[ARM] Improve 64-bit shifts (non-NEON)

2012-02-17  Andrew Stubbs  <ams@codesourcery.com>

	gcc/
	* config/arm/arm-protos.h (arm_emit_coreregs_64bit_shift): New
	prototype.
	* config/arm/arm.c (arm_emit_coreregs_64bit_shift): New function.
	* config/arm/arm.md (ashldi3): Use arm_emit_coreregs_64bit_shift.
	(ashrdi3,lshrdi3): Likewise.
	(arm_cond_branch): Remove '*' to enable gen_arm_cond_branch.

---
 gcc/config/arm/arm-protos.h |    3 +
 gcc/config/arm/arm.c        |  201 +++++++++++++++++++++++++++++++++++++++++++
 gcc/config/arm/arm.md       |  104 ++++++++++++++++------
 3 files changed, 280 insertions(+), 28 deletions(-)

diff --git a/gcc/config/arm/arm-protos.h b/gcc/config/arm/arm-protos.h
index 296550a..df8d7a9 100644
--- a/gcc/config/arm/arm-protos.h
+++ b/gcc/config/arm/arm-protos.h
@@ -242,6 +242,9 @@  struct tune_params
 
 extern const struct tune_params *current_tune;
 extern int vfp3_const_double_for_fract_bits (rtx);
+
+extern void arm_emit_coreregs_64bit_shift (enum rtx_code, rtx, rtx, rtx, rtx,
+					   rtx);
 #endif /* RTX_CODE */
 
 #endif /* ! GCC_ARM_PROTOS_H */
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index c3a19e4..02dc6ca 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -25213,5 +25213,206 @@  vfp3_const_double_for_fract_bits (rtx operand)
   return 0;
 }
 
