[Patch AArch64] Use 128-bit vectors when autovectorizing 16-bit float types

gcc/

	* config/aarch64/aarch64.c (aarch64_simd_container_mode): Handle
	HFmode.

gcc/testsuite/

	* gcc.target/aarch64/vect_fp16_1.c: New.

From-SVN: r245429

gcc/ChangeLog

+2017-02-14  James Greenhalgh  <james.greenhalgh@arm.com>
+
+	* config/aarch64/aarch64.c (aarch64_simd_container_mode): Handle
+	HFmode.
+
 2017-02-14  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
 
 	PR rtl-optimization/68664

gcc/config/aarch64/aarch64.c

@@ -10845,6 +10845,8 @@ aarch64_simd_container_mode (machine_mode mode, unsigned width)
 	    return V2DFmode;
 	  case SFmode:
 	    return V4SFmode;
+	  case HFmode:
+	    return V8HFmode;
 	  case SImode:
 	    return V4SImode;
 	  case HImode:
@@ -10861,6 +10863,8 @@ aarch64_simd_container_mode (machine_mode mode, unsigned width)
 	  {
 	  case SFmode:
 	    return V2SFmode;
+	  case HFmode:
+	    return V4HFmode;
 	  case SImode:
 	    return V2SImode;
 	  case HImode:

gcc/testsuite/ChangeLog

+2017-02-14  James Greenhalgh  <james.greenhalgh@arm.com>
+
+	* gcc.target/aarch64/vect_fp16_1.c: New.
+
 2017-02-14  Prathamesh Kulkarni  <prathamesh.kulkarni@linaro.org>
 
 	* gcc.dg/gimplefe-25.c: New test.

gcc/testsuite/gcc.target/aarch64/vect_fp16_1.c

+/* { dg-do compile } */
+/* { dg-options "-O3 -fno-vect-cost-model" } */
+
+/* Check that we vectorize to a full 128-bit vector for _Float16 and __fp16
+   types.  */
+
+/* Enable ARMv8.2-A+fp16 so we have access to the vector instructions.  */
+#pragma GCC target ("arch=armv8.2-a+fp16")
+
+_Float16
+sum_Float16 (_Float16 *__restrict__ __attribute__ ((__aligned__ (16))) a,
+	     _Float16 *__restrict__ __attribute__ ((__aligned__ (16))) b,
+	     _Float16 *__restrict__ __attribute__ ((__aligned__ (16))) c)
+{
+  for (int i = 0; i < 256; i++)
+    a[i] = b[i] + c[i];
+}
+
+_Float16
+sum_fp16 (__fp16 *__restrict__ __attribute__ ((__aligned__ (16))) a,
+	  __fp16 *__restrict__ __attribute__ ((__aligned__ (16))) b,
+	  __fp16 *__restrict__ __attribute__ ((__aligned__ (16))) c)
+{
+  for (int i = 0; i < 256; i++)
+    a[i] = b[i] + c[i];
+}
+
+/* Two FADD operations on "8h" data widths, one from sum_Float16, one from
+   sum_fp16.  */
+/* { dg-final { scan-assembler-times "fadd\tv\[0-9\]\+.8h" 2 } } */