[ARM][PR82989] Fix unexpected use of NEON instructions for shifts

This patch fixes PR82989 so that we avoid NEON instructions when
-mneon-for-64bits is not enabled. This is more of a short term fix
for the real deeper problem of making an early decision of choosing
or rejecting NEON instructions. There is now a new ticket PR84467 to
deal with the longer term solution.
(Please refer to the discussion in the bug report for more details).

Sudi

*** gcc/ChangeLog ***

2018-03-20  Sudakshina Das  <sudi.das@arm.com>

	PR target/82989
	* config/arm/neon.md (ashldi3_neon): Update ?s for constraints
	to favor GPR over NEON registers.
	(<shift>di3_neon): Likewise.

*** gcc/testsuite/ChangeLog ***

2018-03-20  Sudakshina Das  <sudi.das@arm.com>

	PR target/82989
	* gcc.target/arm/pr82989.c: New test.

From-SVN: r258677

gcc/ChangeLog

+2018-03-20  Sudakshina Das  <sudi.das@arm.com>
+
+	PR target/82989
+	* config/arm/neon.md (ashldi3_neon): Update ?s for constraints
+	to favor GPR over NEON registers.
+	(<shift>di3_neon): Likewise.
+
 2018-03-20  Tom de Vries  <tom@codesourcery.com>
 
 	PR target/84952

gcc/config/arm/neon.md

@@ -1180,12 +1180,12 @@
 )
 
 (define_insn_and_split "ashldi3_neon"
-  [(set (match_operand:DI 0 "s_register_operand"	    "= w, w,?&r,?r,?&r, ?w,w")
-	(ashift:DI (match_operand:DI 1 "s_register_operand" " 0w, w, 0r, 0,  r, 0w,w")
-		   (match_operand:SI 2 "general_operand"    "rUm, i,  r, i,  i,rUm,i")))
-   (clobber (match_scratch:SI 3				    "= X, X,?&r, X,  X,  X,X"))
-   (clobber (match_scratch:SI 4				    "= X, X,?&r, X,  X,  X,X"))
-   (clobber (match_scratch:DI 5				    "=&w, X,  X, X,  X, &w,X"))
+  [(set (match_operand:DI 0 "s_register_operand"	    "= w, w, &r, r, &r, ?w,?w")
+	(ashift:DI (match_operand:DI 1 "s_register_operand" " 0w, w, 0r, 0,  r, 0w, w")
+		   (match_operand:SI 2 "general_operand"    "rUm, i,  r, i,  i,rUm, i")))
+   (clobber (match_scratch:SI 3				    "= X, X, &r, X,  X,  X, X"))
+   (clobber (match_scratch:SI 4				    "= X, X, &r, X,  X,  X, X"))
+   (clobber (match_scratch:DI 5				    "=&w, X,  X, X,  X, &w, X"))
    (clobber (reg:CC_C CC_REGNUM))]
   "TARGET_NEON"
   "#"
@@ -1276,7 +1276,7 @@
 ;; ashrdi3_neon
 ;; lshrdi3_neon
 (define_insn_and_split "<shift>di3_neon"
-  [(set (match_operand:DI 0 "s_register_operand"	     "= w, w,?&r,?r,?&r,?w,?w")
+  [(set (match_operand:DI 0 "s_register_operand"	     "= w, w, &r, r, &r,?w,?w")
 	(RSHIFTS:DI (match_operand:DI 1 "s_register_operand" " 0w, w, 0r, 0,  r,0w, w")
 		    (match_operand:SI 2 "reg_or_int_operand" "  r, i,  r, i,  i, r, i")))
    (clobber (match_scratch:SI 3				     "=2r, X, &r, X,  X,2r, X"))

gcc/testsuite/ChangeLog

+2018-03-20  Sudakshina Das  <sudi.das@arm.com>
+
+	PR target/82989
+	* gcc.target/arm/pr82989.c: New test.
+
 2018-03-20  Jakub Jelinek  <jakub@redhat.com>
 
 	PR target/84945

gcc/testsuite/gcc.target/arm/pr82989.c

+/* PR target/82989.  */
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-skip-if "avoid conflicts with multilib options" { *-*-* } { "-mcpu=*" } { "-mcpu=cortex-a8" } } */
+/* { dg-skip-if "avoid conflicts with multilib options" { *-*-* } { "-mfpu=*" } { "-mfpu=neon" } } */
+/* { dg-skip-if "avoid conflicts with multilib options" { *-*-* } { "-mfloat-abi=*" } { "-mfloat-abi=hard" } } */
+/* { dg-options "-O2 -mcpu=cortex-a8 -mfpu=neon -mfloat-abi=hard" } */
+/* { dg-add-options arm_neon } */
+
+typedef unsigned long long uint64_t;
+
+void f_shr_imm (uint64_t *a)
+{
+  *a += *a >> 32;
+}
+/* { dg-final { scan-assembler-not "vshr*" } } */
+
+void f_shr_reg (uint64_t *a, uint64_t b)
+{
+  *a += *a >> b;
+}
+/* { dg-final { scan-assembler-not "vshl*" } } */
+/* Only 2 times for f_shr_reg. f_shr_imm should not have any.  */
+/* { dg-final { scan-assembler-times {lsr\tr[0-9]+, r[0-9]+, r[0-9]} 2 } } */
+
+void f_shl_imm (uint64_t *a)
+{
+  *a += *a << 32;
+}
+/* { dg-final { scan-assembler-not "vshl*" } } */
+
+void f_shl_reg (uint64_t *a, uint64_t b)
+{
+  *a += *a << b;
+}
+/* { dg-final { scan-assembler-not "vshl*" } } */
+/* Only 2 times for f_shl_reg. f_shl_imm should not have any.  */
+/* { dg-final { scan-assembler-times {lsl\tr[0-9]+, r[0-9]+, r[0-9]} 2 } } */