Using libc assembler code in dhrystone stdlib.c

4 files changed, 604 insertions, 2 deletions

diff --git a/dhrystone/Makefile b/dhrystone/Makefile
index 81dea54..412ffda 100644
--- a/dhrystone/Makefile
+++ b/dhrystone/Makefile
@@ -1,6 +1,6 @@
 
 OBJS = start.o dhry_1.o dhry_2.o stdlib.o
-CFLAGS = -MD -O3 -m32 -march=RV32I -ffreestanding -nostdlib -DTIME
+CFLAGS = -MD -O3 -m32 -march=RV32I -ffreestanding -nostdlib -DTIME -DRISCV
 
 test: testbench.exe dhry.hex
 	vvp -N testbench.exe
diff --git a/dhrystone/dhry_1.c b/dhrystone/dhry_1.c
index f2fd95c..849cea8 100644
--- a/dhrystone/dhry_1.c
+++ b/dhrystone/dhry_1.c
@@ -52,7 +52,9 @@ extern  int     times ();
 #endif
 #ifdef TIME
 extern long     time();
+#ifdef RISCV
 extern long     insn();
+#endif
                 /* see library function "time"  */
 #define Too_Small_Time 2
                 /* Measurements should last at least 2 seconds */
@@ -61,9 +63,11 @@ extern long     insn();
 long            Begin_Time,
                 End_Time,
                 User_Time;
+#ifdef RISCV
 long            Begin_Insn,
                 End_Insn,
                 User_Insn;
+#endif
 float           Microseconds,
                 Dhrystones_Per_Second;
 
@@ -138,8 +142,10 @@ main ()
 #endif
 #ifdef TIME
   Begin_Time = time ( (long *) 0);
+#ifdef RISCV
   Begin_Insn = insn ( (long *) 0);
 #endif
+#endif
 
   for (Run_Index = 1; Run_Index <= Number_Of_Runs; ++Run_Index)
   {
@@ -197,8 +203,10 @@ main ()
 #endif
 #ifdef TIME
   End_Time = time ( (long *) 0);
+#ifdef RISCV
   End_Insn = insn ( (long *) 0);
 #endif
+#endif
 
   printf ("Execution ends\n");
   printf ("\n");
@@ -254,9 +262,10 @@ main ()
   printf ("\n");
 
   User_Time = End_Time - Begin_Time;
+
+#ifdef RISCV
   User_Insn = End_Insn - Begin_Insn;
 
-#if 1
   printf("Number_Of_Runs: %d\n", Number_Of_Runs);
   printf("User_Time: %d cycles, %d insn\n", User_Time, User_Insn);
 
