Introduce support for a new set of NEON square-root intrinsics for half,
single, and double precision.
modified: gcc/config/arm/arm-builtins.cc
1. Define the df_UP macro to map to E_DFmode.
2. Add CODE_FOR_neon_vsqrtsf and CODE_FOR_neon_vsqrtdf constants that
reference the underlying VFP sqrt RTL patterns (sqrtsf2 and sqrtdf2).
modified: gcc/config/arm/arm_vfp_builtins.def
1. Replace the single-mode entry for vsqrt with a unified VAR3 entry
that supports hf, sf, and df modes.
These modifications enable the use of __builtin_neon_vsqrt{hf,sf,df} in user
code and ensure the correct mode is selected for each precision variant.
Signed-off-by: Ayan Shafqat <ayan.x.shaf...@gmail.com>
Signed-off-by: Andrew Pinski <quic_apin...@quicinc.com>
---
gcc/config/arm/arm-builtins.cc | 3 +++
gcc/config/arm/arm_vfp_builtins.def | 2 +-
2 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/gcc/config/arm/arm-builtins.cc b/gcc/config/arm/arm-builtins.cc
index c56ab5db985..acc86c7e8a1 100644
--- a/gcc/config/arm/arm-builtins.cc
+++ b/gcc/config/arm/arm-builtins.cc
@@ -694,6 +694,7 @@ arm_set_sat_qualifiers[SIMD_MAX_BUILTIN_ARGS]
#define hi_UP E_HImode
#define void_UP E_VOIDmode
#define sf_UP E_SFmode
+#define df_UP E_DFmode
#define UP(X) X##_UP
typedef struct {
@@ -710,6 +711,8 @@ constexpr insn_code CODE_FOR_neon_usdotv8qi =
CODE_FOR_neon_usdotv2siv8qi;
constexpr insn_code CODE_FOR_neon_sdotv16qi = CODE_FOR_neon_sdotv4siv16qi;
constexpr insn_code CODE_FOR_neon_udotv16qi = CODE_FOR_neon_udotv4siv16qi;
constexpr insn_code CODE_FOR_neon_usdotv16qi = CODE_FOR_neon_usdotv4siv16qi;
+constexpr insn_code CODE_FOR_neon_vsqrtsf = CODE_FOR_sqrtsf2;
+constexpr insn_code CODE_FOR_neon_vsqrtdf = CODE_FOR_sqrtdf2;
#define CF(N,X) CODE_FOR_neon_##N##X
diff --git a/gcc/config/arm/arm_vfp_builtins.def
b/gcc/config/arm/arm_vfp_builtins.def
index 1fbf71e728e..8cafd72b565 100644
--- a/gcc/config/arm/arm_vfp_builtins.def
+++ b/gcc/config/arm/arm_vfp_builtins.def
@@ -40,7 +40,7 @@ VAR1 (UNOP, vrndm, hf)
VAR1 (UNOP, vrndn, hf)
VAR1 (UNOP, vrndp, hf)
VAR1 (UNOP, vrndx, hf)
-VAR1 (UNOP, vsqrt, hf)
+VAR3 (UNOP, vsqrt, hf, sf, df)
VAR2 (BINOP, vcvths_n, hf, si)
VAR2 (BINOP, vcvthu_n, hf, si)
--
2.43.0
