> >>
> >> int32x4_t foo(int32x4_t x) {
> >> return vshlq_s32(x, vdupq_n_s32(256)); }
> >>
> >> should fold to “x” (if we fold it at all). Similarly:
> >>
> >> int32x4_t foo(int32x4_t x) {
> >> return vshlq_s32(x, vdupq_n_s32(257)); }
> >>
> >> should fold to x << 1 (again if we fold it at all).
> >>
> >> For a shift right:
> >>
> >> int32x4_t foo(int32x4_t x) {
> >> return vshlq_s32(x, vdupq_n_s32(-64)); }
> >>
> >> is equivalent to:
> >>
> >> int32x4_t foo(int32x4_t x) {
> >> return vshrq_n_s32(x, 31);
> >> }
> >>
> >> and so it shouldn't fold to 0.
> >
> > And here I thought I had read the specs very carefully...
> >
> > I will punt on them because I don't think those ranged are common at all.
>
> Sounds good.
>
> There were other review comments further down the message (I should
> have been clearer about that, sorry). Could you have a look at those too?
>
Yes sorry I had missed those.
> > + }
> > + break;
> > + BUILTIN_VSDQ_I_DI (BINOP, sshl, 0, NONE)
> > + BUILTIN_VSDQ_I_DI (BINOP_UUS, ushl, 0, NONE)
> > + {
> > + tree cst = args[1];
> > + tree ctype = TREE_TYPE (cst);
> > + HOST_WIDE_INT bits = GET_MODE_UNIT_BITSIZE (TYPE_MODE (TREE_TYPE
> > (args[0])));
> > + if (INTEGRAL_TYPE_P (ctype)
> > + && TREE_CODE (cst) == INTEGER_CST)
>
> I don't think this works, since args[1] is a vector rather than a scalar.
> E.g. trying locally:
The _x1_t types are treated as scalar, not vectors, so both are needed.
My original patch tested the scalar variant which is why this is here.
I added vector one.
Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.
Ok for master?
Thanks,
Tamar
gcc/ChangeLog:
* config/aarch64/aarch64-builtins.c
(aarch64_general_gimple_fold_builtin): Add ashl, sshl, ushl, ashr,
ashr_simd, lshr, lshr_simd.
* config/aarch64/aarch64-simd-builtins.def (lshr): Use USHIFTIMM.
* config/aarch64/arm_neon.h (vshr_n_u8, vshr_n_u16, vshr_n_u32,
vshrq_n_u8, vshrq_n_u16, vshrq_n_u32, vshrq_n_u64): Fix type hack.
gcc/testsuite/ChangeLog:
* gcc.target/aarch64/advsimd-intrinsics/vshl-opt-1.c: New test.
* gcc.target/aarch64/advsimd-intrinsics/vshl-opt-2.c: New test.
* gcc.target/aarch64/advsimd-intrinsics/vshl-opt-3.c: New test.
* gcc.target/aarch64/advsimd-intrinsics/vshl-opt-4.c: New test.
* gcc.target/aarch64/advsimd-intrinsics/vshl-opt-5.c: New test.
* gcc.target/aarch64/advsimd-intrinsics/vshl-opt-6.c: New test.
* gcc.target/aarch64/advsimd-intrinsics/vshl-opt-7.c: New test.
* gcc.target/aarch64/advsimd-intrinsics/vshl-opt-8.c: New test.
* gcc.target/aarch64/signbit-2.c: New test.
