Based on top of [1/6], this patch reimplement vector intrinsics for
conversion between floating-point and fixed-point.
gcc/
2016-06-06 Jiong Wang<[email protected]>
* config/aarch64/aarch64-builtins.def (scvtf): Register vector modes.
(ucvtf): Likewise.
(fcvtzs): Likewise.
(fcvtzu): Likewise.
* config/aarch64/aarch64-simd.md
(<FCVT_F2FIXED:fcvt_fixed_insn><VDQF:mode>3): New.
(<FCVT_FIXED2F:fcvt_fixed_insn><VDQ_SDI:mode>3): Likewise.
* config/aarch64/arm_neon.h (vcvt_n_f32_s32): Remove inline assembly.
Use builtin.
(vcvt_n_f32_u32): Likewise.
(vcvt_n_s32_f32): Likewise.
(vcvt_n_u32_f32): Likewise.
(vcvtq_n_f32_s32): Likewise.
(vcvtq_n_f32_u32): Likewise.
(vcvtq_n_f64_s64): Likewise.
(vcvtq_n_f64_u64): Likewise.
(vcvtq_n_s32_f32): Likewise.
(vcvtq_n_s64_f64): Likewise.
(vcvtq_n_u32_f32): Likewise.
(vcvtq_n_u64_f64): Likewise.
* config/aarch64/iterators.md (VDQ_SDI): New mode iterator.
(VSDQ_SDI): Likewise.
(fcvt_target): Support V4DI, V4SI and V2SI.
(FCVT_TARGET): Likewise.
diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index 0b2f0631c740558c62cffe5715eaffa5ad0557a9..a7ea3c4b8ea7d695b12e6b0291e6ff815826a641 100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -447,7 +447,7 @@
BUILTIN_VSDQ_HSI (QUADOP_LANE, sqrdmlsh_laneq, 0)
/* Implemented by <FCVT_F2FIXED/FIXED2F:fcvt_fixed_insn><*><*>3. */
- BUILTIN_GPI (BINOP, scvtf, 3)
- BUILTIN_GPI (BINOP_SUS, ucvtf, 3)
- BUILTIN_GPF (BINOP, fcvtzs, 3)
- BUILTIN_GPF (BINOP_USS, fcvtzu, 3)
+ BUILTIN_VSDQ_SDI (BINOP, scvtf, 3)
+ BUILTIN_VSDQ_SDI (BINOP_SUS, ucvtf, 3)
+ BUILTIN_VALLF (BINOP, fcvtzs, 3)
+ BUILTIN_VALLF (BINOP_USS, fcvtzu, 3)
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 6ea35bf487eaa47dd78742e3eae7507b6875ba1a..d2a6cc27de9c571e84cf59713e5fcb9c450f83a3 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -1778,6 +1778,28 @@
[(set_attr "type" "neon_fp_cvt_widen_s")]
)
+;; Convert between fixed-point and floating-point (vector modes)
+
+(define_insn "<FCVT_F2FIXED:fcvt_fixed_insn><VDQF:mode>3"
+ [(set (match_operand:<VDQF:FCVT_TARGET> 0 "register_operand" "=w")
+ (unspec:<VDQF:FCVT_TARGET> [(match_operand:VDQF 1 "register_operand" "w")
+ (match_operand:SI 2 "immediate_operand" "i")]
+ FCVT_F2FIXED))]
+ "TARGET_SIMD"
+ "<FCVT_F2FIXED:fcvt_fixed_insn>\t%<v>0<Vmtype>, %<v>1<Vmtype>, #%2"
+ [(set_attr "type" "neon_fp_to_int_<VDQF:Vetype><q>")]
+)
+
+(define_insn "<FCVT_FIXED2F:fcvt_fixed_insn><VDQ_SDI:mode>3"
+ [(set (match_operand:<VDQ_SDI:FCVT_TARGET> 0 "register_operand" "=w")
+ (unspec:<VDQ_SDI:FCVT_TARGET> [(match_operand:VDQ_SDI 1 "register_operand" "w")
+ (match_operand:SI 2 "immediate_operand" "i")]
+ FCVT_FIXED2F))]
+ "TARGET_SIMD"
+ "<FCVT_FIXED2F:fcvt_fixed_insn>\t%<v>0<Vmtype>, %<v>1<Vmtype>, #%2"
+ [(set_attr "type" "neon_int_to_fp_<VDQ_SDI:Vetype><q>")]
+)
+
;; ??? Note that the vectorizer usage of the vec_unpacks_[lo/hi] patterns
;; is inconsistent with vector ordering elsewhere in the compiler, in that
;; the meaning of HI and LO changes depending on the target endianness.
