* [PATCH] aarch64: Use type-qualified builtins for unsigned MLA/MLS intrinsics
@ 2021-11-11 10:08 Jonathan Wright
2021-11-11 10:13 ` Richard Sandiford
0 siblings, 1 reply; 2+ messages in thread
From: Jonathan Wright @ 2021-11-11 10:08 UTC (permalink / raw)
To: gcc-patches; +Cc: Kyrylo Tkachov, Richard Sandiford
[-- Attachment #1: Type: text/plain, Size: 1049 bytes --]
Hi,
This patch declares type-qualified builtins and uses them for MLA/MLS
Neon intrinsics that operate on unsigned types. This eliminates lots of
casts in arm_neon.h.
Bootstrapped and regression tested on aarch64-none-linux-gnu - no
issues.
Ok for master?
Thanks,
Jonathan
---
gcc/ChangeLog:
2021-11-08 Jonathan Wright <jonathan.wright@arm.com>
* config/aarch64/aarch64-simd-builtins.def: Declare type-
qualified builtin generators for unsigned MLA/MLS intrinsics.
* config/aarch64/arm_neon.h (vmla_n_u16): Use type-qualified
builtin.
(vmla_n_u32): Likewise.
(vmla_u8): Likewise.
(vmla_u16): Likewise.
(vmla_u32): Likewise.
(vmlaq_n_u16): Likewise.
(vmlaq_n_u32): Likewise.
(vmlaq_u8): Likewise.
(vmlaq_u16): Likewise.
(vmlaq_u32): Likewise.
(vmls_n_u16): Likewise.
(vmls_n_u32): Likewise.
(vmls_u8): Likewise.
(vmls_u16): Likewise.
(vmls_u32): Likewise.
(vmlsq_n_u16): Likewise.
(vmlsq_n_u32): Likewise.
(vmlsq_u8): Likewise.
(vmlsq_u16): Likewise.
(vmlsq_u32): Likewise.
[-- Attachment #2: rb15027.patch --]
[-- Type: application/octet-stream, Size: 10500 bytes --]
diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index 4a7e2cf4125fe674dbb31c8f068b3b9970e9ea80..cdc44f0a22fd29715472e5b2dfe6a19ad0c729dd 100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -238,13 +238,17 @@
/* Implemented by aarch64_mla<mode>. */
BUILTIN_VDQ_BHSI (TERNOP, mla, 0, NONE)
+ BUILTIN_VDQ_BHSI (TERNOPU, mla, 0, NONE)
/* Implemented by aarch64_mla_n<mode>. */
BUILTIN_VDQHS (TERNOP, mla_n, 0, NONE)
+ BUILTIN_VDQHS (TERNOPU, mla_n, 0, NONE)
/* Implemented by aarch64_mls<mode>. */
BUILTIN_VDQ_BHSI (TERNOP, mls, 0, NONE)
+ BUILTIN_VDQ_BHSI (TERNOPU, mls, 0, NONE)
/* Implemented by aarch64_mls_n<mode>. */
BUILTIN_VDQHS (TERNOP, mls_n, 0, NONE)
+ BUILTIN_VDQHS (TERNOPU, mls_n, 0, NONE)
/* Implemented by aarch64_shrn<mode>". */
BUILTIN_VQN (SHIFTIMM, shrn, 0, NONE)
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 398a2e3a021fc488519acf6b54ff114805340e8a..de29b3b7da9a2ab16f6c5bdc832907df5deb7d61 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -6608,18 +6608,14 @@ __extension__ extern __inline uint16x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmla_n_u16 (uint16x4_t __a, uint16x4_t __b, uint16_t __c)
{
- return (uint16x4_t) __builtin_aarch64_mla_nv4hi ((int16x4_t) __a,
- (int16x4_t) __b,
- (int16_t) __c);
+ return __builtin_aarch64_mla_nv4hi_uuuu (__a, __b, __c);
}
__extension__ extern __inline uint32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmla_n_u32 (uint32x2_t __a, uint32x2_t __b, uint32_t __c)
{
- return (uint32x2_t) __builtin_aarch64_mla_nv2si ((int32x2_t) __a,
- (int32x2_t) __b,
- (int32_t) __c);
+ return __builtin_aarch64_mla_nv2si_uuuu (__a, __b, __c);
}
__extension__ extern __inline int8x8_t
@@ -6647,27 +6643,21 @@ __extension__ extern __inline uint8x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmla_u8 (uint8x8_t __a, uint8x8_t __b, uint8x8_t __c)
