[ARM] PR66791: Replace builtins for fp and unsigned vmul_n intrinsics

[Prathamesh Kulkarni]

Hi Kyrill,
I assume this patch is OK to commit after bootstrap+testing ?

Thanks,
Prathamesh
-------------- next part --------------
diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index f42a15f7912..41b596b5fc6 100644
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -8384,21 +8384,25 @@ __extension__ extern __inline float32x2_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vmul_n_f32 (float32x2_t __a, float32_t __b)
 {
+#ifdef __FAST_MATH__
+  return __a * __b;
+#else
   return (float32x2_t)__builtin_neon_vmul_nv2sf (__a, (__builtin_neon_sf) __b);
+#endif
 }
 
 __extension__ extern __inline uint16x4_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vmul_n_u16 (uint16x4_t __a, uint16_t __b)
 {
-  return (uint16x4_t)__builtin_neon_vmul_nv4hi ((int16x4_t) __a, (__builtin_neon_hi) __b);
+  return __a * __b;
 }
 
 __extension__ extern __inline uint32x2_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vmul_n_u32 (uint32x2_t __a, uint32_t __b)
 {
-  return (uint32x2_t)__builtin_neon_vmul_nv2si ((int32x2_t) __a, (__builtin_neon_si) __b);
+  return __a * __b;
 }
 
 __extension__ extern __inline int16x8_t
@@ -8419,21 +8423,25 @@ __extension__ extern __inline float32x4_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vmulq_n_f32 (float32x4_t __a, float32_t __b)
 {
+#ifdef __FAST_MATH__
+  return __a * __b;
+#else
   return (float32x4_t)__builtin_neon_vmul_nv4sf (__a, (__builtin_neon_sf) __b);
+#endif
 }
 
 __extension__ extern __inline uint16x8_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vmulq_n_u16 (uint16x8_t __a, uint16_t __b)
 {
-  return (uint16x8_t)__builtin_neon_vmul_nv8hi ((int16x8_t) __a, (__builtin_neon_hi) __b);
+  return __a * __b;
 }
 
 __extension__ extern __inline uint32x4_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vmulq_n_u32 (uint32x4_t __a, uint32_t __b)
 {
-  return (uint32x4_t)__builtin_neon_vmul_nv4si ((int32x4_t) __a, (__builtin_neon_si) __b);
+  return __a * __b;
 }
 
 __extension__ extern __inline int32x4_t
@@ -17740,7 +17748,11 @@ __extension__ extern __inline float16x4_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vmul_n_f16 (float16x4_t __a, float16_t __b)
 {
+#ifdef __FAST_MATH__
+  return __a * __b;
+#else
   return __builtin_neon_vmul_nv4hf (__a, __b);
+#endif
 }
 
 __extension__ extern __inline float16x8_t
@@ -17765,7 +17777,11 @@ __extension__ extern __inline float16x8_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vmulq_n_f16 (float16x8_t __a, float16_t __b)
 {
+#ifdef __FAST_MATH__
+  return __a * __b;
+#else
   return __builtin_neon_vmul_nv8hf (__a, __b);
+#endif
 }
 
 __extension__ extern __inline float16x4_t
diff --git a/gcc/testsuite/gcc.target/arm/armv8_2-fp16-neon-2.c b/gcc/testsuite/gcc.target/arm/armv8_2-fp16-neon-2.c
index 50f689352ca..6808576ce59 100644
--- a/gcc/testsuite/gcc.target/arm/armv8_2-fp16-neon-2.c
+++ b/gcc/testsuite/gcc.target/arm/armv8_2-fp16-neon-2.c
@@ -327,13 +327,13 @@ BINOP_TEST (vminnm)
 
 BINOP_TEST (vmul)
 /* { dg-final { scan-assembler-times {vmul\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 3 } }
-   { dg-final { scan-assembler-times {vmul\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } }  */
+   { dg-final { scan-assembler-times {vmul\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 2 } }  */
 BINOP_LANE_TEST (vmul, 2)
 /* { dg-final { scan-assembler-times {vmul\.f16\td[0-9]+, d[0-9]+, d[0-9]+\[2\]} 1 } }
    { dg-final { scan-assembler-times {vmul\.f16\tq[0-9]+, q[0-9]+, d[0-9]+\[2\]} 1 } }  */
 BINOP_N_TEST (vmul)
-/* { dg-final { scan-assembler-times {vmul\.f16\td[0-9]+, d[0-9]+, d[0-9]+\[0\]} 1 } }
-   { dg-final { scan-assembler-times {vmul\.f16\tq[0-9]+, q[0-9]+, d[0-9]+\[0\]} 1 } }*/
+/* { dg-final { scan-assembler-times {vmul\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 3 } }
+   { dg-final { scan-assembler-times {vmul\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 2 } }*/
 
 float16x4_t
 test_vpadd_16x4 (float16x4_t a, float16x4_t b)
@@ -387,7 +387,7 @@ test_vdup_n_f16 (float16_t a)
 {
   return vdup_n_f16 (a);
 }
-/* { dg-final { scan-assembler-times {vdup\.16\td[0-9]+, r[0-9]+} 2 } }  */
+/* { dg-final { scan-assembler-times {vdup\.16\td[0-9]+, r[0-9]+} 3 } }  */
 
 float16x8_t
 test_vmovq_n_f16 (float16_t a)
@@ -400,7 +400,7 @@ test_vdupq_n_f16 (float16_t a)
 {
   return vdupq_n_f16 (a);
 }
-/* { dg-final { scan-assembler-times {vdup\.16\tq[0-9]+, r[0-9]+} 2 } }  */
+/* { dg-final { scan-assembler-times {vdup\.16\tq[0-9]+, r[0-9]+} 3 } }  */
 
 float16x4_t
 test_vdup_lane_f16 (float16x4_t a)