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 8a0fba6513e572ede9f2e4aaf8d29baf6baf683d..04bce9ab80c151877619ee75e7cb50f5951099f7 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -6025,150 +6025,6 @@ vaddlvq_u32 (uint32x4_t a)
result; \
})
-#define vcvt_n_f32_s32(a, b) \
- __extension__ \
- ({ \
- int32x2_t a_ = (a); \
- float32x2_t result; \
- __asm__ ("scvtf %0.2s, %1.2s, #%2" \
- : "=w"(result) \
- : "w"(a_), "i"(b) \
- : /* No clobbers */); \
- result; \
- })
-
-#define vcvt_n_f32_u32(a, b) \
- __extension__ \
- ({ \
- uint32x2_t a_ = (a); \
- float32x2_t result; \
- __asm__ ("ucvtf %0.2s, %1.2s, #%2" \
- : "=w"(result) \
- : "w"(a_), "i"(b) \
- : /* No clobbers */); \
- result; \
- })
-
-#define vcvt_n_s32_f32(a, b) \
- __extension__ \
- ({ \
- float32x2_t a_ = (a); \
- int32x2_t result; \
- __asm__ ("fcvtzs %0.2s, %1.2s, #%2" \
- : "=w"(result) \
- : "w"(a_), "i"(b) \
- : /* No clobbers */); \
- result; \
- })
-
-#define vcvt_n_u32_f32(a, b) \
- __extension__ \
- ({ \
- float32x2_t a_ = (a); \
- uint32x2_t result; \
- __asm__ ("fcvtzu %0.2s, %1.2s, #%2" \
- : "=w"(result) \
- : "w"(a_), "i"(b) \
- : /* No clobbers */); \
- result; \
- })
-
-#define vcvtq_n_f32_s32(a, b) \
- __extension__ \
- ({ \
- int32x4_t a_ = (a); \
- float32x4_t result; \
- __asm__ ("scvtf %0.4s, %1.4s, #%2" \
- : "=w"(result) \
- : "w"(a_), "i"(b) \
- : /* No clobbers */); \
- result; \
- })
-
-#define vcvtq_n_f32_u32(a, b) \
- __extension__ \
- ({ \
- uint32x4_t a_ = (a); \
- float32x4_t result; \
- __asm__ ("ucvtf %0.4s, %1.4s, #%2" \
- : "=w"(result) \
- : "w"(a_), "i"(b) \
- : /* No clobbers */); \
- result; \
- })
-
-#define vcvtq_n_f64_s64(a, b) \
- __extension__ \
- ({ \
- int64x2_t a_ = (a); \
- float64x2_t result; \
- __asm__ ("scvtf %0.2d, %1.2d, #%2" \
- : "=w"(result) \
- : "w"(a_), "i"(b) \
- : /* No clobbers */); \
- result; \
- })
-
-#define vcvtq_n_f64_u64(a, b) \
- __extension__ \
- ({ \
- uint64x2_t a_ = (a); \
- float64x2_t result; \
- __asm__ ("ucvtf %0.2d, %1.2d, #%2" \
- : "=w"(result) \
- : "w"(a_), "i"(b) \
- : /* No clobbers */); \
- result; \
- })
-
-#define vcvtq_n_s32_f32(a, b) \
- __extension__ \
- ({ \
- float32x4_t a_ = (a); \
- int32x4_t result; \
- __asm__ ("fcvtzs %0.4s, %1.4s, #%2" \
- : "=w"(result) \
- : "w"(a_), "i"(b) \
- : /* No clobbers */); \
- result; \
- })
-
-#define vcvtq_n_s64_f64(a, b) \
- __extension__ \
- ({ \
- float64x2_t a_ = (a); \
- int64x2_t result; \
- __asm__ ("fcvtzs %0.2d, %1.2d, #%2" \
- : "=w"(result) \
- : "w"(a_), "i"(b) \
- : /* No clobbers */); \
- result; \
- })
-
-#define vcvtq_n_u32_f32(a, b) \
- __extension__ \
- ({ \
- float32x4_t a_ = (a); \
- uint32x4_t result; \
- __asm__ ("fcvtzu %0.4s, %1.4s, #%2" \
- : "=w"(result) \
- : "w"(a_), "i"(b) \
- : /* No clobbers */); \
- result; \
- })
-
-#define vcvtq_n_u64_f64(a, b) \
- __extension__ \
- ({ \
- float64x2_t a_ = (a); \
- uint64x2_t result; \
- __asm__ ("fcvtzu %0.2d, %1.2d, #%2" \
- : "=w"(result) \
- : "w"(a_), "i"(b) \
- : /* No clobbers */); \
- result; \
- })
-
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vcvtx_f32_f64 (float64x2_t a)
{
@@ -12760,6 +12616,42 @@ vcvts_n_f32_u32 (uint32_t __a, const int __b)
return __builtin_aarch64_ucvtfsi_sus (__a, __b);
}