{
- return (uint8x8_t) __builtin_aarch64_mlav8qi ((int8x8_t) __a,
- (int8x8_t) __b,
- (int8x8_t) __c);
+ return __builtin_aarch64_mlav8qi_uuuu (__a, __b, __c);
}
__extension__ extern __inline uint16x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmla_u16 (uint16x4_t __a, uint16x4_t __b, uint16x4_t __c)
{
- return (uint16x4_t) __builtin_aarch64_mlav4hi ((int16x4_t) __a,
- (int16x4_t) __b,
- (int16x4_t) __c);
+ return __builtin_aarch64_mlav4hi_uuuu (__a, __b, __c);
}
__extension__ extern __inline uint32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmla_u32 (uint32x2_t __a, uint32x2_t __b, uint32x2_t __c)
{
- return (uint32x2_t) __builtin_aarch64_mlav2si ((int32x2_t) __a,
- (int32x2_t) __b,
- (int32x2_t) __c);
+ return __builtin_aarch64_mlav2si_uuuu (__a, __b, __c);
}
__extension__ extern __inline int32x4_t
@@ -6955,18 +6945,14 @@ __extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmlaq_n_u16 (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
{
- return (uint16x8_t) __builtin_aarch64_mla_nv8hi ((int16x8_t) __a,
- (int16x8_t) __b,
- (int16_t) __c);
+ return __builtin_aarch64_mla_nv8hi_uuuu (__a, __b, __c);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmlaq_n_u32 (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
{
- return (uint32x4_t) __builtin_aarch64_mla_nv4si ((int32x4_t) __a,
- (int32x4_t) __b,
- (int32_t) __c);
+ return __builtin_aarch64_mla_nv4si_uuuu (__a, __b, __c);
}
__extension__ extern __inline int8x16_t
@@ -6994,27 +6980,21 @@ __extension__ extern __inline uint8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmlaq_u8 (uint8x16_t __a, uint8x16_t __b, uint8x16_t __c)
{
- return (uint8x16_t) __builtin_aarch64_mlav16qi ((int8x16_t) __a,
- (int8x16_t) __b,
- (int8x16_t) __c);
+ return __builtin_aarch64_mlav16qi_uuuu (__a, __b, __c);
}
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmlaq_u16 (uint16x8_t __a, uint16x8_t __b, uint16x8_t __c)
{
- return (uint16x8_t) __builtin_aarch64_mlav8hi ((int16x8_t) __a,
- (int16x8_t) __b,
- (int16x8_t) __c);
+ return __builtin_aarch64_mlav8hi_uuuu (__a, __b, __c);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmlaq_u32 (uint32x4_t __a, uint32x4_t __b, uint32x4_t __c)
{
- return (uint32x4_t) __builtin_aarch64_mlav4si ((int32x4_t) __a,
- (int32x4_t) __b,
- (int32x4_t) __c);
+ return __builtin_aarch64_mlav4si_uuuu (__a, __b, __c);
}
__extension__ extern __inline float32x2_t
@@ -7042,18 +7022,14 @@ __extension__ extern __inline uint16x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmls_n_u16 (uint16x4_t __a, uint16x4_t __b, uint16_t __c)
{
- return (uint16x4_t) __builtin_aarch64_mls_nv4hi ((int16x4_t) __a,
- (int16x4_t) __b,
- (int16_t) __c);
+ return __builtin_aarch64_mls_nv4hi_uuuu (__a, __b, __c);
}
__extension__ extern __inline uint32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmls_n_u32 (uint32x2_t __a, uint32x2_t __b, uint32_t __c)
{
- return (uint32x2_t) __builtin_aarch64_mls_nv2si ((int32x2_t) __a,
- (int32x2_t) __b,
- (int32_t) __c);
+ return __builtin_aarch64_mls_nv2si_uuuu (__a, __b, __c);
}
