arm: Use LDMIA/STMIA for thumb1 DI/DF loads/stores

If the address register is dead after load/store operation it looks
beneficial to use LDMIA/STMIA instead of pair of LDR/STR instructions,
at least if optimizing for size.

gcc/ChangeLog:

	* config/arm/arm.cc (thumb_load_double_from_address): Emit ldmia
	when address reg rewritten by load.
	* config/arm/thumb1.md (peephole2 to rewrite DI/DF load): New.
	(peephole2 to rewrite DI/DF store): New.
	* config/arm/iterators.md (DIDF): New.

gcc/testsuite:

	* gcc.target/arm/thumb1-load-store-64bit.c: Add new test.

Signed-off-by: Siarhei Volkau <lis8215@gmail.com>

4 files changed, 58 insertions, 8 deletions

diff --git a/gcc/config/arm/arm.cc b/gcc/config/arm/arm.cc
index 6dab65f..bb9c7c3 100644
--- a/gcc/config/arm/arm.cc
+++ b/gcc/config/arm/arm.cc
@@ -28374,15 +28374,11 @@ thumb_load_double_from_address (rtx *operands)
   switch (GET_CODE (addr))
     {
     case REG:
-      operands[2] = adjust_address (operands[1], SImode, 4);
-
-      if (REGNO (operands[0]) == REGNO (addr))
-	{
-	  output_asm_insn ("ldr\t%H0, %2", operands);
-	  output_asm_insn ("ldr\t%0, %1", operands);
-	}
+      if (reg_overlap_mentioned_p (addr, operands[0]))
+	output_asm_insn ("ldmia\t%m1, {%0, %H0}", operands);
       else
 	{
+	  operands[2] = adjust_address (operands[1], SImode, 4);
 	  output_asm_insn ("ldr\t%0, %1", operands);
 	  output_asm_insn ("ldr\t%H0, %2", operands);
 	}
diff --git a/gcc/config/arm/iterators.md b/gcc/config/arm/iterators.md
index 987602d..b9ff01c 100644
--- a/gcc/config/arm/iterators.md
+++ b/gcc/config/arm/iterators.md
@@ -50,6 +50,9 @@
 ;; A list of the 32bit and 64bit integer modes
 (define_mode_iterator SIDI [SI DI])
 
+;; A list of the 64bit modes for thumb1.
+(define_mode_iterator DIDF [DI DF])
+
 ;; A list of atomic compare and swap success return modes
 (define_mode_iterator CCSI [(CC_Z "TARGET_32BIT") (SI "TARGET_THUMB1")])
 
diff --git a/gcc/config/arm/thumb1.md b/gcc/config/arm/thumb1.md
index d7074b4..b4d7c6e 100644
--- a/gcc/config/arm/thumb1.md
+++ b/gcc/config/arm/thumb1.md
@@ -655,6 +655,42 @@
    (set_attr "pool_range" "*,*,*,*,*,*,1018,*,*")]
 )
 
+
+;; match patterns usable by ldmia/stmia
+(define_peephole2
+  [(set (match_operand:DIDF 0 "low_register_operand" "")
+	(match_operand:DIDF 1 "memory_operand" ""))]
+  "TARGET_THUMB1
+   && low_register_operand (XEXP (operands[1], 0), SImode)
+   && !reg_overlap_mentioned_p (XEXP (operands[1], 0), operands[0])
+   && peep2_reg_dead_p (1, XEXP (operands[1], 0))"
+  [(set (match_dup 0)
+	(match_dup 1))]
+  {
+    operands[1] = change_address (operands[1], VOIDmode,
+				  gen_rtx_POST_INC (SImode,
+						    XEXP (operands[1], 0)));
+  }
+)
+
+(define_peephole2
+  [(set (match_operand:DIDF 0 "memory_operand" "")
+	(match_operand:DIDF 1 "low_register_operand" ""))]
+  "TARGET_THUMB1
+   && low_register_operand (XEXP (operands[0], 0), SImode)
+   && peep2_reg_dead_p (1, XEXP (operands[0], 0))
+   /* The low register in the transfer list may overlap the address,
+      but the second cannot.  */
+   && REGNO (XEXP (operands[0], 0)) != (REGNO (operands[1]) + 1)"
+  [(set (match_dup 0)
+	(match_dup 1))]
+  {
+    operands[0] = change_address (operands[0], VOIDmode,
+				  gen_rtx_POST_INC (SImode,
+						    XEXP (operands[0], 0)));
+  }
+)
+
 (define_insn "*thumb1_movsi_insn"
   [(set (match_operand:SI 0 "nonimmediate_operand" "=l,l,r,l,l,l,>,l, l, m,*l*h*k")
 	(match_operand:SI 1 "general_operand"      "l, I,j,J,K,>,l,i, mi,l,*l*h*k"))]
@@ -2055,4 +2091,3 @@
    (set_attr "conds" "clob")
    (set_attr "type" "multiple")]
 )
-
diff --git a/gcc/testsuite/gcc.target/arm/thumb1-load-store-64bit.c b/gcc/testsuite/gcc.target/arm/thumb1-load-store-64bit.c
new file mode 100644
index 0000000..167fa9e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/thumb1-load-store-64bit.c
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-mthumb -Os" }  */
+/* { dg-require-effective-target arm_thumb1_ok } */
+
+void copy_df(double *dst, const double *src)
+{
+    *dst = *src;
+}
+
+void copy_di(unsigned long long *dst, const unsigned long long *src)
+{
+    *dst = *src;
+}
+
+/* { dg-final { scan-assembler-times "ldmia\tr\[0-7\]" 2 } } */
+/* { dg-final { scan-assembler-times "stmia\tr\[0-7\]!" 2 } } */