arm.md (zero_extend<mode>di2): Add extra alternatives for NEON registers.

2012-12-17  Andrew Stubbs  <ams@codesourcery.com>
	    Ulrich Weigand  <ulrich.weigand@linaro.org>

	gcc/
	* config/arm/arm.md (zero_extend<mode>di2): Add extra alternatives
	for NEON registers.
	Add alternative for one-instruction extend-in-place.
	(extend<mode>di2): Likewise.
	Add constraints for Thumb-mode memory loads.
	Prevent extend splitters doing NEON alternatives.
	* config/arm/iterators.md (qhs_extenddi_cstr, qhs_zextenddi_cstr):
	Adjust constraints to add new alternatives.
	* config/arm/neon.md: Add splitters for zero- and sign-extend.

	gcc/testsuite/
	* gcc.target/arm/neon-extend-1.c: New file.
	* gcc.target/arm/neon-extend-2.c: New file.

Co-Authored-By: Ulrich Weigand <ulrich.weigand@linaro.org>

From-SVN: r194558

7 files changed, 121 insertions, 9 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 3c0f6c4..fb99af0 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,16 @@
+2012-12-17  Andrew Stubbs  <ams@codesourcery.com>
+	    Ulrich Weigand  <ulrich.weigand@linaro.org>
+
+	* config/arm/arm.md (zero_extend<mode>di2): Add extra alternatives
+	for NEON registers.
+	Add alternative for one-instruction extend-in-place.
+	(extend<mode>di2): Likewise.
+	Add constraints for Thumb-mode memory loads.
+	Prevent extend splitters doing NEON alternatives.
+	* config/arm/iterators.md (qhs_extenddi_cstr, qhs_zextenddi_cstr):
+	Adjust constraints to add new alternatives.
+	* config/arm/neon.md: Add splitters for zero- and sign-extend.
+
 2012-12-17  Greta Yorsh  <Greta.Yorsh@arm.com>
 
         * config/arm/arm.md (type): Add "simple_alu_shift" to attribute "type".
diff --git a/gcc/config/arm/arm.md b/gcc/config/arm/arm.md
index 649e901..9add9e5 100644
--- a/gcc/config/arm/arm.md
+++ b/gcc/config/arm/arm.md
@@ -4488,33 +4488,36 @@
 ;; Zero and sign extension instructions.
 
 (define_insn "zero_extend<mode>di2"
-  [(set (match_operand:DI 0 "s_register_operand" "=r")
+  [(set (match_operand:DI 0 "s_register_operand" "=w,r,?r")
         (zero_extend:DI (match_operand:QHSI 1 "<qhs_zextenddi_op>"
 					    "<qhs_zextenddi_cstr>")))]
   "TARGET_32BIT <qhs_zextenddi_cond>"
   "#"
-  [(set_attr "length" "8")
+  [(set_attr "length" "8,4,8")
    (set_attr "ce_count" "2")
    (set_attr "predicable" "yes")]
 )
 
 (define_insn "extend<mode>di2"
-  [(set (match_operand:DI 0 "s_register_operand" "=r")
+  [(set (match_operand:DI 0 "s_register_operand" "=w,r,?r,?r")
         (sign_extend:DI (match_operand:QHSI 1 "<qhs_extenddi_op>"
 					    "<qhs_extenddi_cstr>")))]
   "TARGET_32BIT <qhs_sextenddi_cond>"
   "#"
-  [(set_attr "length" "8")
+  [(set_attr "length" "8,4,8,8")
    (set_attr "ce_count" "2")
    (set_attr "shift" "1")
-   (set_attr "predicable" "yes")]
+   (set_attr "predicable" "yes")
+   (set_attr "arch" "*,*,a,t")]
 )
 