__extension__ extern __inline int8x8_t
@@ -7081,27 +7057,21 @@ __extension__ extern __inline uint8x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmls_u8 (uint8x8_t __a, uint8x8_t __b, uint8x8_t __c)
{
- return (uint8x8_t) __builtin_aarch64_mlsv8qi ((int8x8_t) __a,
- (int8x8_t) __b,
- (int8x8_t) __c);
+ return __builtin_aarch64_mlsv8qi_uuuu (__a, __b, __c);
}
__extension__ extern __inline uint16x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmls_u16 (uint16x4_t __a, uint16x4_t __b, uint16x4_t __c)
{
- return (uint16x4_t) __builtin_aarch64_mlsv4hi ((int16x4_t) __a,
- (int16x4_t) __b,
- (int16x4_t) __c);
+ return __builtin_aarch64_mlsv4hi_uuuu (__a, __b, __c);
}
__extension__ extern __inline uint32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmls_u32 (uint32x2_t __a, uint32x2_t __b, uint32x2_t __c)
{
- return (uint32x2_t) __builtin_aarch64_mlsv2si ((int32x2_t) __a,
- (int32x2_t) __b,
- (int32x2_t) __c);
+ return __builtin_aarch64_mlsv2si_uuuu (__a, __b, __c);
}
__extension__ extern __inline int32x4_t
@@ -7393,18 +7363,14 @@ __extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmlsq_n_u16 (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
{
- return (uint16x8_t) __builtin_aarch64_mls_nv8hi ((int16x8_t) __a,
- (int16x8_t) __b,
- (int16_t) __c);
+ return __builtin_aarch64_mls_nv8hi_uuuu (__a, __b, __c);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmlsq_n_u32 (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
{
- return (uint32x4_t) __builtin_aarch64_mls_nv4si ((int32x4_t) __a,
- (int32x4_t) __b,
- (int32_t) __c);
+ return __builtin_aarch64_mls_nv4si_uuuu (__a, __b, __c);
}
__extension__ extern __inline int8x16_t
@@ -7432,27 +7398,21 @@ __extension__ extern __inline uint8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmlsq_u8 (uint8x16_t __a, uint8x16_t __b, uint8x16_t __c)
{
- return (uint8x16_t) __builtin_aarch64_mlsv16qi ((int8x16_t) __a,
- (int8x16_t) __b,
- (int8x16_t) __c);
+ return __builtin_aarch64_mlsv16qi_uuuu (__a, __b, __c);
}
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmlsq_u16 (uint16x8_t __a, uint16x8_t __b, uint16x8_t __c)
{
- return (uint16x8_t) __builtin_aarch64_mlsv8hi ((int16x8_t) __a,
- (int16x8_t) __b,
- (int16x8_t) __c);
+ return __builtin_aarch64_mlsv8hi_uuuu (__a, __b, __c);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vmlsq_u32 (uint32x4_t __a, uint32x4_t __b, uint32x4_t __c)
{
- return (uint32x4_t) __builtin_aarch64_mlsv4si ((int32x4_t) __a,
- (int32x4_t) __b,
- (int32x4_t) __c);
+ return __builtin_aarch64_mlsv4si_uuuu (__a, __b, __c);
}
__extension__ extern __inline int16x8_t
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [PATCH] aarch64: Use type-qualified builtins for unsigned MLA/MLS intrinsics
2021-11-11 10:08 [PATCH] aarch64: Use type-qualified builtins for unsigned MLA/MLS intrinsics Jonathan Wright
@ 2021-11-11 10:13 ` Richard Sandiford
0 siblings, 0 replies; 2+ messages in thread
From: Richard Sandiford @ 2021-11-11 10:13 UTC (permalink / raw)
To: Jonathan Wright; +Cc: gcc-patches, Kyrylo Tkachov
Jonathan Wright <Jonathan.Wright@arm.com> writes:
> Hi,
>
> This patch declares type-qualified builtins and uses them for MLA/MLS
> Neon intrinsics that operate on unsigned types. This eliminates lots of
> casts in arm_neon.h.