diff --git a/dhrystone/dhry_1_orig.c b/dhrystone/dhry_1_orig.c
new file mode 100644
index 0000000..7ab02a8
--- /dev/null
+++ b/dhrystone/dhry_1_orig.c
@@ -0,0 +1,385 @@
+/*
+ ****************************************************************************
+ *
+ *                   "DHRYSTONE" Benchmark Program
+ *                   -----------------------------
+ *                                                                            
+ *  Version:    C, Version 2.1
+ *                                                                            
+ *  File:       dhry_1.c (part 2 of 3)
+ *
+ *  Date:       May 25, 1988
+ *
+ *  Author:     Reinhold P. Weicker
+ *
+ ****************************************************************************
+ */
+
+#include "dhry.h"
+
+/* Global Variables: */
+
+Rec_Pointer     Ptr_Glob,
+                Next_Ptr_Glob;
+int             Int_Glob;
+Boolean         Bool_Glob;
+char            Ch_1_Glob,
+                Ch_2_Glob;
+int             Arr_1_Glob [50];
+int             Arr_2_Glob [50] [50];
+
+extern char     *malloc ();
+Enumeration     Func_1 ();
+  /* forward declaration necessary since Enumeration may not simply be int */
+
+#ifndef REG
+        Boolean Reg = false;
+#define REG
+        /* REG becomes defined as empty */
+        /* i.e. no register variables   */
+#else
+        Boolean Reg = true;
+#endif
+
+/* variables for time measurement: */
+
+#ifdef TIMES
+struct tms      time_info;
+extern  int     times ();
+                /* see library function "times" */
+#define Too_Small_Time 120
+                /* Measurements should last at least about 2 seconds */
+#endif
+#ifdef TIME
+extern long     time();
+                /* see library function "time"  */
+#define Too_Small_Time 2
+                /* Measurements should last at least 2 seconds */
+#endif
+
+long            Begin_Time,
+                End_Time,
+                User_Time;
+float           Microseconds,
+                Dhrystones_Per_Second;
+
+/* end of variables for time measurement */
+
+
+main ()
+/*****/
+
+  /* main program, corresponds to procedures        */
+  /* Main and Proc_0 in the Ada version             */
+{
+        One_Fifty       Int_1_Loc;
+  REG   One_Fifty       Int_2_Loc;
+        One_Fifty       Int_3_Loc;
+  REG   char            Ch_Index;
+        Enumeration     Enum_Loc;
+        Str_30          Str_1_Loc;
+        Str_30          Str_2_Loc;
+  REG   int             Run_Index;
+  REG   int             Number_Of_Runs;
+
+  /* Initializations */
+
+  Next_Ptr_Glob = (Rec_Pointer) malloc (sizeof (Rec_Type));
+  Ptr_Glob = (Rec_Pointer) malloc (sizeof (Rec_Type));
+
+  Ptr_Glob->Ptr_Comp                    = Next_Ptr_Glob;
+  Ptr_Glob->Discr                       = Ident_1;
+  Ptr_Glob->variant.var_1.Enum_Comp     = Ident_3;
+  Ptr_Glob->variant.var_1.Int_Comp      = 40;
+  strcpy (Ptr_Glob->variant.var_1.Str_Comp, 
+          "DHRYSTONE PROGRAM, SOME STRING");
+  strcpy (Str_1_Loc, "DHRYSTONE PROGRAM, 1'ST STRING");
+
+  Arr_2_Glob [8][7] = 10;
+        /* Was missing in published program. Without this statement,    */
+        /* Arr_2_Glob [8][7] would have an undefined value.             */
+        /* Warning: With 16-Bit processors and Number_Of_Runs > 32000,  */
+        /* overflow may occur for this array element.                   */
+
+  printf ("\n");
+  printf ("Dhrystone Benchmark, Version 2.1 (Language: C)\n");
+  printf ("\n");
+  if (Reg)
+  {
+    printf ("Program compiled with 'register' attribute\n");
+    printf ("\n");
+  }
+  else
+  {
+    printf ("Program compiled without 'register' attribute\n");
+    printf ("\n");
+  }
+  printf ("Please give the number of runs through the benchmark: ");
+  {
+    int n;
+    scanf ("%d", &n);
+    Number_Of_Runs = n;
+  }
+  printf ("\n");
+
+  printf ("Execution starts, %d runs through Dhrystone\n", Number_Of_Runs);
+
+  /***************/
+  /* Start timer */
+  /***************/
+ 
+#ifdef TIMES
+  times (&time_info);
+  Begin_Time = (long) time_info.tms_utime;
+#endif
+#ifdef TIME
+  Begin_Time = time ( (long *) 0);
+#endif
+
