[v2,08/36] arm: [MVE intrinsics] add vcvt_f16_f32 and vcvt_f32_f16 shapes
Commit Message
This patch adds the vcvt_f16_f32 and vcvt_f32_f16 shapes descriptions.
2024-07-11 Christophe Lyon <christophe.lyon@linaro.org>
gcc/
* config/arm/arm-mve-builtins-shapes.cc (vcvt_f16_f32)
(vcvt_f32_f16): New.
* config/arm/arm-mve-builtins-shapes.h (vcvt_f16_f32)
(vcvt_f32_f16): New.
---
gcc/config/arm/arm-mve-builtins-shapes.cc | 35 +++++++++++++++++++++++
gcc/config/arm/arm-mve-builtins-shapes.h | 2 ++
2 files changed, 37 insertions(+)
Comments
On 04/09/2024 14:26, Christophe Lyon wrote:
> This patch adds the vcvt_f16_f32 and vcvt_f32_f16 shapes descriptions.
>
> 2024-07-11 Christophe Lyon <christophe.lyon@linaro.org>
>
> gcc/
> * config/arm/arm-mve-builtins-shapes.cc (vcvt_f16_f32)
> (vcvt_f32_f16): New.
> * config/arm/arm-mve-builtins-shapes.h (vcvt_f16_f32)
> (vcvt_f32_f16): New.
OK.
R.
> ---
> gcc/config/arm/arm-mve-builtins-shapes.cc | 35 +++++++++++++++++++++++
> gcc/config/arm/arm-mve-builtins-shapes.h | 2 ++
> 2 files changed, 37 insertions(+)
>
> diff --git a/gcc/config/arm/arm-mve-builtins-shapes.cc b/gcc/config/arm/arm-mve-builtins-shapes.cc
> index bc99a6a7c43..5ebf666d954 100644
> --- a/gcc/config/arm/arm-mve-builtins-shapes.cc
> +++ b/gcc/config/arm/arm-mve-builtins-shapes.cc
> @@ -2081,6 +2081,41 @@ struct vcvt_def : public overloaded_base<0>
> };
> SHAPE (vcvt)
>
> +/* float16x8_t foo_f16_f32(float16x8_t, float32x4_t)
> +
> + Example: vcvttq_f16_f32.
> + float16x8_t [__arm_]vcvttq_f16_f32(float16x8_t a, float32x4_t b)
> + float16x8_t [__arm_]vcvttq_m_f16_f32(float16x8_t a, float32x4_t b, mve_pred16_t p)
> +*/
> +struct vcvt_f16_f32_def : public nonoverloaded_base
> +{
> + void
> + build (function_builder &b, const function_group_info &group,
> + bool preserve_user_namespace) const override
> + {
> + build_all (b, "v0,v0,v1", group, MODE_none, preserve_user_namespace);
> + }
> +};
> +SHAPE (vcvt_f16_f32)
> +
> +/* float32x4_t foo_f32_f16(float16x8_t)
> +
> + Example: vcvttq_f32_f16.
> + float32x4_t [__arm_]vcvttq_f32_f16(float16x8_t a)
> + float32x4_t [__arm_]vcvttq_m_f32_f16(float32x4_t inactive, float16x8_t a, mve_pred16_t p)
> + float32x4_t [__arm_]vcvttq_x_f32_f16(float16x8_t a, mve_pred16_t p)
> +*/
> +struct vcvt_f32_f16_def : public nonoverloaded_base
> +{
> + void
> + build (function_builder &b, const function_group_info &group,
> + bool preserve_user_namespace) const override
> + {
> + build_all (b, "v0,v1", group, MODE_none, preserve_user_namespace);
> + }
> +};
> +SHAPE (vcvt_f32_f16)
> +
> /* <T0>_t vfoo[_t0](<T0>_t, <T0>_t, mve_pred16_t)
>
> i.e. a version of the standard ternary shape in which
> diff --git a/gcc/config/arm/arm-mve-builtins-shapes.h b/gcc/config/arm/arm-mve-builtins-shapes.h
> index 9a112ceeb29..50157b57571 100644
> --- a/gcc/config/arm/arm-mve-builtins-shapes.h
> +++ b/gcc/config/arm/arm-mve-builtins-shapes.h
> @@ -78,6 +78,8 @@ namespace arm_mve
> extern const function_shape *const unary_widen;
> extern const function_shape *const unary_widen_acc;
> extern const function_shape *const vcvt;
> + extern const function_shape *const vcvt_f16_f32;
> + extern const function_shape *const vcvt_f32_f16;
> extern const function_shape *const vpsel;
>
> } /* end namespace arm_mve::shapes */
@@ -2081,6 +2081,41 @@ struct vcvt_def : public overloaded_base<0>
};
SHAPE (vcvt)
+/* float16x8_t foo_f16_f32(float16x8_t, float32x4_t)
+
+ Example: vcvttq_f16_f32.
+ float16x8_t [__arm_]vcvttq_f16_f32(float16x8_t a, float32x4_t b)
+ float16x8_t [__arm_]vcvttq_m_f16_f32(float16x8_t a, float32x4_t b, mve_pred16_t p)
+*/
+struct vcvt_f16_f32_def : public nonoverloaded_base
+{
+ void
+ build (function_builder &b, const function_group_info &group,
+ bool preserve_user_namespace) const override
+ {
+ build_all (b, "v0,v0,v1", group, MODE_none, preserve_user_namespace);
+ }
+};
+SHAPE (vcvt_f16_f32)
+
+/* float32x4_t foo_f32_f16(float16x8_t)
+
+ Example: vcvttq_f32_f16.
+ float32x4_t [__arm_]vcvttq_f32_f16(float16x8_t a)
+ float32x4_t [__arm_]vcvttq_m_f32_f16(float32x4_t inactive, float16x8_t a, mve_pred16_t p)
+ float32x4_t [__arm_]vcvttq_x_f32_f16(float16x8_t a, mve_pred16_t p)
+*/
+struct vcvt_f32_f16_def : public nonoverloaded_base
+{
+ void
+ build (function_builder &b, const function_group_info &group,
+ bool preserve_user_namespace) const override
+ {
+ build_all (b, "v0,v1", group, MODE_none, preserve_user_namespace);
+ }
+};
+SHAPE (vcvt_f32_f16)
+
/* <T0>_t vfoo[_t0](<T0>_t, <T0>_t, mve_pred16_t)
i.e. a version of the standard ternary shape in which
@@ -78,6 +78,8 @@ namespace arm_mve
extern const function_shape *const unary_widen;
extern const function_shape *const unary_widen_acc;
extern const function_shape *const vcvt;
+ extern const function_shape *const vcvt_f16_f32;
+ extern const function_shape *const vcvt_f32_f16;
extern const function_shape *const vpsel;
} /* end namespace arm_mve::shapes */