>
> Bootstrapped and regression tested on aarch64-none-linux-gnu - no
> issues.
>
> Ok for master?
>
> Thanks,
> Jonathan
>
> ---
>
> gcc/ChangeLog:
>
> 2021-11-08 Jonathan Wright <jonathan.wright@arm.com>
>
> * config/aarch64/aarch64-simd-builtins.def: Declare type-
> qualified builtin generators for unsigned MLA/MLS intrinsics.
> * config/aarch64/arm_neon.h (vmla_n_u16): Use type-qualified
> builtin.
> (vmla_n_u32): Likewise.
> (vmla_u8): Likewise.
> (vmla_u16): Likewise.
> (vmla_u32): Likewise.
> (vmlaq_n_u16): Likewise.
> (vmlaq_n_u32): Likewise.
> (vmlaq_u8): Likewise.
> (vmlaq_u16): Likewise.
> (vmlaq_u32): Likewise.
> (vmls_n_u16): Likewise.
> (vmls_n_u32): Likewise.
> (vmls_u8): Likewise.
> (vmls_u16): Likewise.
> (vmls_u32): Likewise.
> (vmlsq_n_u16): Likewise.
> (vmlsq_n_u32): Likewise.
> (vmlsq_u8): Likewise.
> (vmlsq_u16): Likewise.
> (vmlsq_u32): Likewise.
OK, thanks.
Richard
>
> diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
> index 4a7e2cf4125fe674dbb31c8f068b3b9970e9ea80..cdc44f0a22fd29715472e5b2dfe6a19ad0c729dd 100644
> --- a/gcc/config/aarch64/aarch64-simd-builtins.def
> +++ b/gcc/config/aarch64/aarch64-simd-builtins.def
> @@ -238,13 +238,17 @@
>
> /* Implemented by aarch64_mla<mode>. */
> BUILTIN_VDQ_BHSI (TERNOP, mla, 0, NONE)
> + BUILTIN_VDQ_BHSI (TERNOPU, mla, 0, NONE)
> /* Implemented by aarch64_mla_n<mode>. */
> BUILTIN_VDQHS (TERNOP, mla_n, 0, NONE)
> + BUILTIN_VDQHS (TERNOPU, mla_n, 0, NONE)
>
> /* Implemented by aarch64_mls<mode>. */
> BUILTIN_VDQ_BHSI (TERNOP, mls, 0, NONE)
> + BUILTIN_VDQ_BHSI (TERNOPU, mls, 0, NONE)
> /* Implemented by aarch64_mls_n<mode>. */
> BUILTIN_VDQHS (TERNOP, mls_n, 0, NONE)
> + BUILTIN_VDQHS (TERNOPU, mls_n, 0, NONE)
>
> /* Implemented by aarch64_shrn<mode>". */
> BUILTIN_VQN (SHIFTIMM, shrn, 0, NONE)
> diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
> index 398a2e3a021fc488519acf6b54ff114805340e8a..de29b3b7da9a2ab16f6c5bdc832907df5deb7d61 100644
> --- a/gcc/config/aarch64/arm_neon.h
> +++ b/gcc/config/aarch64/arm_neon.h
> @@ -6608,18 +6608,14 @@ __extension__ extern __inline uint16x4_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmla_n_u16 (uint16x4_t __a, uint16x4_t __b, uint16_t __c)
> {
> - return (uint16x4_t) __builtin_aarch64_mla_nv4hi ((int16x4_t) __a,
> - (int16x4_t) __b,
> - (int16_t) __c);
> + return __builtin_aarch64_mla_nv4hi_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline uint32x2_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmla_n_u32 (uint32x2_t __a, uint32x2_t __b, uint32_t __c)
> {
> - return (uint32x2_t) __builtin_aarch64_mla_nv2si ((int32x2_t) __a,
> - (int32x2_t) __b,
> - (int32_t) __c);
> + return __builtin_aarch64_mla_nv2si_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline int8x8_t
> @@ -6647,27 +6643,21 @@ __extension__ extern __inline uint8x8_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmla_u8 (uint8x8_t __a, uint8x8_t __b, uint8x8_t __c)
> {
> - return (uint8x8_t) __builtin_aarch64_mlav8qi ((int8x8_t) __a,
> - (int8x8_t) __b,
> - (int8x8_t) __c);
> + return __builtin_aarch64_mlav8qi_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline uint16x4_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmla_u16 (uint16x4_t __a, uint16x4_t __b, uint16x4_t __c)