+  for (Run_Index = 1; Run_Index <= Number_Of_Runs; ++Run_Index)
+  {
+
+    Proc_5();
+    Proc_4();
+      /* Ch_1_Glob == 'A', Ch_2_Glob == 'B', Bool_Glob == true */
+    Int_1_Loc = 2;
+    Int_2_Loc = 3;
+    strcpy (Str_2_Loc, "DHRYSTONE PROGRAM, 2'ND STRING");
+    Enum_Loc = Ident_2;
+    Bool_Glob = ! Func_2 (Str_1_Loc, Str_2_Loc);
+      /* Bool_Glob == 1 */
+    while (Int_1_Loc < Int_2_Loc)  /* loop body executed once */
+    {
+      Int_3_Loc = 5 * Int_1_Loc - Int_2_Loc;
+        /* Int_3_Loc == 7 */
+      Proc_7 (Int_1_Loc, Int_2_Loc, &Int_3_Loc);
+        /* Int_3_Loc == 7 */
+      Int_1_Loc += 1;
+    } /* while */
+      /* Int_1_Loc == 3, Int_2_Loc == 3, Int_3_Loc == 7 */
+    Proc_8 (Arr_1_Glob, Arr_2_Glob, Int_1_Loc, Int_3_Loc);
+      /* Int_Glob == 5 */
+    Proc_1 (Ptr_Glob);
+    for (Ch_Index = 'A'; Ch_Index <= Ch_2_Glob; ++Ch_Index)
+                             /* loop body executed twice */
+    {
+      if (Enum_Loc == Func_1 (Ch_Index, 'C'))
+          /* then, not executed */
+        {
+        Proc_6 (Ident_1, &Enum_Loc);
+        strcpy (Str_2_Loc, "DHRYSTONE PROGRAM, 3'RD STRING");
+        Int_2_Loc = Run_Index;
+        Int_Glob = Run_Index;
+        }
+    }
+      /* Int_1_Loc == 3, Int_2_Loc == 3, Int_3_Loc == 7 */
+    Int_2_Loc = Int_2_Loc * Int_1_Loc;
+    Int_1_Loc = Int_2_Loc / Int_3_Loc;
+    Int_2_Loc = 7 * (Int_2_Loc - Int_3_Loc) - Int_1_Loc;
+      /* Int_1_Loc == 1, Int_2_Loc == 13, Int_3_Loc == 7 */
+    Proc_2 (&Int_1_Loc);
+      /* Int_1_Loc == 5 */
+
+  } /* loop "for Run_Index" */
+
+  /**************/
+  /* Stop timer */
+  /**************/
+  
+#ifdef TIMES
+  times (&time_info);
+  End_Time = (long) time_info.tms_utime;
+#endif
+#ifdef TIME
+  End_Time = time ( (long *) 0);
+#endif
+
+  printf ("Execution ends\n");
+  printf ("\n");
+  printf ("Final values of the variables used in the benchmark:\n");
+  printf ("\n");
+  printf ("Int_Glob:            %d\n", Int_Glob);
+  printf ("        should be:   %d\n", 5);
+  printf ("Bool_Glob:           %d\n", Bool_Glob);
+  printf ("        should be:   %d\n", 1);
+  printf ("Ch_1_Glob:           %c\n", Ch_1_Glob);
+  printf ("        should be:   %c\n", 'A');
+  printf ("Ch_2_Glob:           %c\n", Ch_2_Glob);
+  printf ("        should be:   %c\n", 'B');
+  printf ("Arr_1_Glob[8]:       %d\n", Arr_1_Glob[8]);
+  printf ("        should be:   %d\n", 7);
+  printf ("Arr_2_Glob[8][7]:    %d\n", Arr_2_Glob[8][7]);
+  printf ("        should be:   Number_Of_Runs + 10\n");
+  printf ("Ptr_Glob->\n");
+  printf ("  Ptr_Comp:          %d\n", (int) Ptr_Glob->Ptr_Comp);
+  printf ("        should be:   (implementation-dependent)\n");
+  printf ("  Discr:             %d\n", Ptr_Glob->Discr);
+  printf ("        should be:   %d\n", 0);
+  printf ("  Enum_Comp:         %d\n", Ptr_Glob->variant.var_1.Enum_Comp);
+  printf ("        should be:   %d\n", 2);
+  printf ("  Int_Comp:          %d\n", Ptr_Glob->variant.var_1.Int_Comp);
+  printf ("        should be:   %d\n", 17);
+  printf ("  Str_Comp:          %s\n", Ptr_Glob->variant.var_1.Str_Comp);
+  printf ("        should be:   DHRYSTONE PROGRAM, SOME STRING\n");
+  printf ("Next_Ptr_Glob->\n");
+  printf ("  Ptr_Comp:          %d\n", (int) Next_Ptr_Glob->Ptr_Comp);
+  printf ("        should be:   (implementation-dependent), same as above\n");
+  printf ("  Discr:             %d\n", Next_Ptr_Glob->Discr);
+  printf ("        should be:   %d\n", 0);
+  printf ("  Enum_Comp:         %d\n", Next_Ptr_Glob->variant.var_1.Enum_Comp);
+  printf ("        should be:   %d\n", 1);
+  printf ("  Int_Comp:          %d\n", Next_Ptr_Glob->variant.var_1.Int_Comp);
+  printf ("        should be:   %d\n", 18);
+  printf ("  Str_Comp:          %s\n",
+                                Next_Ptr_Glob->variant.var_1.Str_Comp);
+  printf ("        should be:   DHRYSTONE PROGRAM, SOME STRING\n");
+  printf ("Int_1_Loc:           %d\n", Int_1_Loc);
+  printf ("        should be:   %d\n", 5);
+  printf ("Int_2_Loc:           %d\n", Int_2_Loc);
+  printf ("        should be:   %d\n", 13);
+  printf ("Int_3_Loc:           %d\n", Int_3_Loc);
+  printf ("        should be:   %d\n", 7);