--- inline copy of patch ---
diff --git a/gcc/config/aarch64/aarch64-builtins.c
b/gcc/config/aarch64/aarch64-builtins.c
index
f6b41d9c200d6300dee65ba60ae94488231a8a38..41da13f82f8cfe0de3c56e62fe884ffabf315ef9
100644
--- a/gcc/config/aarch64/aarch64-builtins.c
+++ b/gcc/config/aarch64/aarch64-builtins.c
@@ -2394,6 +2394,89 @@ aarch64_general_gimple_fold_builtin (unsigned int fcode,
gcall *stmt)
1, args[0]);
gimple_call_set_lhs (new_stmt, gimple_call_lhs (stmt));
break;
+ BUILTIN_VSDQ_I_DI (BINOP, ashl, 3, NONE)
+ {
+ tree cst = args[1];
+ tree ctype = TREE_TYPE (cst);
+ if (TREE_CODE (cst) == INTEGER_CST)
+ {
+ wide_int wcst = wi::to_wide (cst);
+ if (wi::geu_p (wi::abs (wcst), element_precision (args[0])))
+ break;
+
+ if (wi::neg_p (wcst, TYPE_SIGN (ctype)))
+ new_stmt =
+ gimple_build_assign (gimple_call_lhs (stmt),
+ RSHIFT_EXPR, args[0],
+ wide_int_to_tree (ctype,
+ wi::abs (wcst)));
+ else
+ new_stmt =
+ gimple_build_assign (gimple_call_lhs (stmt),
+ LSHIFT_EXPR, args[0], args[1]);
+ }
+ }
+ break;
+ BUILTIN_VSDQ_I_DI (BINOP, sshl, 0, NONE)
+ BUILTIN_VSDQ_I_DI (BINOP_UUS, ushl, 0, NONE)
+ {
+ tree cst = args[1];
+ tree ctype = TREE_TYPE (cst);
+ /* Left shifts can be both scalar or vector, e.g. uint64x1_t is
+ treated as a scalar type not a vector one. */
+ if ((VECTOR_INTEGER_TYPE_P (ctype)
+ && uniform_vector_p (cst))
+ || TREE_CODE (cst) == INTEGER_CST)
+ {
+ wide_int wcst;
+ tree unit_ty;
+ if (TREE_CODE (cst) == INTEGER_CST)
+ {
+ wcst = wi::to_wide (cst);
+ unit_ty = TREE_TYPE (cst);
+ }
+ else
+ {
+ tree tmp = vector_cst_elt (cst, 0);
+ wcst = wi::to_wide (tmp);
+ unit_ty = TREE_TYPE (tmp);
+ }
+
+ wide_int abs_cst = wi::abs (wcst);
+ if (wi::geu_p (wi::abs (wcst), element_precision (args[0])))
+ break;
+
+ if (wi::neg_p (wcst, TYPE_SIGN (ctype)))
+ {
+ tree final_cst;
+ final_cst = wide_int_to_tree (unit_ty, abs_cst);
+ if (TREE_CODE (cst) != INTEGER_CST)
+ final_cst = build_uniform_cst (ctype, final_cst);
+
+ new_stmt =
+ gimple_build_assign (gimple_call_lhs (stmt),
+ RSHIFT_EXPR, args[0], final_cst);
+ }
+ else
+ new_stmt =
+ gimple_build_assign (gimple_call_lhs (stmt),
+ LSHIFT_EXPR, args[0], args[1]);
+ }
+ }
+ break;
+ BUILTIN_VDQ_I (SHIFTIMM, ashr, 3, NONE)
+ VAR1 (SHIFTIMM, ashr_simd, 0, NONE, di)
+ BUILTIN_VDQ_I (USHIFTIMM, lshr, 3, NONE)
+ VAR1 (USHIFTIMM, lshr_simd, 0, NONE, di)
+ {
+ tree cst = args[1];
+ if (TREE_CODE (cst) == INTEGER_CST
+ && wi::leu_p (wi::to_wide (cst), element_precision (args[0]) - 1)
+ && wi::geu_p (wi::to_wide (cst), 0))
+ new_stmt = gimple_build_assign (gimple_call_lhs (stmt),
+ RSHIFT_EXPR, args[0], args[1]);
+ }
+ break;
BUILTIN_GPF (BINOP, fmulx, 0, ALL)
{
gcc_assert (nargs == 2);
diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def
b/gcc/config/aarch64/aarch64-simd-builtins.def
index
402453aa9bba5949da43c984c4603196b1efd092..bbe0a4a3c4aea4187e7b1a9f10ab60e79df7b138
100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -409,7 +409,7 @@
BUILTIN_VDQ_I (SHIFTIMM, ashr, 3, NONE)
VAR1 (SHIFTIMM, ashr_simd, 0, NONE, di)
- BUILTIN_VDQ_I (SHIFTIMM, lshr, 3, NONE)
+ BUILTIN_VDQ_I (USHIFTIMM, lshr, 3, NONE)
VAR1 (USHIFTIMM, lshr_simd, 0, NONE, di)
/* Implemented by aarch64_<sur>shr_n<mode>. */
BUILTIN_VSDQ_I_DI (SHIFTIMM, srshr_n, 0, NONE)
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index
635a223b59eb0f64304351939d444411b697af81..c4ef5f7f7e3658c830893931ef5a874842410e10
100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -27400,21 +27400,21 @@ __extension__ extern __inline uint8x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vshr_n_u8 (uint8x8_t __a, const int __b)