+/* The default expansion of general 64-bit shifts in core-regs is suboptimal
+   on ARM, since we know that shifts by negative amounts are no-ops.
+
+   It's safe for the input and output to be the same register, but
+   early-clobber rules apply for the shift amount and scratch registers.
+
+   Shift by register requires both scratch registers.  Shift by a constant
+   less than 32 in Thumb2 mode requires SCRATCH1 only.  In all other cases
+   the scratch registers may be NULL.
+
+   Additionally, ashiftrt by a register also clobbers the CC register.  */
+void
+arm_emit_coreregs_64bit_shift (enum rtx_code code, rtx out, rtx in,
+			       rtx amount, rtx scratch1, rtx scratch2)
+{
+  rtx out_high = gen_highpart (SImode, out);
+  rtx out_low = gen_lowpart (SImode, out);
+  rtx in_high = gen_highpart (SImode, in);
+  rtx in_low = gen_lowpart (SImode, in);
+
+  /* Bits flow from up-stream to down-stream.  */
+  rtx out_up   = code == ASHIFT ? out_low : out_high;
+  rtx out_down = code == ASHIFT ? out_high : out_low;
+  rtx in_up   = code == ASHIFT ? in_low : in_high;
+  rtx in_down = code == ASHIFT ? in_high : in_low;
+
+  gcc_assert (code == ASHIFT || code == ASHIFTRT || code == LSHIFTRT);
+  gcc_assert (out
+	      && (REG_P (out) || GET_CODE (out) == SUBREG)
+	      && GET_MODE (out) == DImode);
+  gcc_assert (in
+	      && (REG_P (in) || GET_CODE (in) == SUBREG)
+	      && GET_MODE (in) == DImode);
+  gcc_assert (amount
+	      && (((REG_P (amount) || GET_CODE (amount) == SUBREG)
+		   && GET_MODE (amount) == SImode)
+		  || CONST_INT_P (amount)));
+  gcc_assert (scratch1 == NULL
+	      || (GET_CODE (scratch1) == SCRATCH)
+	      || (GET_MODE (scratch1) == SImode
+		  && REG_P (scratch1)));
+  gcc_assert (scratch2 == NULL
+	      || (GET_CODE (scratch2) == SCRATCH)
+	      || (GET_MODE (scratch2) == SImode
+		  && REG_P (scratch2)));
+  gcc_assert (!REG_P (out) || !REG_P (amount)
+	      || !HARD_REGISTER_P (out)
+	      || (REGNO (out) != REGNO (amount)
+		  && REGNO (out) + 1 != REGNO (amount)));
+
+  /* Macros to make following code more readable.  */
+  #define SUB_32(DEST,SRC) \
+	    gen_addsi3 ((DEST), (SRC), gen_rtx_CONST_INT (VOIDmode, -32))
+  #define RSB_32(DEST,SRC) \
+	    gen_subsi3 ((DEST), gen_rtx_CONST_INT (VOIDmode, 32), (SRC))
+  #define SUB_S_32(DEST,SRC) \
+	    gen_addsi3_compare0 ((DEST), (SRC), \
+				 gen_rtx_CONST_INT (VOIDmode, -32))
+  #define SET(DEST,SRC) \
+	    gen_rtx_SET (SImode, (DEST), (SRC))
+  #define SHIFT(CODE,SRC,AMOUNT) \
+	    gen_rtx_fmt_ee ((CODE), SImode, (SRC), (AMOUNT))
+  #define LSHIFT(CODE,SRC,AMOUNT) \
+	    gen_rtx_fmt_ee ((CODE) == ASHIFT ? ASHIFT : LSHIFTRT, \
+			    SImode, (SRC), (AMOUNT))
+  #define REV_LSHIFT(CODE,SRC,AMOUNT) \
+	    gen_rtx_fmt_ee ((CODE) == ASHIFT ? LSHIFTRT : ASHIFT, \
+			    SImode, (SRC), (AMOUNT))
+  #define ORR(A,B) \
+	    gen_rtx_IOR (SImode, (A), (B))
+  #define BRANCH(COND,LABEL) \
+	    gen_arm_cond_branch ((LABEL), \
+				 gen_rtx_ ## COND (CCmode, cc_reg, \
+						   const0_rtx), \
+				 cc_reg)
+
+  if (CONST_INT_P (amount))
+    {
+      /* Shifts by a constant amount.  */
+      if (INTVAL (amount) <= 0)
+	/* Match what shift-by-register would do.  */
+	emit_insn (gen_movdi (out, in));
+      else if (INTVAL (amount) >= 64)
+	{
+	  /* Match what shift-by-register would do.  */
+	  if (code == ASHIFTRT)
+	    {
+	      rtx const31_rtx = gen_rtx_CONST_INT (VOIDmode, 31);
+	      emit_insn (SET (out_down, SHIFT (code, in_up, const31_rtx)));
+	      emit_insn (SET (out_up, SHIFT (code, in_up, const31_rtx)));
+	    }
+	  else
+	    emit_insn (gen_movdi (out, const0_rtx));
+	}
+      else if (INTVAL (amount) < 32)
+	{
+	  /* Shifts by a constant less than 32.  */
+	  rtx reverse_amount = gen_rtx_CONST_INT (VOIDmode,
+						  32 - INTVAL (amount));
+
+	  emit_insn (SET (out_down, LSHIFT (code, in_down, amount)));
+	  emit_insn (SET (out_down,
+			  ORR (REV_LSHIFT (code, in_up, reverse_amount),
+			       out_down)));
+	  emit_insn (SET (out_up, SHIFT (code, in_up, amount)));
+	}
+      else
+	{
+	  /* Shifts by a constant greater than 31.  */
+	  rtx adj_amount = gen_rtx_CONST_INT (VOIDmode, INTVAL (amount) - 32);
+
+	  emit_insn (SET (out_down, SHIFT (code, in_up, adj_amount)));
+	  if (code == ASHIFTRT)
+	    emit_insn (gen_ashrsi3 (out_up, in_up,
+				    gen_rtx_CONST_INT (VOIDmode, 31)));
+	  else
+	    emit_insn (SET (out_up, const0_rtx));
+	}
+    }
+  else
+    {
+      /* Shifts by a variable amount.  */
+      rtx cc_reg = gen_rtx_REG (CC_NCVmode, CC_REGNUM);
+
+      gcc_assert (scratch1 && REG_P (scratch1));
+      gcc_assert (scratch2 && REG_P (scratch2));
+
+      switch (code)
+	{
+	case ASHIFT:
+	  emit_insn (SUB_32 (scratch1, amount));
+	  emit_insn (RSB_32 (scratch2, amount));
+	  break;
+	case ASHIFTRT:
+	  emit_insn (RSB_32 (scratch1, amount));
+	  emit_insn (SUB_S_32 (scratch2, amount));
+	  break;
+	case LSHIFTRT:
+	  emit_insn (RSB_32 (scratch1, amount));
+	  emit_insn (SUB_32 (scratch2, amount));
+	  break;
+	default:
+	  gcc_unreachable ();
+	}
+
+      emit_insn (SET (out_down, LSHIFT (code, in_down, amount)));
+
+      if (!TARGET_THUMB2)
+	{
+	  /* If this were only called during expand we could just use the else
+	     case and let combine deal with it, but this can also be called
+	     from post-reload splitters.  */
+	  emit_insn (SET (out_down,
+			  ORR (SHIFT (ASHIFT, in_up, scratch1), out_down)));
+	  if (code == ASHIFTRT)
+	    {
+	      rtx done_label = gen_label_rtx ();
+	      emit_jump_insn (BRANCH (LT, done_label));
+	      emit_insn (SET (out_down, ORR (SHIFT (ASHIFTRT, in_up, scratch2),
+					     out_down)));
+	      emit_label (done_label);
+	    }
+	  else
+	    emit_insn (SET (out_down, ORR (SHIFT (LSHIFTRT, in_up, scratch2),
+					   out_down)));
+	}
+      else
+	{
+	  /* Thumb2 can't do shift and or in one insn.  */
+	  emit_insn (SET (scratch1, SHIFT (ASHIFT, in_up, scratch1)));
+	  emit_insn (gen_iorsi3 (out_down, out_down, scratch1));
+
+	  if (code == ASHIFTRT)
+	    {
+	      rtx done_label = gen_label_rtx ();
+	      emit_jump_insn (BRANCH (LT, done_label));
+	      emit_insn (SET (scratch2, SHIFT (ASHIFTRT, in_up, scratch2)));
+	      emit_insn (SET (out_down, ORR (out_down, scratch2)));
+	      emit_label (done_label);
+	    }
+	  else
+	    {
+	      emit_insn (SET (scratch2, SHIFT (LSHIFTRT, in_up, scratch2)));
+	      emit_insn (gen_iorsi3 (out_down, out_down, scratch2));
+	    }
+	}
+
+      emit_insn (SET (out_up, SHIFT (code, in_up, amount)));
+    }
+
+  #undef SUB_32
+  #undef RSB_32
+  #undef SUB_S_32
+  #undef SET
+  #undef SHIFT
+  #undef LSHIFT
+  #undef REV_LSHIFT
+  #undef ORR
+  #undef BRANCH
+}
+
 #include "gt-arm.h"
 