+  printf ("Enum_Loc:            %d\n", Enum_Loc);
+  printf ("        should be:   %d\n", 1);
+  printf ("Str_1_Loc:           %s\n", Str_1_Loc);
+  printf ("        should be:   DHRYSTONE PROGRAM, 1'ST STRING\n");
+  printf ("Str_2_Loc:           %s\n", Str_2_Loc);
+  printf ("        should be:   DHRYSTONE PROGRAM, 2'ND STRING\n");
+  printf ("\n");
+
+  User_Time = End_Time - Begin_Time;
+
+  if (User_Time < Too_Small_Time)
+  {
+    printf ("Measured time too small to obtain meaningful results\n");
+    printf ("Please increase number of runs\n");
+    printf ("\n");
+  }
+  else
+  {
+#ifdef TIME
+    Microseconds = (float) User_Time * Mic_secs_Per_Second 
+                        / (float) Number_Of_Runs;
+    Dhrystones_Per_Second = (float) Number_Of_Runs / (float) User_Time;
+#else
+    Microseconds = (float) User_Time * Mic_secs_Per_Second 
+                        / ((float) HZ * ((float) Number_Of_Runs));
+    Dhrystones_Per_Second = ((float) HZ * (float) Number_Of_Runs)
+                        / (float) User_Time;
+#endif
+    printf ("Microseconds for one run through Dhrystone: ");
+    printf ("%6.1f \n", Microseconds);
+    printf ("Dhrystones per Second:                      ");
+    printf ("%6.1f \n", Dhrystones_Per_Second);
+    printf ("\n");
+  }
+  
+}
+
+
+Proc_1 (Ptr_Val_Par)
+/******************/
+
+REG Rec_Pointer Ptr_Val_Par;
+    /* executed once */
+{
+  REG Rec_Pointer Next_Record = Ptr_Val_Par->Ptr_Comp;  
+                                        /* == Ptr_Glob_Next */
+  /* Local variable, initialized with Ptr_Val_Par->Ptr_Comp,    */
+  /* corresponds to "rename" in Ada, "with" in Pascal           */
+  
+  structassign (*Ptr_Val_Par->Ptr_Comp, *Ptr_Glob); 
+  Ptr_Val_Par->variant.var_1.Int_Comp = 5;
+  Next_Record->variant.var_1.Int_Comp 
+        = Ptr_Val_Par->variant.var_1.Int_Comp;
+  Next_Record->Ptr_Comp = Ptr_Val_Par->Ptr_Comp;
+  Proc_3 (&Next_Record->Ptr_Comp);
+    /* Ptr_Val_Par->Ptr_Comp->Ptr_Comp 
+                        == Ptr_Glob->Ptr_Comp */
+  if (Next_Record->Discr == Ident_1)
+    /* then, executed */
+  {
+    Next_Record->variant.var_1.Int_Comp = 6;
+    Proc_6 (Ptr_Val_Par->variant.var_1.Enum_Comp, 
+           &Next_Record->variant.var_1.Enum_Comp);
+    Next_Record->Ptr_Comp = Ptr_Glob->Ptr_Comp;
+    Proc_7 (Next_Record->variant.var_1.Int_Comp, 10, 
+           &Next_Record->variant.var_1.Int_Comp);
+  }
+  else /* not executed */
+    structassign (*Ptr_Val_Par, *Ptr_Val_Par->Ptr_Comp);
+} /* Proc_1 */
+
+
+Proc_2 (Int_Par_Ref)
+/******************/
+    /* executed once */
+    /* *Int_Par_Ref == 1, becomes 4 */
+
+One_Fifty   *Int_Par_Ref;
+{
+  One_Fifty  Int_Loc;  
+  Enumeration   Enum_Loc;
+
+  Int_Loc = *Int_Par_Ref + 10;
+  do /* executed once */
+    if (Ch_1_Glob == 'A')
+      /* then, executed */
+    {
+      Int_Loc -= 1;
+      *Int_Par_Ref = Int_Loc - Int_Glob;
+      Enum_Loc = Ident_1;
+    } /* if */
+  while (Enum_Loc != Ident_1); /* true */
+} /* Proc_2 */
+
+
+Proc_3 (Ptr_Ref_Par)
+/******************/
+    /* executed once */
+    /* Ptr_Ref_Par becomes Ptr_Glob */
+
+Rec_Pointer *Ptr_Ref_Par;
+
+{
+  if (Ptr_Glob != Null)
+    /* then, executed */
+    *Ptr_Ref_Par = Ptr_Glob->Ptr_Comp;
+  Proc_7 (10, Int_Glob, &Ptr_Glob->variant.var_1.Int_Comp);
+} /* Proc_3 */
+
+
+Proc_4 () /* without parameters */
+/*******/
+    /* executed once */
+{
+  Boolean Bool_Loc;
+
+  Bool_Loc = Ch_1_Glob == 'A';
+  Bool_Glob = Bool_Loc | Bool_Glob;
+  Ch_2_Glob = 'B';
+} /* Proc_4 */
+
+
+Proc_5 () /* without parameters */
+/*******/
+    /* executed once */
+{
+  Ch_1_Glob = 'A';
+  Bool_Glob = false;
+} /* Proc_5 */
+
+
+        /* Procedure for the assignment of structures,          */
+        /* if the C compiler doesn't support this feature       */
+#ifdef  NOSTRUCTASSIGN
+memcpy (d, s, l)
+register char   *d;
+register char   *s;
+register int    l;
+{
+        while (l--) *d++ = *s++;
+}
+#endif
+
+
diff --git a/dhrystone/stdlib.c b/dhrystone/stdlib.c
index 4229aa2..2ff7ba3 100644
--- a/dhrystone/stdlib.c
+++ b/dhrystone/stdlib.c
@@ -38,12 +38,97 @@ char *malloc(int size)
 	return p;
 }
 