{
- return (uint8x8_t) __builtin_aarch64_lshrv8qi ((int8x8_t) __a, __b);
+ return __builtin_aarch64_lshrv8qi_uus (__a, __b);
}
__extension__ extern __inline uint16x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vshr_n_u16 (uint16x4_t __a, const int __b)
{
- return (uint16x4_t) __builtin_aarch64_lshrv4hi ((int16x4_t) __a, __b);
+ return __builtin_aarch64_lshrv4hi_uus (__a, __b);
}
__extension__ extern __inline uint32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vshr_n_u32 (uint32x2_t __a, const int __b)
{
- return (uint32x2_t) __builtin_aarch64_lshrv2si ((int32x2_t) __a, __b);
+ return __builtin_aarch64_lshrv2si_uus (__a, __b);
}
__extension__ extern __inline uint64x1_t
@@ -27456,28 +27456,28 @@ __extension__ extern __inline uint8x16_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vshrq_n_u8 (uint8x16_t __a, const int __b)
{
- return (uint8x16_t) __builtin_aarch64_lshrv16qi ((int8x16_t) __a, __b);
+ return __builtin_aarch64_lshrv16qi_uus (__a, __b);
}
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vshrq_n_u16 (uint16x8_t __a, const int __b)
{
- return (uint16x8_t) __builtin_aarch64_lshrv8hi ((int16x8_t) __a, __b);
+ return __builtin_aarch64_lshrv8hi_uus (__a, __b);
}
__extension__ extern __inline uint32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vshrq_n_u32 (uint32x4_t __a, const int __b)
{
- return (uint32x4_t) __builtin_aarch64_lshrv4si ((int32x4_t) __a, __b);
+ return __builtin_aarch64_lshrv4si_uus (__a, __b);
}
__extension__ extern __inline uint64x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vshrq_n_u64 (uint64x2_t __a, const int __b)
{
- return (uint64x2_t) __builtin_aarch64_lshrv2di ((int64x2_t) __a, __b);
+ return __builtin_aarch64_lshrv2di_uus (__a, __b);
}
__extension__ extern __inline int64_t
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-1.c
b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-1.c
new file mode 100644
index
0000000000000000000000000000000000000000..31cc9e2319aadf5414fa32edc40094c1fc579db5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-1.c
@@ -0,0 +1,11 @@
+/* { dg-do assemble } */
+/* { dg-additional-options "--save-temps" } */
+
+#include <arm_neon.h>
+
+uint8x8_t foo (uint8x8_t a)
+{
+ return vshr_n_u8 (a, 2);
+}
+
+/* { dg-final { scan-assembler-times {\tushr\t.+, 2} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-2.c
b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-2.c
new file mode 100644
index
0000000000000000000000000000000000000000..0b48c67f02e77c2c2ecb469537f8f376b48d9074
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-2.c
@@ -0,0 +1,11 @@
+/* { dg-do assemble } */
+/* { dg-additional-options "--save-temps" } */
+
+#include <arm_neon.h>
+
+int16x8_t foo (int16x8_t a)
+{
+ return vshrq_n_s16 (a, 8);
+}
+
+/* { dg-final { scan-assembler-times {\tsshr\t.+, 8} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-3.c
b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-3.c
new file mode 100644
index
0000000000000000000000000000000000000000..2ea15b4c0fffdb02b8af4c576a5b3e8757fa8b23
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-3.c
@@ -0,0 +1,11 @@
+/* { dg-do assemble } */
+/* { dg-additional-options "--save-temps" } */
+
+#include <arm_neon.h>
+
+int16x8_t foo (int16x8_t a)
+{
+ return vshrq_n_s16 (a, 16);
+}
+
+/* { dg-final { scan-assembler-times {\tsshr\t.+, 16} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-4.c
b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-4.c
new file mode 100644
index
0000000000000000000000000000000000000000..e26a1e422781577bc42ac22e7c993a8093e44925
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-4.c
