Patchwork [ix86/gcc-4_5-branch] PATCH: Improve 8bit div/mod

diff --git a/gcc/ChangeLog.ix86 b/gcc/ChangeLog.ix86
new file mode 100644
index 0000000..1e2f8c0
--- /dev/null
+++ b/gcc/ChangeLog.ix86
@@ -0,0 +1,22 @@ 
+2010-07-07  H.J. Lu  <hongjiu.lu@intel.com>
+
+	Backport from mainline
+	2010-07-04  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR rtl-optimization/44695
+	* config/i386/i386.md (extract_code): Removed.
+	(<u>divmodqi4): Likewise.
+	(divmodqi4): New.
+	(udivmodqi4): Likewise.
+	(divmodhiqi3): Change div/mod to HImode and extend operand 2 to
+	HImode.
+	(udivmodhiqi3): Likewise.
+
+	2010-06-24  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR target/44588
+	* config/i386/i386.md (extract_code): New.
+	(<u>divmodqi4): Likewise.
+	(divmodhiqi3): Likewise.
+	(udivmodhiqi3): Likewise.
+	(<u>divqi3): Remvoved.
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 49bad32..3ddd816 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -7945,17 +7945,6 @@ 
 
 ;; Divide instructions
 
-(define_insn "<u>divqi3"
-  [(set (match_operand:QI 0 "register_operand" "=a")
-	(any_div:QI
-	  (match_operand:HI 1 "register_operand" "0")
-	  (match_operand:QI 2 "nonimmediate_operand" "qm")))
-   (clobber (reg:CC FLAGS_REG))]
-  "TARGET_QIMODE_MATH"
-  "<sgnprefix>div{b}\t%2"
-  [(set_attr "type" "idiv")
-   (set_attr "mode" "QI")])
-
 ;; The patterns that match these are at the end of this file.
 
 (define_expand "divxf3"
@@ -7992,6 +7981,125 @@ 
 
 ;; Divmod instructions.
 