+#if 0
 void *memcpy(char *dest, const char *src, int n)
 {
 	while (n--)
 		*(dest++) = *(src++);
 }
+#else
+/* copy&paste from disassembled libc */
+asm (
+"               .global memcpy;      "
+"  memcpy:      xor     a5,a1,a0;    "
+"               slli    a4,a5,0x1e;  "
+"               add     a7,a0,a2;    "
+"               bnez    a4,.M1;      "
+"               li      a5,3;        "
+"               bleu    a2,a5,.M2;   "
+"               slli    a5,a0,0x1e;  "
+"               bnez    a5,.M3;      "
+"               andi    a6,a7,-4;    "
+"               addi    a5,a6,-32;   "
+"               mv      a4,a0;       "
+"               bltu    a0,a5,.M4;   "
+"  .M9:         mv      a3,a1;       "
+"               mv      a5,a4;       "
+"               bleu    a6,a4,.M5;   "
+"  .M6:         lw      a2,0(a3);    "
+"               addi    a5,a5,4;     "
+"               addi    a3,a3,4;     "
+"               sw      a2,-4(a5);   "
+"               bltu    a5,a6,.M6;   "
+"               not     a5,a4;       "
+"               add     a6,a5,a6;    "
+"               andi    a6,a6,-4;    "
+"               addi    a6,a6,4;     "
+"               add     a4,a4,a6;    "
+"               add     a1,a1,a6;    "
+"  .M5:         bltu    a4,a7,.M7;   "
+"  .M11:        ret;                 "
+"  .M3:         mv      a4,a0;       "
+"  .M8:         lbu     a5,0(a1);    "
+"               addi    a4,a4,1;     "
+"               addi    a1,a1,1;     "
+"               sb      a5,-1(a4);   "
+"               slli    a5,a4,0x1e;  "
+"               bnez    a5,.M8;      "
+"               andi    a6,a7,-4;    "
+"               addi    a5,a6,-32;   "
+"               bleu    a5,a4,.M9;   "
+"  .M4:         lw      t6,0(a1);    "
+"               lw      t5,4(a1);    "
+"               lw      t4,8(a1);    "
+"               lw      t3,12(a1);   "
+"               lw      t2,16(a1);   "
+"               lw      t1,20(a1);   "
+"               lw      t0,24(a1);   "
+"               lw      a2,28(a1);   "
+"               addi    a1,a1,36;    "
+"               addi    a4,a4,36;    "
+"               lw      a3,-4(a1);   "
+"               sw      t6,-36(a4);  "
+"               sw      t5,-32(a4);  "
+"               sw      t4,-28(a4);  "
+"               sw      t3,-24(a4);  "
+"               sw      t2,-20(a4);  "
+"               sw      t1,-16(a4);  "
+"               sw      t0,-12(a4);  "
+"               sw      a2,-8(a4);   "
+"               sw      a3,-4(a4);   "
+"               bltu    a4,a5,.M4;   "
+"               j       .M9;         "
+"  .M1:         mv      a4,a0;       "
+"               bleu    a7,a0,.M10;  "
+"  .M7:         lbu     a5,0(a1);    "
+"               addi    a4,a4,1;     "
+"               addi    a1,a1,1;     "
+"               sb      a5,-1(a4);   "
+"               bltu    a4,a7,.M7;   "
+"  .M12:        ret;                 "
+"  .M2:         mv      a4,a0;       "
+"               bleu    a7,a0,.M11;  "
+"               lbu     a5,0(a1);    "
+"               addi    a4,a4,1;     "
+"               addi    a1,a1,1;     "
+"               sb      a5,-1(a4);   "
+"               bltu    a4,a7,.M7;   "
+"               j       .M12;        "
+"  .M10:        ret;                 "
+);
+#endif
 