> {
> - return (uint16x4_t) __builtin_aarch64_mlav4hi ((int16x4_t) __a,
> - (int16x4_t) __b,
> - (int16x4_t) __c);
> + return __builtin_aarch64_mlav4hi_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline uint32x2_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmla_u32 (uint32x2_t __a, uint32x2_t __b, uint32x2_t __c)
> {
> - return (uint32x2_t) __builtin_aarch64_mlav2si ((int32x2_t) __a,
> - (int32x2_t) __b,
> - (int32x2_t) __c);
> + return __builtin_aarch64_mlav2si_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline int32x4_t
> @@ -6955,18 +6945,14 @@ __extension__ extern __inline uint16x8_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmlaq_n_u16 (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
> {
> - return (uint16x8_t) __builtin_aarch64_mla_nv8hi ((int16x8_t) __a,
> - (int16x8_t) __b,
> - (int16_t) __c);
> + return __builtin_aarch64_mla_nv8hi_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline uint32x4_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmlaq_n_u32 (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
> {
> - return (uint32x4_t) __builtin_aarch64_mla_nv4si ((int32x4_t) __a,
> - (int32x4_t) __b,
> - (int32_t) __c);
> + return __builtin_aarch64_mla_nv4si_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline int8x16_t
> @@ -6994,27 +6980,21 @@ __extension__ extern __inline uint8x16_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmlaq_u8 (uint8x16_t __a, uint8x16_t __b, uint8x16_t __c)
> {
> - return (uint8x16_t) __builtin_aarch64_mlav16qi ((int8x16_t) __a,
> - (int8x16_t) __b,
> - (int8x16_t) __c);
> + return __builtin_aarch64_mlav16qi_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline uint16x8_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmlaq_u16 (uint16x8_t __a, uint16x8_t __b, uint16x8_t __c)
> {
> - return (uint16x8_t) __builtin_aarch64_mlav8hi ((int16x8_t) __a,
> - (int16x8_t) __b,
> - (int16x8_t) __c);
> + return __builtin_aarch64_mlav8hi_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline uint32x4_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmlaq_u32 (uint32x4_t __a, uint32x4_t __b, uint32x4_t __c)
> {
> - return (uint32x4_t) __builtin_aarch64_mlav4si ((int32x4_t) __a,
> - (int32x4_t) __b,
> - (int32x4_t) __c);
> + return __builtin_aarch64_mlav4si_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline float32x2_t
> @@ -7042,18 +7022,14 @@ __extension__ extern __inline uint16x4_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmls_n_u16 (uint16x4_t __a, uint16x4_t __b, uint16_t __c)
> {
> - return (uint16x4_t) __builtin_aarch64_mls_nv4hi ((int16x4_t) __a,
> - (int16x4_t) __b,
> - (int16_t) __c);
> + return __builtin_aarch64_mls_nv4hi_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline uint32x2_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmls_n_u32 (uint32x2_t __a, uint32x2_t __b, uint32_t __c)
> {
> - return (uint32x2_t) __builtin_aarch64_mls_nv2si ((int32x2_t) __a,
> - (int32x2_t) __b,
> - (int32_t) __c);
> + return __builtin_aarch64_mls_nv2si_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline int8x8_t
