re PR target/50931 ([avr] Support a 24-bit scalar integer mode)

libgcc/
	PR target/50931
	* config/avr/t-avr (LIB1ASMSRC): Add _mulpsi3, _mulsqipsi3.
	* config/avr/lib1funcs.S (__mulpsi3, __mulsqipsi3): New functions.
gcc/
	PR target/50931
	* config/avr/avr.md (mulpsi3): New expander.
	(*umulqihipsi3, *umulhiqipsi3): New insns.
	(*mulsqipsi3.libgcc, *mulpsi3.libgcc): New insns.
	(mulsqipsi3, *mulpsi3): New insn-and-splits.
	(ashlpsi3): Turn to expander.  Move insn code to...
	(*ashlpsi3): ...this new insn.
testsuite/
	PR target/50931
	* gcc.target/avr/torture/int24-mul.c: New testcase.

From-SVN: r182328

7 files changed, 411 insertions, 3 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index d792244..c9e927a 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,13 @@
+2011-12-14  Georg-Johann Lay  <avr@gjlay.de>
+
+	PR target/50931
+	* config/avr/avr.md (mulpsi3): New expander.
+	(*umulqihipsi3, *umulhiqipsi3): New insns.
+	(*mulsqipsi3.libgcc, *mulpsi3.libgcc): New insns.
+	(mulsqipsi3, *mulpsi3): New insn-and-splits.
+	(ashlpsi3): Turn to expander.  Move insn code to...
+	(*ashlpsi3): ...this new insn.
+
 2011-12-14  Richard Guenther  <rguenther@suse.de>
 
 	* tree-cfg.c (replace_uses_by): Only mark blocks altered
diff --git a/gcc/config/avr/avr.md b/gcc/config/avr/avr.md
index 940a46f..21e329b 100644
--- a/gcc/config/avr/avr.md
+++ b/gcc/config/avr/avr.md
@@ -2113,7 +2113,7 @@
   [(set_attr "type" "xcall")
    (set_attr "cc" "clobber")])
 
-;; To support widening multiplicatioon with constant we postpone
+;; To support widening multiplication with constant we postpone
 ;; expanding to the implicit library call until post combine and
 ;; prior to register allocation.  Clobber all hard registers that
 ;; might be used by the (widening) multiply until it is split and
@@ -2575,6 +2575,132 @@
    (set_attr "cc" "clobber")])
 