+#if 0
 char *strcpy(char *dest, const char *src)
 {
 	char *ret = dest;
@@ -53,7 +138,55 @@ char *strcpy(char *dest, const char *src)
 	while (*(src++));
 	return ret;
 }
+#else
+/* copy&paste from disassembled libc */
+asm (
+"               .global strcpy;      "
+"  strcpy:      or      a5,a0,a1;    "
+"               slli    a4,a5,0x1e;  "
+"               bnez    a4,.S1;      "
+"               lw      a4,0(a1);    "
+"               lui     a3,0x7f7f8;  "
+"               addi    a3,a3,-129;  "
+"               and     a5,a4,a3;    "
+"               add     a5,a5,a3;    "
+"               or      a7,a4,a3;    "
+"               or      a7,a7,a5;    "
+"               li      a5,-1;       "
+"               mv      a2,a0;       "
+"               bne     a7,a5,.S2;   "
+"  .S3:         addi    a2,a2,4;     "
+"               addi    a1,a1,4;     "
+"               sw      a4,-4(a2);   "
+"               lw      a4,0(a1);    "
+"               and     a5,a4,a3;    "
+"               or      a6,a4,a3;    "
+"               add     a5,a5,a3;    "
+"               or      a5,a6,a5;    "
+"               beq     a5,a7,.S3;   "
+"  .S2:         lbu     a5,0(a1);    "
+"               lbu     a4,1(a1);    "
+"               lbu     a3,2(a1);    "
+"               sb      a5,0(a2);    "
+"               beqz    a5,.S4;      "
+"               sb      a4,1(a2);    "
+"               beqz    a4,.S4;      "
+"               sb      a3,2(a2);    "
+"               bnez    a3,.S5;      "
+"  .S4:         ret;                 "
+"  .S5:         sb      zero,3(a2);  "
+"               ret;                 "
+"  .S1:         mv      a5,a0;       "
+"  .S6:         lbu     a4,0(a1);    "
+"               addi    a5,a5,1;     "
+"               addi    a1,a1,1;     "
+"               sb      a4,-1(a5);   "
+"               bnez    a4,.S6;      "
+"               ret;                 "
+);
+#endif
 
