Hi all,

This was committed following offline approval by Kyryl.

One minor intended optimisation introduced by :

https://gcc.gnu.org/ml/gcc-patches/2020-01/msg01237.html

was to set a preference for both __fp16 types and __bf16 types to be
loaded/stored directly into/from the FP/NEON registers (if they are available
and if the vld1.16 is compatible), rather than be passed through the regular
r-registers.

This would convert many observed instances of:

**	ldrh	r3, [r3]	@ __fp16
**	vmov.f16	s15, r3	@ __fp16

Into a single:

**	vld1.16	{d7[2]}, [r3]

This resulted in a regression of a dg-scan-assembler in a __fp16 test.

This patch updates the test to the same testing standard used by the BFloat
tests (use check-function-bodies to explicitly check for correct assembler
generated by each function) and updates it for the latest optimisation.

Cheers,
Stam

gcc/testsuite/ChangeLog:

2020-01-27  Stam Markianos-Wright  <stam.markianos-wright@arm.com>

	* gcc.target/arm/armv8_2-fp16-move-1.c: Update following load/store
        optimisation.

gcc/testsuite/ChangeLog

+2020-01-27  Stam Markianos-Wright  <stam.markianos-wright@arm.com>
+
+	* gcc.target/arm/armv8_2-fp16-move-1.c: Update following load/store
+	optimisation.
+
 2020-01-27  David Malcolm  <dmalcolm@redhat.com>
 
 	PR analyzer/93349

gcc/testsuite/gcc.target/arm/armv8_2-fp16-move-1.c

@@ -3,39 +3,78 @@
 /* { dg-options "-O2" }  */
 /* { dg-add-options arm_v8_2a_fp16_scalar }  */
 /* { dg-additional-options "-mfloat-abi=hard" } */
-
+/* { dg-final { check-function-bodies "**" "" } } */
+
+/*
+**test_load_1:
+**	...
+**	vld1.16	{d[0-9]+\[[0-9]+\]}, \[r[0-9]+\]
+**	...
+*/
 __fp16
 test_load_1 (__fp16* a)
 {
   return *a;
 }
 
+/*
+**test_load_2:
+**	...
+**	vld1.16	{d[0-9]+\[[0-9]+\]}, \[r[0-9]+\]
+**	...
+*/
 __fp16
 test_load_2 (__fp16* a, int i)
 {
   return a[i];
 }
 
-
+/*
+**test_store_1:
+**	...
+**	vst1.16	{d[0-9]+\[[0-9]+\]}, \[r[0-9]+\]
+**	...
+*/
 void
 test_store_1 (__fp16* a, __fp16 b)
 {
   *a = b;
 }
 
+/*
+**test_store_2:
+**	...
+**	vst1.16	{d[0-9]+\[[0-9]+\]}, \[r[0-9]+\]
+**	...
+*/
 void
 test_store_2 (__fp16* a, int i, __fp16 b)
 {
   a[i] = b;
 }
 
-
+/*
+**test_load_store_1:
+**	...
+**	vld1.16	{d[0-9]+\[[0-9]+\]}, \[r[0-9]+\]
+**	...
+**	vst1.16	{d[0-9]+\[[0-9]+\]}, \[r[0-9]+\]
+**	...
+*/
 __fp16
 test_load_store_1 (__fp16* a, int i, __fp16* b)
 {
   a[i] = b[i];
 }
 
+/*
+**test_load_store_2:
+**	...
+**	vld1.16	{d[0-9]+\[[0-9]+\]}, \[r[0-9]+\]
+**	...
+**	vst1.16	{d[0-9]+\[[0-9]+\]}, \[r[0-9]+\]
+**	...
+*/
 __fp16
 test_load_store_2 (__fp16* a, int i, __fp16* b)
 {
@@ -43,9 +82,6 @@ test_load_store_2 (__fp16* a, int i, __fp16* b)
   return a[i];
 }
 
-/* { dg-final { scan-assembler-times {vst1\.16\t\{d[0-9]+\[[0-9]+\]\}, \[r[0-9]+\]} 3 } }  */
-/* { dg-final { scan-assembler-times {vld1\.16\t\{d[0-9]+\[[0-9]+\]\}, \[r[0-9]+\]} 3 } }  */
-
 __fp16
 test_select_1 (int sel, __fp16 a, __fp16 b)
 {