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;; 24-bit multiply
+
+;; To support widening multiplication with constant we postpone
+;; expanding to the implicit library call until post combine and
+;; prior to register allocation.  Clobber all hard registers that
+;; might be used by the (widening) multiply until it is split and
+;; it's final register footprint is worked out.
+
+(define_expand "mulpsi3"
+  [(parallel [(set (match_operand:PSI 0 "register_operand" "")
+                   (mult:PSI (match_operand:PSI 1 "register_operand" "")
+                             (match_operand:PSI 2 "nonmemory_operand" "")))
+              (clobber (reg:HI 26))
+              (clobber (reg:DI 18))])]
+  "AVR_HAVE_MUL"
+  {
+    if (s8_operand (operands[2], PSImode))
+      {
+        rtx reg = force_reg (QImode, gen_int_mode (INTVAL (operands[2]), QImode));
+        emit_insn (gen_mulsqipsi3 (operands[0], reg, operands[1]));
+        DONE;
+      }
+  })
+
+(define_insn "*umulqihipsi3"
+  [(set (match_operand:PSI 0 "register_operand"                         "=&r")
+        (mult:PSI (zero_extend:PSI (match_operand:QI 1 "register_operand" "r"))
+                  (zero_extend:PSI (match_operand:HI 2 "register_operand" "r"))))]
+  "AVR_HAVE_MUL"
+  "mul %1,%A2
+	movw %A0,r0
+	mul %1,%B2
+	clr %C0
+	add %B0,r0
+	adc %C0,r1
+	clr __zero_reg__"
+  [(set_attr "length" "7")
+   (set_attr "cc" "clobber")])
+
+(define_insn "*umulhiqipsi3"
+  [(set (match_operand:PSI 0 "register_operand"                         "=&r")
+        (mult:PSI (zero_extend:PSI (match_operand:HI 2 "register_operand" "r"))
+                  (zero_extend:PSI (match_operand:QI 1 "register_operand" "r"))))]
+  "AVR_HAVE_MUL"
+  "mul %1,%A2
+	movw %A0,r0
+	mul %1,%B2
+	add %B0,r0
+	mov %C0,r1
+	clr __zero_reg__
+	adc %C0,__zero_reg__"
+  [(set_attr "length" "7")
+   (set_attr "cc" "clobber")])
+
+(define_insn_and_split "mulsqipsi3"
+  [(set (match_operand:PSI 0 "pseudo_register_operand"                          "=r")
+        (mult:PSI (sign_extend:PSI (match_operand:QI 1 "pseudo_register_operand" "r"))
+                  (match_operand:PSI 2 "pseudo_register_or_const_int_operand"    "rn")))
+   (clobber (reg:HI 26))
+   (clobber (reg:DI 18))]
+  "AVR_HAVE_MUL && !reload_completed"
+  { gcc_unreachable(); }
+  "&& 1"
+  [(set (reg:QI 25)
+        (match_dup 1))
+   (set (reg:PSI 22)
+        (match_dup 2))
+   (set (reg:PSI 18)
+        (mult:PSI (sign_extend:PSI (reg:QI 25))
+                  (reg:PSI 22)))
+   (set (match_dup 0)
+        (reg:PSI 18))])
+
+(define_insn_and_split "*mulpsi3"
+  [(set (match_operand:PSI 0 "pseudo_register_operand"                       "=r")
+        (mult:PSI (match_operand:PSI 1 "pseudo_register_operand"              "r")
+                  (match_operand:PSI 2 "pseudo_register_or_const_int_operand" "rn")))
+   (clobber (reg:HI 26))
+   (clobber (reg:DI 18))]
+  "AVR_HAVE_MUL && !reload_completed"
+  { gcc_unreachable(); }
+  "&& 1"
+  [(set (reg:PSI 18)
+        (match_dup 1))
+   (set (reg:PSI 22) 
+        (match_dup 2))
+   (parallel [(set (reg:PSI 22)
+                   (mult:PSI (reg:PSI 22)
+                             (reg:PSI 18)))
+              (clobber (reg:QI 21))
+              (clobber (reg:QI 25))
+              (clobber (reg:HI 26))])
+   (set (match_dup 0)
+        (reg:PSI 22))]
+  {
+    if (s8_operand (operands[2], PSImode))
+      {
+        rtx reg = force_reg (QImode, gen_int_mode (INTVAL (operands[2]), QImode));
+        emit_insn (gen_mulsqipsi3 (operands[0], reg, operands[1]));
+        DONE;
+      }
+  })
+
+(define_insn "*mulsqipsi3.libgcc"
+  [(set (reg:PSI 18)
+        (mult:PSI (sign_extend:PSI (reg:QI 25))
+                  (reg:PSI 22)))]
+  "AVR_HAVE_MUL"
+  "%~call __mulsqipsi3"
+  [(set_attr "type" "xcall")
+   (set_attr "cc" "clobber")])
+
+(define_insn "*mulpsi3.libgcc"
+  [(set (reg:PSI 22)
+        (mult:PSI (reg:PSI 22)
+                  (reg:PSI 18)))
+   (clobber (reg:QI 21))
+   (clobber (reg:QI 25))
+   (clobber (reg:HI 26))]
+  "AVR_HAVE_MUL"
+  "%~call __mulpsi3"
+  [(set_attr "type" "xcall")
+   (set_attr "cc" "clobber")])
+
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 ;; 24-bit signed/unsigned division and modulo.
 ;; Notice that the libgcc implementation return the quotient in R22
 ;; and the remainder in R18 whereas the 32-bit [u]divmodsi4
@@ -3363,7 +3489,34 @@
    (set_attr "adjust_len" "ashlsi")
    (set_attr "cc" "none,set_n,clobber,clobber")])
 
-(define_insn "ashlpsi3"
+(define_expand "ashlpsi3"
+  [(parallel [(set (match_operand:PSI 0 "register_operand"             "")
+                   (ashift:PSI (match_operand:PSI 1 "register_operand" "")
+                               (match_operand:QI 2 "nonmemory_operand" "")))
+              (clobber (scratch:QI))])]
+  ""
+  {
+    if (AVR_HAVE_MUL
+        && CONST_INT_P (operands[2]))
+      {
+        if (IN_RANGE (INTVAL (operands[2]), 3, 6))
+          {
+            rtx xoffset = force_reg (QImode, gen_int_mode (1 << INTVAL (operands[2]), QImode));
+            emit_insn (gen_mulsqipsi3 (operands[0], xoffset, operands[1])); 
+            DONE;
+          }
+        else if (optimize_insn_for_speed_p ()
+                 && INTVAL (operands[2]) != 16
+                 && IN_RANGE (INTVAL (operands[2]), 9, 22))
+          {
+            rtx xoffset = force_reg (PSImode, gen_int_mode (1 << INTVAL (operands[2]), PSImode));
+            emit_insn (gen_mulpsi3 (operands[0], operands[1], xoffset)); 
+            DONE;
+          }
+      }
+  })
+
+(define_insn "*ashlpsi3"
   [(set (match_operand:PSI 0 "register_operand"             "=r,r,r,r")
         (ashift:PSI (match_operand:PSI 1 "register_operand"  "0,0,r,0")
                     (match_operand:QI 2 "nonmemory_operand"  "r,P,O,n")))
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 93c7377..81d50c9d 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2011-12-14  Georg-Johann Lay  <avr@gjlay.de>
+
+	PR target/50931
+	* gcc.target/avr/torture/int24-mul.c: New.
+
 2011-12-14  Dodji Seketeli  <dodji@redhat.com>
 