+__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
+vcvt_n_f32_s32 (int32x2_t __a, const int __b)
+{
+ return __builtin_aarch64_scvtfv2si (__a, __b);
+}
+
+__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
+vcvt_n_f32_u32 (uint32x2_t __a, const int __b)
+{
+ return __builtin_aarch64_ucvtfv2si_sus (__a, __b);
+}
+
+__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
+vcvtq_n_f32_s32 (int32x4_t __a, const int __b)
+{
+ return __builtin_aarch64_scvtfv4si (__a, __b);
+}
+
+__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
+vcvtq_n_f32_u32 (uint32x4_t __a, const int __b)
+{
+ return __builtin_aarch64_ucvtfv4si_sus (__a, __b);
+}
+
+__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
+vcvtq_n_f64_s64 (int64x2_t __a, const int __b)
+{
+ return __builtin_aarch64_scvtfv2di (__a, __b);
+}
+
+__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
+vcvtq_n_f64_u64 (uint64x2_t __a, const int __b)
+{
+ return __builtin_aarch64_ucvtfv2di_sus (__a, __b);
+}
+
/* vcvt (float -> <u>fixed-point). */
__extension__ static __inline int64_t __attribute__ ((__always_inline__))
@@ -12786,6 +12678,42 @@ vcvts_n_u32_f32 (float32_t __a, const int __b)
return __builtin_aarch64_fcvtzusf_uss (__a, __b);
}
+__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
+vcvt_n_s32_f32 (float32x2_t __a, const int __b)
+{
+ return __builtin_aarch64_fcvtzsv2sf (__a, __b);
+}
+
+__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
+vcvt_n_u32_f32 (float32x2_t __a, const int __b)
+{
+ return __builtin_aarch64_fcvtzuv2sf_uss (__a, __b);
+}
+
+__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
+vcvtq_n_s32_f32 (float32x4_t __a, const int __b)
+{
+ return __builtin_aarch64_fcvtzsv4sf (__a, __b);
+}
+
+__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
+vcvtq_n_u32_f32 (float32x4_t __a, const int __b)
+{
+ return __builtin_aarch64_fcvtzuv4sf_uss (__a, __b);
+}
+
+__extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
+vcvtq_n_s64_f64 (float64x2_t __a, const int __b)
+{
+ return __builtin_aarch64_fcvtzsv2df (__a, __b);
+}
+
+__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
+vcvtq_n_u64_f64 (float64x2_t __a, const int __b)
+{
+ return __builtin_aarch64_fcvtzuv2df_uss (__a, __b);
+}
+
/* vcvt (<u>int -> float) */
__extension__ static __inline float64_t __attribute__ ((__always_inline__))
diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
index 2d59bed99b9d269c656e5c451246a16a7e13b8b8..e8fbb1281dec2e8f37f58ef2ced792dd62e3b5aa 100644
--- a/gcc/config/aarch64/iterators.md
+++ b/gcc/config/aarch64/iterators.md
@@ -154,6 +154,12 @@
;; Vector modes for S type.
(define_mode_iterator VDQ_SI [V2SI V4SI])
+;; Vector modes for S and D
+(define_mode_iterator VDQ_SDI [V2SI V4SI V2DI])
+
+;; Scalar and Vector modes for S and D
+(define_mode_iterator VSDQ_SDI [V2SI V4SI V2DI SI DI])
+
;; Vector modes for Q and H types.
(define_mode_iterator VDQQH [V8QI V16QI V4HI V8HI])
@@ -649,8 +655,10 @@
[(QI "b") (HI "h") (SI "") (DI "")])
(define_mode_attr fcvt_target [(V2DF "v2di") (V4SF "v4si") (V2SF "v2si")
+ (V2DI "v2df") (V4SI "v4sf") (V2SI "v2sf")
(SF "si") (DF "di") (SI "sf") (DI "df")])
(define_mode_attr FCVT_TARGET [(V2DF "V2DI") (V4SF "V4SI") (V2SF "V2SI")
+ (V2DI "V2DF") (V4SI "V4SF") (V2SI "V2SF")
(SF "SI") (DF "DI") (SI "SF") (DI "DF")])