@@ -0,0 +1,11 @@
+/* { dg-do assemble } */
+/* { dg-additional-options "--save-temps" } */
+
+#include <arm_neon.h>
+
+int64x1_t foo (int64x1_t a)
+{
+ return vshl_s64 (a, vdup_n_s64(80));
+}
+
+/* { dg-final { scan-assembler-times {\tsshl\t.+, d[0-9]+} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-5.c
b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-5.c
new file mode 100644
index
0000000000000000000000000000000000000000..1444f3a6420aef0d88dba57f2334992b183098ff
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-5.c
@@ -0,0 +1,12 @@
+/* { dg-do assemble } */
+/* { dg-additional-options "--save-temps" } */
+/* { dg-skip-if "no optimizations" { *-*-* } { "-O0" } { "" } } */
+
+#include <arm_neon.h>
+
+int64x1_t foo (int64x1_t a)
+{
+ return vshl_s64 (a, vdup_n_s64(-6));
+}
+
+/* { dg-final { scan-assembler-times {\tsshr\t.+, 6} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-6.c
b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-6.c
new file mode 100644
index
0000000000000000000000000000000000000000..4ff493f96bdd9461042683f3373c05103d4a9d8f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-6.c
@@ -0,0 +1,10 @@
+/* { dg-do assemble } */
+/* { dg-additional-options "--save-temps" } */
+
+#include <arm_neon.h>
+
+int32x4_t foo (int32x4_t x) {
+ return vshlq_s32(x, vdupq_n_s32(256));
+}
+
+/* { dg-final { scan-assembler-times {\tsshl\t.+, v[0-9].4s} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-7.c
b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-7.c
new file mode 100644
index
0000000000000000000000000000000000000000..76a73ba812a853541a93e2024b166e34ff540d08
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-7.c
@@ -0,0 +1,12 @@
+/* { dg-do assemble } */
+/* { dg-additional-options "--save-temps" } */
+/* { dg-skip-if "no optimizations" { *-*-* } { "-O0" } { "" } } */
+
+#include <arm_neon.h>
+
+int32x4_t foo (int32x4_t x) {
+ return vshlq_s32(vdupq_n_s32(1), vdupq_n_s32(10));
+}
+
+/* { dg-final { scan-assembler-not {\tsshl\t} } } */
+/* { dg-final { scan-assembler-times {\tmovi\t} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-8.c
b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-8.c
new file mode 100644
index
0000000000000000000000000000000000000000..27de3498f5321eee68fa0f1288b66bb11014c4e3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vshl-opt-8.c
@@ -0,0 +1,10 @@
+/* { dg-do assemble } */
+/* { dg-additional-options "--save-temps" } */
+
+#include <arm_neon.h>
+
+int32x4_t foo (int32x4_t x) {
+ return vshlq_s32(x, vdupq_n_s32(-64));
+}
+
+/* { dg-final { scan-assembler-times {\tsshl\t.+, v[0-9]+.4s} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/signbit-2.c
b/gcc/testsuite/gcc.target/aarch64/signbit-2.c
new file mode 100644
index
0000000000000000000000000000000000000000..e4e9afc854317cb599fa8118a1117c5a52e6f497
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/signbit-2.c
@@ -0,0 +1,36 @@
+/* { dg-do assemble } */
+/* { dg-options "-O1 --save-temps" } */
+
+#include <arm_neon.h>
+
+int32x2_t foo1 (int32x2_t a)
+{
+ return vshr_n_s32 (vneg_s32 (a), 31);
+}
+
+int32x4_t foo2 (int32x4_t a)
+{
+ return vshrq_n_s32 (vnegq_s32 (a), 31);
+}
+
+int16x8_t foo3 (int16x8_t a)
+{
+ return vshrq_n_s16 (vnegq_s16 (a), 15);
+}
+
+int16x4_t foo4 (int16x4_t a)
+{
+ return vshr_n_s16 (vneg_s16 (a), 15);
+}
+
+int8x16_t foo5 (int8x16_t a)
+{
+ return vshrq_n_s8 (vnegq_s8 (a), 7);
+}
+
+int8x8_t foo6 (int8x8_t a)
+{
+ return vshr_n_s8 (vneg_s8 (a), 7);
+}
+
+/* { dg-final { scan-assembler-times {\tcmgt\t} 6 } } */
rb14935.patch
Description: rb14935.patch