diff --git a/gcc/config/arm/arm.md b/gcc/config/arm/arm.md
index 751997f..7910bae 100644
--- a/gcc/config/arm/arm.md
+++ b/gcc/config/arm/arm.md
@@ -3466,21 +3466,37 @@ 
                    (match_operand:SI 2 "reg_or_int_operand" "")))]
   "TARGET_32BIT"
   "
-  if (GET_CODE (operands[2]) == CONST_INT)
+  if (!CONST_INT_P (operands[2])
+      && (TARGET_REALLY_IWMMXT || (TARGET_HARD_FLOAT && TARGET_MAVERICK)))
+    ; /* No special preparation statements; expand pattern as above.  */
+  else
     {
-      if ((HOST_WIDE_INT) INTVAL (operands[2]) == 1)
+      rtx scratch1, scratch2;
+
+      if (GET_CODE (operands[2]) == CONST_INT
+	  && (HOST_WIDE_INT) INTVAL (operands[2]) == 1)
         {
           emit_insn (gen_arm_ashldi3_1bit (operands[0], operands[1]));
           DONE;
         }
-        /* Ideally we shouldn't fail here if we could know that operands[1] 
-           ends up already living in an iwmmxt register. Otherwise it's
-           cheaper to have the alternate code being generated than moving
-           values to iwmmxt regs and back.  */
-        FAIL;
+
+      /* Ideally we should use iwmmxt here if we could know that operands[1]
+         ends up already living in an iwmmxt register. Otherwise it's
+         cheaper to have the alternate code being generated than moving
+         values to iwmmxt regs and back.  */
+
+      /* If we're optimizing for size, we prefer the libgcc calls.  */
+      if (optimize_function_for_size_p (cfun))
+	FAIL;
+
+      /* Expand operation using core-registers.
+	 'FAIL' would achieve the same thing, but this is a bit smarter.  */
+      scratch1 = gen_reg_rtx (SImode);
+      scratch2 = gen_reg_rtx (SImode);
+      arm_emit_coreregs_64bit_shift (ASHIFT, operands[0], operands[1],
+				     operands[2], scratch1, scratch2);
+      DONE;
     }
-  else if (!TARGET_REALLY_IWMMXT && !(TARGET_HARD_FLOAT && TARGET_MAVERICK))
-    FAIL;
   "
 )
 