 	PR c++/51476
diff --git a/gcc/testsuite/gcc.target/avr/torture/int24-mul.c b/gcc/testsuite/gcc.target/avr/torture/int24-mul.c
new file mode 100644
index 0000000..084e5a5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/avr/torture/int24-mul.c
@@ -0,0 +1,86 @@
+/* { dg-do run } */
+/* { dg-options "-w" } */
+
+#include <stdlib.h>
+
+const __pgm __int24 vals[] =
+  {
+    0, 1, 2, 3, -1, -2, -3, 0xff, 0x100, 0x101,
+    0xffL * 0xff, 0xfffL * 0xfff, 0x101010L, 0xaaaaaaL
+  };
+
+void test_u (void)
+{
+  unsigned int i;
+  unsigned long la, lb, lc;
+  __uint24 a, b, c;
+
+  int S = sizeof (vals) / sizeof (*vals);
+
+  for (i = 0; i < 500; i++)
+    {
+      if (i < S*S)
+        {
+          a = vals[i / S];
+          b = vals[i % S];
+        }
+      else
+        {
+          if (i & 1)
+            a += 0x7654321L;
+          else
+            b += 0x5fe453L;
+        }
+
+      c = a * b;
+
+      la = a;
+      lb = b;
+      lc = 0xffffff & (la * lb);
+      
+      if (c != lc)
+        abort();
+    }
+}
+
+#define TEST_N_U(A1,A2,B)                       \
+  do {                                          \
+    if ((0xffffff & (A1*B)) != A2*B)            \
+      abort();                                  \
+  } while (0)
+
+void test_nu (void)
+{
+  unsigned long la;
+  unsigned int i;
+  int S = sizeof (vals) / sizeof (*vals);
+  __uint24 a;
+  
+  for (i = 0; i < 500; i++)
+    {
+      a = i < S
+        ? vals[i % S]
+        : a + 0x7654321;
+
+      la = a;
+
+      TEST_N_U (la, a, 2);
+      TEST_N_U (la, a, 3);
+      TEST_N_U (la, a, 4);
+      TEST_N_U (la, a, 5);
+      TEST_N_U (la, a, 15);
+      TEST_N_U (la, a, 16);
+      TEST_N_U (la, a, 128);
+      TEST_N_U (la, a, 0x1000);
+    }
+}
+     
+int main (void)
+{
+  test_u();
+  test_nu();
+  
+  exit(0);
+    
+  return 0;
+}
diff --git a/libgcc/ChangeLog b/libgcc/ChangeLog
index 5122e9f..ce2df4a 100644
--- a/libgcc/ChangeLog
+++ b/libgcc/ChangeLog
@@ -1,3 +1,9 @@
+2011-12-14  Georg-Johann Lay  <avr@gjlay.de>
+
+	PR target/49313
+	* config/avr/t-avr (LIB1ASMSRC): Add _mulpsi3, _mulsqipsi3.
+	* config/avr/lib1funcs.S (__mulpsi3, __mulsqipsi3): New functions.
+
 2011-12-11  Eric Botcazou  <ebotcazou@adacore.com>
 
 	* config/sparc/sol2-unwind.h: Use #ifdef directive consistently.
diff --git a/libgcc/config/avr/lib1funcs.S b/libgcc/config/avr/lib1funcs.S
index 07490fb..bc16cf2 100644
--- a/libgcc/config/avr/lib1funcs.S
+++ b/libgcc/config/avr/lib1funcs.S
@@ -466,6 +466,153 @@ ENDF __mulsi3
 #endif /* __AVR_HAVE_MUL__ */
 