 ;; Splits for all extensions to DImode
 (define_split
   [(set (match_operand:DI 0 "s_register_operand" "")
         (zero_extend:DI (match_operand 1 "nonimmediate_operand" "")))]
-  "TARGET_32BIT"
+  "TARGET_32BIT && (!TARGET_NEON
+		    || (reload_completed
+			&& !(IS_VFP_REGNUM (REGNO (operands[0])))))"
   [(set (match_dup 0) (match_dup 1))]
 {
   rtx lo_part = gen_lowpart (SImode, operands[0]);
@@ -4540,7 +4543,9 @@
 (define_split
   [(set (match_operand:DI 0 "s_register_operand" "")
         (sign_extend:DI (match_operand 1 "nonimmediate_operand" "")))]
-  "TARGET_32BIT"
+  "TARGET_32BIT && (!TARGET_NEON
+		    || (reload_completed
+			&& !(IS_VFP_REGNUM (REGNO (operands[0])))))"
   [(set (match_dup 0) (ashiftrt:SI (match_dup 1) (const_int 31)))]
 {
   rtx lo_part = gen_lowpart (SImode, operands[0]);
diff --git a/gcc/config/arm/iterators.md b/gcc/config/arm/iterators.md
index 5ae1aefe..3a20f5f 100644
--- a/gcc/config/arm/iterators.md
+++ b/gcc/config/arm/iterators.md
@@ -429,8 +429,8 @@
 (define_mode_attr qhs_extenddi_op [(SI "s_register_operand")
 				   (HI "nonimmediate_operand")
 				   (QI "arm_reg_or_extendqisi_mem_op")])
-(define_mode_attr qhs_extenddi_cstr [(SI "r") (HI "rm") (QI "rUq")])
-(define_mode_attr qhs_zextenddi_cstr [(SI "r") (HI "rm") (QI "rm")])
+(define_mode_attr qhs_extenddi_cstr [(SI "r,0,r,r") (HI "r,0,rm,rm") (QI "r,0,rUq,rm")])
+(define_mode_attr qhs_zextenddi_cstr [(SI "r,0,r") (HI "r,0,rm") (QI "r,0,rm")])
 