+(define_expand "divmodqi4"
+  [(parallel [(set (match_operand:QI 0 "register_operand" "")
+		   (div:QI
+		     (match_operand:QI 1 "register_operand" "")
+		     (match_operand:QI 2 "nonimmediate_operand" "")))
+	      (set (match_operand:QI 3 "register_operand" "")
+		   (mod:QI (match_dup 1) (match_dup 2)))
+	      (clobber (reg:CC FLAGS_REG))])]
+  "TARGET_QIMODE_MATH"
+{
+  rtx div, mod, insn;
+  rtx tmp0, tmp1;
+  
+  tmp0 = gen_reg_rtx (HImode);
+  tmp1 = gen_reg_rtx (HImode);
+
+  /* Extend operands[1] to HImode.  Generate 8bit divide.  Result is
+     in AX.  */
+  emit_insn (gen_extendqihi2 (tmp1, operands[1]));
+  emit_insn (gen_divmodhiqi3 (tmp0, tmp1, operands[2]));
+
+  /* Extract remainder from AH.  */
+  tmp1 = gen_rtx_SIGN_EXTRACT (QImode, tmp0, GEN_INT (8), GEN_INT (8));
+  insn = emit_move_insn (operands[3], tmp1);
+
+  mod = gen_rtx_MOD (QImode, operands[1], operands[2]);
+  set_unique_reg_note (insn, REG_EQUAL, mod);
+
+  /* Extract quotient from AL.  */
+  insn = emit_move_insn (operands[0], gen_lowpart (QImode, tmp0));
+
+  div = gen_rtx_DIV (QImode, operands[1], operands[2]);
+  set_unique_reg_note (insn, REG_EQUAL, div);
+
+  DONE;
+})
+
+(define_expand "udivmodqi4"
+  [(parallel [(set (match_operand:QI 0 "register_operand" "")
+		   (udiv:QI
+		     (match_operand:QI 1 "register_operand" "")
+		     (match_operand:QI 2 "nonimmediate_operand" "")))
+	      (set (match_operand:QI 3 "register_operand" "")
+		   (umod:QI (match_dup 1) (match_dup 2)))
+	      (clobber (reg:CC FLAGS_REG))])]
+  "TARGET_QIMODE_MATH"
+{
+  rtx div, mod, insn;
+  rtx tmp0, tmp1;
+  
+  tmp0 = gen_reg_rtx (HImode);
+  tmp1 = gen_reg_rtx (HImode);
+
+  /* Extend operands[1] to HImode.  Generate 8bit divide.  Result is
+     in AX.  */
+  emit_insn (gen_zero_extendqihi2 (tmp1, operands[1]));
+  emit_insn (gen_udivmodhiqi3 (tmp0, tmp1, operands[2]));
+
+  /* Extract remainder from AH.  */
+  tmp1 = gen_rtx_ZERO_EXTRACT (SImode, tmp0, GEN_INT (8), GEN_INT (8));
+  tmp1 = simplify_gen_subreg (QImode, tmp1, SImode, 0);
+  insn = emit_move_insn (operands[3], tmp1);
+
+  mod = gen_rtx_UMOD (QImode, operands[1], operands[2]);
+  set_unique_reg_note (insn, REG_EQUAL, mod);
+
+  /* Extract quotient from AL.  */
+  insn = emit_move_insn (operands[0], gen_lowpart (QImode, tmp0));
+
+  div = gen_rtx_UDIV (QImode, operands[1], operands[2]);
+  set_unique_reg_note (insn, REG_EQUAL, div);
+
+  DONE;
+})
+
+;; Divide AX by r/m8, with result stored in
+;; AL <- Quotient
+;; AH <- Remainder
+;; Change div/mod to HImode and extend the second argument to HImode
+;; so that mode of div/mod matches with mode of arguments.  Otherwise
+;; combine may fail.
+(define_insn "divmodhiqi3"
+  [(set (match_operand:HI 0 "register_operand" "=a")
+	(ior:HI
+	  (ashift:HI
+	    (zero_extend:HI
+	      (truncate:QI
+		(mod:HI (match_operand:HI 1 "register_operand" "0")
+			(sign_extend:HI
+			  (match_operand:QI 2 "nonimmediate_operand" "qm")))))
+	    (const_int 8))
+	  (zero_extend:HI
+	    (truncate:QI
+	      (div:HI (match_dup 1) (sign_extend:HI (match_dup 2)))))))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_QIMODE_MATH"
+  "idiv{b}\t%2"
+  [(set_attr "type" "idiv")
+   (set_attr "mode" "QI")])
+
+(define_insn "udivmodhiqi3"
+  [(set (match_operand:HI 0 "register_operand" "=a")
+	(ior:HI
+	  (ashift:HI
+	    (zero_extend:HI
+	      (truncate:QI
+		(mod:HI (match_operand:HI 1 "register_operand" "0")
+			(zero_extend:HI
+			  (match_operand:QI 2 "nonimmediate_operand" "qm")))))
+	    (const_int 8))
+	  (zero_extend:HI
+	    (truncate:QI
+	      (div:HI (match_dup 1) (zero_extend:HI (match_dup 2)))))))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_QIMODE_MATH"