+#if 0
 int strcmp(const char *s1, const char *s2)
 {
 	// printf("[strcmp()]");
@@ -67,6 +200,81 @@ int strcmp(const char *s1, const char *s2)
 		s1++, s2++;
 	}
 }
+#else
+/* copy&paste from disassembled libc */
+asm (
+"               .global strcmp;      "
+"  strcmp:      or      a4,a0,a1;    "
+"               li      t2,-1;       "
+"               andi    a4,a4,3;     "
+"               bnez    a4,.K1;      "
+"               lui     t3,0x7f7f8;  "
+"               addi    t3,t3,-129;  "
+"  .K6:         lw      a2,0(a0);    "
+"               lw      a3,0(a1);    "
+"               and     t0,a2,t3;    "
+"               or      t1,a2,t3;    "
+"               add     t0,t0,t3;    "
+"               or      t0,t0,t1;    "
+"               bne     t0,t2,.K2;   "
+"               bne     a2,a3,.K3;   "
+"               lw      a2,4(a0);    "
+"               lw      a3,4(a1);    "
+"               and     t0,a2,t3;    "
+"               or      t1,a2,t3;    "
+"               add     t0,t0,t3;    "
+"               or      t0,t0,t1;    "
+"               bne     t0,t2,.K4;   "
+"               bne     a2,a3,.K3;   "
+"               lw      a2,8(a0);    "
+"               lw      a3,8(a1);    "
+"               and     t0,a2,t3;    "
+"               or      t1,a2,t3;    "
+"               add     t0,t0,t3;    "
+"               or      t0,t0,t1;    "
+"               bne     t0,t2,.K5;   "
+"               addi    a0,a0,12;    "
+"               addi    a1,a1,12;    "
+"               beq     a2,a3,.K6;   "
+"  .K3:         slli    a4,a2,0x10;  "
+"               slli    a5,a3,0x10;  "
+"               bne     a4,a5,.K7;   "
+"               srli    a4,a2,0x10;  "
+"               srli    a5,a3,0x10;  "
+"               sub     a0,a4,a5;    "
+"               andi    a1,a0,255;   "
+"               bnez    a1,.K8;      "
+"               ret;                 "
+"  .K7:         srli    a4,a4,0x10;  "
+"               srli    a5,a5,0x10;  "
+"               sub     a0,a4,a5;    "
+"               andi    a1,a0,255;   "
+"               bnez    a1,.K8;      "
+"               ret;                 "
+"  .K8:         andi    a4,a4,255;   "
+"               andi    a5,a5,255;   "
+"               sub     a0,a4,a5;    "
+"               ret;                 "
+"  .K1:         lbu     a2,0(a0);    "
+"               lbu     a3,0(a1);    "
+"               addi    a0,a0,1;     "
+"               addi    a1,a1,1;     "
+"               bne     a2,a3,.K9;   "
+"               bnez    a2,.K1;      "
+"  .K9:         sub     a0,a2,a3;    "
+"               ret;                 "
+"  .K4:         addi    a0,a0,4;     "
+"               addi    a1,a1,4;     "
+"  .K2:         bne     a2,a3,.K1;   "
+"               li      a0,0;        "
+"               ret;                 "
+"  .K5:         addi    a0,a0,8;     "
+"               addi    a1,a1,8;     "
+"               bne     a2,a3,.K1;   "
+"               li      a0,0;        "
+"               ret;                 "
+);
+#endif
 
 static void printf_c(int c)
 {