 /*******************************************************
+       Multiplication 24 x 24
+*******************************************************/
+
+#if defined (L_mulpsi3)
+
+;; A[0..2]: In: Multiplicand; Out: Product
+#define A0  22
+#define A1  A0+1
+#define A2  A0+2
+
+;; B[0..2]: In: Multiplier
+#define B0  18
+#define B1  B0+1
+#define B2  B0+2
+
+#if defined (__AVR_HAVE_MUL__)
+
+;; C[0..2]: Expand Result
+#define C0  22
+#define C1  C0+1
+#define C2  C0+2
+
+;; R24:R22 *= R20:R18
+;; Clobbers: r21, r25, r26, r27, __tmp_reg__
+
+#define AA0 26
+#define AA2 21
+
+DEFUN __mulpsi3
+    wmov    AA0, A0
+    mov     AA2, A2
+    XCALL   __umulhisi3
+    mul     AA2, B0     $  add  C2, r0
+    mul     AA0, B2     $  add  C2, r0
+    clr     __zero_reg__
+    ret
+ENDF __mulpsi3
+
+#undef AA2
+#undef AA0
+
+#undef C2
+#undef C1
+#undef C0
+
+#else /* !HAVE_MUL */
+
+;; C[0..2]: Expand Result
+#define C0  0
+#define C1  C0+1
+#define C2  21
+
+;; R24:R22 *= R20:R18
+;; Clobbers: __tmp_reg__, R18, R19, R20, R21
+
+DEFUN __mulpsi3
+
+    ;; C[] = 0
+    clr     __tmp_reg__
+    clr     C2
+    
+0:  ;; Shift N-th Bit of B[] into Carry.  N = 24 - Loop
+    LSR  B2     $  ror  B1     $  ror  B0
+    
+    ;; If the N-th Bit of B[] was set...
+    brcc    1f
+    
+    ;; ...then add A[] * 2^N to the Result C[]
+    ADD  C0,A0  $  adc  C1,A1  $  adc  C2,A2
+    
+1:  ;; Multiply A[] by 2
+    LSL  A0     $  rol  A1     $  rol  A2
+    
+    ;; Loop until B[] is 0
+    subi B0,0   $  sbci B1,0   $  sbci B2,0
+    brne    0b
+    
+    ;; Copy C[] to the return Register A[]
+    wmov    A0, C0
+    mov     A2, C2
+
+    clr     __zero_reg__
+    ret
+ENDF __mulpsi3
+
+#undef C2
+#undef C1
+#undef C0
+
+#endif /* HAVE_MUL */
+
+#undef B2
+#undef B1
+#undef B0
+
+#undef A2
+#undef A1
+#undef A0
+
+#endif /* L_mulpsi3 */
+
+#if defined (L_mulsqipsi3) && defined (__AVR_HAVE_MUL__)
+
+;; A[0..2]: In: Multiplicand
+#define A0  22
+#define A1  A0+1
+#define A2  A0+2
+
+;; BB: In: Multiplier
+#define BB  25
+
+;; C[0..2]: Result
+#define C0  18
+#define C1  C0+1
+#define C2  C0+2
+
+;; C[] = A[] * sign_extend (BB)
+DEFUN __mulsqipsi3
+    mul     A0, BB
+    movw    C0, r0
+    mul     A2, BB
+    mov     C2, r0
+    mul     A1, BB
+    add     C1, r0
+    adc     C2, r1
+    clr     __zero_reg__
+    sbrs    BB, 7
+    ret
+    ;; One-extend BB
+    sub     C1, A0
+    sbc     C2, A1
+    ret
+ENDF __mulsqipsi3
+
+#undef C2
+#undef C1
+#undef C0
+
+#undef BB
+
+#undef A2
+#undef A1
+#undef A0
+
+#endif /* L_mulsqipsi3  &&  HAVE_MUL */
+
+/*******************************************************
        Multiplication 64 x 64
 *******************************************************/
 
@@ -1342,7 +1489,7 @@ DEFUN  __divdi3_moddi3
 #endif /* SPEED_DIV */    
 
 0:  ;; The Prologue
-    ;; Save Z = 12 Registers:  Y, 17...8
+    ;; Save 12 Registers:  Y, 17...8
     ;; No Frame needed (X = 0)
     clr r26
     clr r27
diff --git a/libgcc/config/avr/t-avr b/libgcc/config/avr/t-avr
index c6806dc..7d7dc9e 100644
--- a/libgcc/config/avr/t-avr
+++ b/libgcc/config/avr/t-avr
@@ -2,6 +2,7 @@ LIB1ASMSRC = avr/lib1funcs.S
 LIB1ASMFUNCS = \
 	_mulqi3 \
 	_mulhi3 \
+	_mulpsi3 _mulsqipsi3 \
 	_mulhisi3 \
 	_umulhisi3 \
 	_usmulhisi3 \