+  "div{b}\t%2"
+  [(set_attr "type" "idiv")
+   (set_attr "mode" "QI")])
+
 (define_expand "divmod<mode>4"
   [(parallel [(set (match_operand:SWIM248 0 "register_operand" "")
 		   (div:SWIM248
diff --git a/gcc/testsuite/ChangeLog.ix86 b/gcc/testsuite/ChangeLog.ix86
new file mode 100644
index 0000000..b902c5b
--- /dev/null
+++ b/gcc/testsuite/ChangeLog.ix86
@@ -0,0 +1,15 @@ 
+2010-07-07  H.J. Lu  <hongjiu.lu@intel.com>
+
+	Backport from mainline
+	2010-07-04  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR rtl-optimization/44695
+	* gcc.dg/torture/pr44695.c: New.
+
+	2010-06-24  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR target/44588
+	* gcc.target/i386/mod-1.c: New.
+	* gcc.target/i386/umod-1.c: Likewise.
+	* gcc.target/i386/umod-2.c: Likewise.
+	* gcc.target/i386/umod-3.c: Likewise.
diff --git a/gcc/testsuite/gcc.dg/torture/pr44695.c b/gcc/testsuite/gcc.dg/torture/pr44695.c
new file mode 100644
index 0000000..85bb4c7
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr44695.c
@@ -0,0 +1,15 @@ 
+/* { dg-do compile } */
+
+typedef unsigned char uint8_t;
+
+static uint8_t
+safe_div_func_uint8_t_u_u (uint8_t ui1, uint8_t ui2)
+{
+  return ui2 ? ui2 : (ui1 / ui2);
+}
+
+int
+int81 (int x)
+{
+  return safe_div_func_uint8_t_u_u (1, 8 & x);
+}
diff --git a/gcc/testsuite/gcc.target/i386/mod-1.c b/gcc/testsuite/gcc.target/i386/mod-1.c
new file mode 100644
index 0000000..a7b1a92
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/mod-1.c
@@ -0,0 +1,29 @@ 
+/* { dg-do compile } */
+/* { dg-options "-Os -mtune=generic" } */
+
+typedef struct {
+  int a;
+} VCR;
+
+typedef struct {
+  VCR vcr[8];
+} VCRC;
+
+typedef struct {
+  char vcr;
+} OWN;
+
+OWN Own[16];
+
+void
+f (VCRC *x, OWN *own)
+{
+  x[own->vcr / 8].vcr[own->vcr % 8].a--;
+  x[own->vcr / 8].vcr[own->vcr % 8].a = x[own->vcr / 8].vcr[own->vcr % 8].a;
+}
+
+/* { dg-final { scan-assembler-times "idivb" 1 } } */
+/* { dg-final { scan-assembler-not "incl" } } */
+/* { dg-final { scan-assembler-not "orl" } } */
+/* { dg-final { scan-assembler-not "andb" } } */
+/* { dg-final { scan-assembler-not "jns" } } */
diff --git a/gcc/testsuite/gcc.target/i386/umod-1.c b/gcc/testsuite/gcc.target/i386/umod-1.c
new file mode 100644
index 0000000..54edf13
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/umod-1.c
@@ -0,0 +1,11 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O2 -mtune=atom" } */
+
+unsigned char
+foo (unsigned char x, unsigned char y)
+{
+  return x % y;
+}
+
+/* { dg-final { scan-assembler-times "divb" 1 } } */
+/* { dg-final { scan-assembler-not "divw" } } */
diff --git a/gcc/testsuite/gcc.target/i386/umod-2.c b/gcc/testsuite/gcc.target/i386/umod-2.c
new file mode 100644
index 0000000..6fe7384
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/umod-2.c
@@ -0,0 +1,14 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O2 -mtune=atom" } */
+
+extern unsigned char z;
+
+unsigned char
+foo (unsigned char x, unsigned char y)
+{
+  z = x/y;
+  return x % y;
+}
+
+/* { dg-final { scan-assembler-times "divb" 1 } } */
+/* { dg-final { scan-assembler-not "divw" } } */
diff --git a/gcc/testsuite/gcc.target/i386/umod-3.c b/gcc/testsuite/gcc.target/i386/umod-3.c
new file mode 100644
index 0000000..94310b0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/umod-3.c
@@ -0,0 +1,21 @@ 
+/* { dg-do compile } */
+/* { dg-options "-Os -mtune=atom" } */
+
+extern void abort (void);
+extern void exit (int);
+
+unsigned char cx = 7;
+
+int
+main ()
+{
+  unsigned char cy;
+  
+  cy = cx / 6; if (cy != 1) abort ();
+  cy = cx % 6; if (cy != 1) abort ();
+
+  exit(0);
+}
+
+/* { dg-final { scan-assembler-times "divb" 1 } } */
+/* { dg-final { scan-assembler-not "divw" } } */