 ;; Mode attributes used for fixed-point support.
 (define_mode_attr qaddsub_suf [(V4UQQ "8") (V2UHQ "16") (UQQ "8") (UHQ "16")
diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
index fc38269..c3f14bb 100644
--- a/gcc/config/arm/neon.md
+++ b/gcc/config/arm/neon.md
@@ -5932,3 +5932,65 @@
                                    (const_string "neon_fp_vadd_qqq_vabs_qq"))
                      (const_string "neon_int_5")))]
 )
+
+;; Copy from core-to-neon regs, then extend, not vice-versa
+
+(define_split
+  [(set (match_operand:DI 0 "s_register_operand" "")
+	(sign_extend:DI (match_operand:SI 1 "s_register_operand" "")))]
+  "TARGET_NEON && reload_completed && IS_VFP_REGNUM (REGNO (operands[0]))"
+  [(set (match_dup 2) (vec_duplicate:V2SI (match_dup 1)))
+   (set (match_dup 0) (ashiftrt:DI (match_dup 0) (const_int 32)))]
+  {
+    operands[2] = gen_rtx_REG (V2SImode, REGNO (operands[0]));
+  })
+
+(define_split
+  [(set (match_operand:DI 0 "s_register_operand" "")
+	(sign_extend:DI (match_operand:HI 1 "s_register_operand" "")))]
+  "TARGET_NEON && reload_completed && IS_VFP_REGNUM (REGNO (operands[0]))"
+  [(set (match_dup 2) (vec_duplicate:V4HI (match_dup 1)))
+   (set (match_dup 0) (ashiftrt:DI (match_dup 0) (const_int 48)))]
+  {
+    operands[2] = gen_rtx_REG (V4HImode, REGNO (operands[0]));
+  })
+
+(define_split
+  [(set (match_operand:DI 0 "s_register_operand" "")
+	(sign_extend:DI (match_operand:QI 1 "s_register_operand" "")))]
+  "TARGET_NEON && reload_completed && IS_VFP_REGNUM (REGNO (operands[0]))"
+  [(set (match_dup 2) (vec_duplicate:V8QI (match_dup 1)))
+   (set (match_dup 0) (ashiftrt:DI (match_dup 0) (const_int 56)))]
+  {
+    operands[2] = gen_rtx_REG (V8QImode, REGNO (operands[0]));
+  })
+
+(define_split
+  [(set (match_operand:DI 0 "s_register_operand" "")
+	(zero_extend:DI (match_operand:SI 1 "s_register_operand" "")))]
+  "TARGET_NEON && reload_completed && IS_VFP_REGNUM (REGNO (operands[0]))"
+  [(set (match_dup 2) (vec_duplicate:V2SI (match_dup 1)))
+   (set (match_dup 0) (lshiftrt:DI (match_dup 0) (const_int 32)))]
+  {
+    operands[2] = gen_rtx_REG (V2SImode, REGNO (operands[0]));
+  })
+
+(define_split
+  [(set (match_operand:DI 0 "s_register_operand" "")
+	(zero_extend:DI (match_operand:HI 1 "s_register_operand" "")))]
+  "TARGET_NEON && reload_completed && IS_VFP_REGNUM (REGNO (operands[0]))"
+  [(set (match_dup 2) (vec_duplicate:V4HI (match_dup 1)))
+   (set (match_dup 0) (lshiftrt:DI (match_dup 0) (const_int 48)))]
+  {
+    operands[2] = gen_rtx_REG (V4HImode, REGNO (operands[0]));
+  })
+
+(define_split
+  [(set (match_operand:DI 0 "s_register_operand" "")
+	(zero_extend:DI (match_operand:QI 1 "s_register_operand" "")))]
+  "TARGET_NEON && reload_completed && IS_VFP_REGNUM (REGNO (operands[0]))"
+  [(set (match_dup 2) (vec_duplicate:V8QI (match_dup 1)))
+   (set (match_dup 0) (lshiftrt:DI (match_dup 0) (const_int 56)))]
+  {
+    operands[2] = gen_rtx_REG (V8QImode, REGNO (operands[0]));
+  })
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index d7ff3a5..0d8b3e7 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,9 @@
+2012-12-17  Andrew Stubbs  <ams@codesourcery.com>
+	    Ulrich Weigand  <ulrich.weigand@linaro.org>
+
+	* gcc.target/arm/neon-extend-1.c: New file.
+	* gcc.target/arm/neon-extend-2.c: New file.
+
 2012-12-17  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
 
 	* lib/target-supports.exp (add_options_for_arm_v8_neon):
diff --git a/gcc/testsuite/gcc.target/arm/neon-extend-1.c b/gcc/testsuite/gcc.target/arm/neon-extend-1.c
new file mode 100644
index 0000000..cfe83ce
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/neon-extend-1.c
@@ -0,0 +1,13 @@
+/* { dg-require-effective-target arm_neon_hw } */
+/* { dg-options "-O2" } */
+/* { dg-add-options arm_neon } */
+
+void
+f (unsigned int a)
+{
+  unsigned long long b = a;
+  asm volatile ("@ extended to %0" : : "w" (b));
+}
+
+/* { dg-final { scan-assembler "vdup.32" } } */
+/* { dg-final { scan-assembler "vshr.u64" } } */
diff --git a/gcc/testsuite/gcc.target/arm/neon-extend-2.c b/gcc/testsuite/gcc.target/arm/neon-extend-2.c
new file mode 100644
index 0000000..1c5a17e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/neon-extend-2.c
@@ -0,0 +1,13 @@
+/* { dg-require-effective-target arm_neon_hw } */
+/* { dg-options "-O2" } */
+/* { dg-add-options arm_neon } */
+
+void
+f (int a)
+{
+  long long b = a;
+  asm volatile ("@ extended to %0" : : "w" (b));
+}
+
+/* { dg-final { scan-assembler "vdup.32" } } */
+/* { dg-final { scan-assembler "vshr.s64" } } */