@@ -3525,21 +3541,37 @@ 
                      (match_operand:SI 2 "reg_or_int_operand" "")))]
   "TARGET_32BIT"
   "
-  if (GET_CODE (operands[2]) == CONST_INT)
+  if (!CONST_INT_P (operands[2])
+      && (TARGET_REALLY_IWMMXT || (TARGET_HARD_FLOAT && TARGET_MAVERICK)))
+    ; /* No special preparation statements; expand pattern as above.  */
+  else
     {
-      if ((HOST_WIDE_INT) INTVAL (operands[2]) == 1)
+      rtx scratch1, scratch2;
+
+      if (GET_CODE (operands[2]) == CONST_INT
+	  && (HOST_WIDE_INT) INTVAL (operands[2]) == 1)
         {
           emit_insn (gen_arm_ashrdi3_1bit (operands[0], operands[1]));
           DONE;
         }
-        /* Ideally we shouldn't fail here if we could know that operands[1] 
-           ends up already living in an iwmmxt register. Otherwise it's
-           cheaper to have the alternate code being generated than moving
-           values to iwmmxt regs and back.  */
-        FAIL;
+
+      /* Ideally we should use iwmmxt here if we could know that operands[1]
+         ends up already living in an iwmmxt register. Otherwise it's
+         cheaper to have the alternate code being generated than moving
+         values to iwmmxt regs and back.  */
+
+      /* If we're optimizing for size, we prefer the libgcc calls.  */
+      if (optimize_function_for_size_p (cfun))
+	FAIL;
+
+      /* Expand operation using core-registers.
+	 'FAIL' would achieve the same thing, but this is a bit smarter.  */
+      scratch1 = gen_reg_rtx (SImode);
+      scratch2 = gen_reg_rtx (SImode);
+      arm_emit_coreregs_64bit_shift (ASHIFTRT, operands[0], operands[1],
+				     operands[2], scratch1, scratch2);
+      DONE;
     }
-  else if (!TARGET_REALLY_IWMMXT)
-    FAIL;
   "
 )
 
@@ -3582,21 +3614,37 @@ 
                      (match_operand:SI 2 "reg_or_int_operand" "")))]
   "TARGET_32BIT"
   "
-  if (GET_CODE (operands[2]) == CONST_INT)
+  if (!CONST_INT_P (operands[2])
+      && (TARGET_REALLY_IWMMXT || (TARGET_HARD_FLOAT && TARGET_MAVERICK)))
+    ; /* No special preparation statements; expand pattern as above.  */
+  else
     {
-      if ((HOST_WIDE_INT) INTVAL (operands[2]) == 1)
+      rtx scratch1, scratch2;
+
+      if (GET_CODE (operands[2]) == CONST_INT
+	  && (HOST_WIDE_INT) INTVAL (operands[2]) == 1)
         {
           emit_insn (gen_arm_lshrdi3_1bit (operands[0], operands[1]));
           DONE;
         }
-        /* Ideally we shouldn't fail here if we could know that operands[1] 
-           ends up already living in an iwmmxt register. Otherwise it's
-           cheaper to have the alternate code being generated than moving
-           values to iwmmxt regs and back.  */
-        FAIL;
+
+      /* Ideally we should use iwmmxt here if we could know that operands[1]
+         ends up already living in an iwmmxt register. Otherwise it's
+         cheaper to have the alternate code being generated than moving
+         values to iwmmxt regs and back.  */
+
+      /* If we're optimizing for size, we prefer the libgcc calls.  */
+      if (optimize_function_for_size_p (cfun))
+	FAIL;
+
+      /* Expand operation using core-registers.
+	 'FAIL' would achieve the same thing, but this is a bit smarter.  */
+      scratch1 = gen_reg_rtx (SImode);
+      scratch2 = gen_reg_rtx (SImode);
+      arm_emit_coreregs_64bit_shift (LSHIFTRT, operands[0], operands[1],
+				     operands[2], scratch1, scratch2);
+      DONE;
     }
-  else if (!TARGET_REALLY_IWMMXT)
-    FAIL;
   "
 )
 
@@ -7645,7 +7693,7 @@ 
 ;; Patterns to match conditional branch insns.
 ;;
 
-(define_insn "*arm_cond_branch"
+(define_insn "arm_cond_branch"
   [(set (pc)
 	(if_then_else (match_operator 1 "arm_comparison_operator"
 		       [(match_operand 2 "cc_register" "") (const_int 0)])