This adds support to the auto-vectorizer to support HFmode vectorization for
AArch32. This is supported when +fp16 is used. I wonder if I should disable
the returning of the type if the option isn't enabled.
At the moment it will be returned but the vectorizer will try and fail to use
it. It wastes a few compile cycles but doesn't result in bad code.
gcc/ChangeLog:
* config/arm/arm.c (arm_preferred_simd_mode): Add E_HFmode.
gcc/testsuite/ChangeLog:
* gcc.target/arm/vect-half-floats.c: New test.
if (TARGET_NEON)
switch (mode)
{
+ case E_HFmode:
+ return TARGET_NEON_VECTORIZE_DOUBLE ? V4HFmode : V8HFmode;
case E_SFmode:
return TARGET_NEON_VECTORIZE_DOUBLE ? V2SFmode : V4SFmode;
case E_SImode:
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target target_float16 } */
+/* { dg-require-effective-target arm_fp16_ok } */
+/* { dg-add-options for_float16 } */
+/* { dg-additional-options "-Ofast -ftree-vectorize -fdump-tree-vect-all -std=c11" } */
+
+void foo (_Float16 n1[], _Float16 n2[], _Float16 r[], int n)
+{
+ for (int i = 0; i < n; i++)
+ r[i] = n1[i] + n2[i];
+}
+
+/* { dg-final { scan-tree-dump-not "LOOP VECTORIZED" "vect" } } */
+