> @@ -7081,27 +7057,21 @@ __extension__ extern __inline uint8x8_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmls_u8 (uint8x8_t __a, uint8x8_t __b, uint8x8_t __c)
> {
> - return (uint8x8_t) __builtin_aarch64_mlsv8qi ((int8x8_t) __a,
> - (int8x8_t) __b,
> - (int8x8_t) __c);
> + return __builtin_aarch64_mlsv8qi_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline uint16x4_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmls_u16 (uint16x4_t __a, uint16x4_t __b, uint16x4_t __c)
> {
> - return (uint16x4_t) __builtin_aarch64_mlsv4hi ((int16x4_t) __a,
> - (int16x4_t) __b,
> - (int16x4_t) __c);
> + return __builtin_aarch64_mlsv4hi_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline uint32x2_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmls_u32 (uint32x2_t __a, uint32x2_t __b, uint32x2_t __c)
> {
> - return (uint32x2_t) __builtin_aarch64_mlsv2si ((int32x2_t) __a,
> - (int32x2_t) __b,
> - (int32x2_t) __c);
> + return __builtin_aarch64_mlsv2si_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline int32x4_t
> @@ -7393,18 +7363,14 @@ __extension__ extern __inline uint16x8_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmlsq_n_u16 (uint16x8_t __a, uint16x8_t __b, uint16_t __c)
> {
> - return (uint16x8_t) __builtin_aarch64_mls_nv8hi ((int16x8_t) __a,
> - (int16x8_t) __b,
> - (int16_t) __c);
> + return __builtin_aarch64_mls_nv8hi_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline uint32x4_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmlsq_n_u32 (uint32x4_t __a, uint32x4_t __b, uint32_t __c)
> {
> - return (uint32x4_t) __builtin_aarch64_mls_nv4si ((int32x4_t) __a,
> - (int32x4_t) __b,
> - (int32_t) __c);
> + return __builtin_aarch64_mls_nv4si_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline int8x16_t
> @@ -7432,27 +7398,21 @@ __extension__ extern __inline uint8x16_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmlsq_u8 (uint8x16_t __a, uint8x16_t __b, uint8x16_t __c)
> {
> - return (uint8x16_t) __builtin_aarch64_mlsv16qi ((int8x16_t) __a,
> - (int8x16_t) __b,
> - (int8x16_t) __c);
> + return __builtin_aarch64_mlsv16qi_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline uint16x8_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmlsq_u16 (uint16x8_t __a, uint16x8_t __b, uint16x8_t __c)
> {
> - return (uint16x8_t) __builtin_aarch64_mlsv8hi ((int16x8_t) __a,
> - (int16x8_t) __b,
> - (int16x8_t) __c);
> + return __builtin_aarch64_mlsv8hi_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline uint32x4_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> vmlsq_u32 (uint32x4_t __a, uint32x4_t __b, uint32x4_t __c)
> {
> - return (uint32x4_t) __builtin_aarch64_mlsv4si ((int32x4_t) __a,
> - (int32x4_t) __b,
> - (int32x4_t) __c);
> + return __builtin_aarch64_mlsv4si_uuuu (__a, __b, __c);
> }
>
> __extension__ extern __inline int16x8_t
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2021-11-11 10:13 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-11-11 10:08 [PATCH] aarch64: Use type-qualified builtins for unsigned MLA/MLS intrinsics Jonathan Wright
2021-11-11 10:13 ` Richard Sandiford
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).