi; alloc           r2=ar.pfs,4,4,0,8
         cmp4.le         p6,p0=r34,r0
+        .save   ar.lc,r3
         mov             r3=ar.lc        };;
 { .mib; mov             r8=r0           // return value
         sub             r10=r34,r0,1
 (p6)    br.ret.spnt.many        b0      };;
 
-        .body
 { .mib; setf.sig        f8=r35          // w
+        .save   pr,r9
         mov             r9=pr
         brp.loop.imp    .L_bn_mul_add_words_ctop,.L_bn_mul_add_words_cend-16
                                         }
+        .body
 { .mmi; ADDP            r14=0,r32       // rp
         ADDP            r15=0,r33       // ap
         mov             ar.lc=r10       }
@@ -466,7 +465,6 @@ bn_mul_add_words:
 .skip   32      // makes the loop body aligned at 64-byte boundary 
 bn_sqr_words:
         .prologue
-        .fframe 0
         .save   ar.pfs,r2
 { .mii; alloc           r2=ar.pfs,3,0,0,0
         sxt4            r34=r34         };;
@@ -476,9 +474,10 @@ bn_sqr_words:
         nop.f           0x0
 (p6)    br.ret.spnt.many        b0      };;
 
-        .save   ar.lc,r3
 { .mii; sub     r10=r34,r0,1
+        .save   ar.lc,r3
         mov     r3=ar.lc
+        .save   pr,r9
         mov     r9=pr                   };;
 
         .body
@@ -545,7 +544,6 @@ bn_sqr_words:
 .align  64
 bn_sqr_comba8:
         .prologue
-        .fframe 0
         .save   ar.pfs,r2
 #if defined(_HPUX_SOURCE) && !defined(_LP64)
 { .mii; alloc   r2=ar.pfs,2,1,0,0
@@ -617,7 +615,6 @@ bn_sqr_comba8:
 .align  64
 bn_mul_comba8:
         .prologue
-        .fframe 0
         .save   ar.pfs,r2
 #if defined(_HPUX_SOURCE) && !defined(_LP64)
 { .mii; alloc   r2=ar.pfs,3,0,0,0
@@ -1175,7 +1172,6 @@ bn_mul_comba8:
 .align  64
 bn_sqr_comba4:
         .prologue
-        .fframe 0
         .save   ar.pfs,r2
 #if defined(_HPUX_SOURCE) && !defined(_LP64)
 { .mii; alloc   r2=ar.pfs,2,1,0,0
@@ -1208,7 +1204,6 @@ bn_sqr_comba4:
 .align  64
 bn_mul_comba4:
         .prologue
-        .fframe 0
         .save   ar.pfs,r2
 #if defined(_HPUX_SOURCE) && !defined(_LP64)
 { .mii; alloc   r2=ar.pfs,3,0,0,0
@@ -1411,11 +1406,11 @@ equ=p24
 .align  64
 bn_div_words:
         .prologue
-        .fframe 0
         .save   ar.pfs,r2
-        .save   b0,r3
 { .mii; alloc           r2=ar.pfs,3,5,0,8
+        .save   b0,r3
         mov             r3=b0
+        .save   pr,r10
         mov             r10=pr          };;
 { .mmb; cmp.eq          p6,p0=r34,r0
         mov             r8=-1