[(set_attr "type" "mve_move")
])
+(define_insn "mve_vec_unpack<US>_lo_<mode>"
+ [(set (match_operand:<V_unpack> 0 "register_operand" "=w")
+ (SE:<V_unpack> (vec_select:<V_HALF>
+ (match_operand:MVE_3 1 "register_operand" "w")
+ (match_operand:MVE_3 2 "vect_par_constant_low" ""))))]
+ "TARGET_HAVE_MVE"
+ "vmovlb.<US>%#<V_sz_elem> %q0, %q1"
+ [(set_attr "type" "mve_move")]
+)
+
+(define_insn "mve_vec_unpack<US>_hi_<mode>"
+ [(set (match_operand:<V_unpack> 0 "register_operand" "=w")
+ (SE:<V_unpack> (vec_select:<V_HALF>
+ (match_operand:MVE_3 1 "register_operand" "w")
+ (match_operand:MVE_3 2 "vect_par_constant_high" ""))))]
+ "TARGET_HAVE_MVE"
+ "vmovlt.<US>%#<V_sz_elem> %q0, %q1"
+ [(set_attr "type" "mve_move")]
+)
+
;;
;; [vcvtpq_s, vcvtpq_u])
;;
[(set_attr "type" "mve_move")
])
+;; vmovnb pattern used by the vec_pack_trunc expander to avoid the
+;; need for an uninitialized input operand.
+(define_insn "@mve_vec_pack_trunc_lo_<mode>"
+ [
+ (set (match_operand:<V_narrow_pack> 0 "s_register_operand" "=w")
+ (unspec:<V_narrow_pack> [(match_operand:MVE_5 1 "s_register_operand" "w")]
+ VMOVNBQ_S))
+ ]
+ "TARGET_HAVE_MVE"
+ "vmovnb.i%#<V_sz_elem> %q0, %q1"
+ [(set_attr "type" "mve_move")
+])
+
;;
;; [vmovntq_s, vmovntq_u])
;;
-(define_insn "mve_vmovntq_<supf><mode>"
+(define_insn "@mve_vmovntq_<supf><mode>"
[
(set (match_operand:<V_narrow_pack> 0 "s_register_operand" "=w")
(unspec:<V_narrow_pack> [(match_operand:<V_narrow_pack> 1 "s_register_operand" "0")
[(set_attr "type" "neon_shift_imm_long")]
)
-(define_expand "vec_unpack<US>_hi_<mode>"
- [(match_operand:<V_unpack> 0 "register_operand")
- (SE:<V_unpack> (match_operand:VU 1 "register_operand"))]
- "TARGET_NEON && !BYTES_BIG_ENDIAN"
- {
- rtvec v = rtvec_alloc (<V_mode_nunits>/2) ;
- rtx t1;
- int i;
- for (i = 0; i < (<V_mode_nunits>/2); i++)
- RTVEC_ELT (v, i) = GEN_INT ((<V_mode_nunits>/2) + i);
-
- t1 = gen_rtx_PARALLEL (<MODE>mode, v);
- emit_insn (gen_neon_vec_unpack<US>_hi_<mode> (operands[0],
- operands[1],
- t1));
- DONE;
- }
-)
-
-(define_expand "vec_unpack<US>_lo_<mode>"
- [(match_operand:<V_unpack> 0 "register_operand")
- (SE:<V_unpack> (match_operand:VU 1 "register_operand"))]
- "TARGET_NEON && !BYTES_BIG_ENDIAN"
- {
- rtvec v = rtvec_alloc (<V_mode_nunits>/2) ;
- rtx t1;
- int i;
- for (i = 0; i < (<V_mode_nunits>/2) ; i++)
- RTVEC_ELT (v, i) = GEN_INT (i);
- t1 = gen_rtx_PARALLEL (<MODE>mode, v);
- emit_insn (gen_neon_vec_unpack<US>_lo_<mode> (operands[0],
- operands[1],
- t1));
- DONE;
- }
-)
-
(define_insn "neon_vec_<US>mult_lo_<mode>"
[(set (match_operand:<V_unpack> 0 "register_operand" "=w")
(mult:<V_unpack> (SE:<V_unpack> (vec_select:<V_HALF>
; because the ordering of vector elements in Q registers is different from what
; the semantics of the instructions require.
-(define_insn "vec_pack_trunc_<mode>"
+(define_insn "neon_quad_vec_pack_trunc_<mode>"
[(set (match_operand:<V_narrow_pack> 0 "register_operand" "=&w")
(vec_concat:<V_narrow_pack>
(truncate:<V_narrow>
"ARM_HAVE_<MODE>_ARITH
&& !TARGET_REALLY_IWMMXT"
)
+
+;; vmovl[tb] are not available for V4SI on MVE
+(define_expand "vec_unpack<US>_hi_<mode>"
+ [(set (match_operand:<V_unpack> 0 "register_operand")
+ (SE:<V_unpack> (vec_select:<V_HALF>
+ (match_operand:VU 1 "register_operand")
+ (match_dup 2))))]
+ "ARM_HAVE_<MODE>_ARITH
+ && !TARGET_REALLY_IWMMXT
+ && ! (<MODE>mode == V4SImode && TARGET_HAVE_MVE)
+ && !BYTES_BIG_ENDIAN"
+ {
+ rtvec v = rtvec_alloc (<V_mode_nunits>/2);
+ int i;
+ for (i = 0; i < (<V_mode_nunits>/2); i++)
+ RTVEC_ELT (v, i) = GEN_INT ((<V_mode_nunits>/2) + i);
+
+ operands[2] = gen_rtx_PARALLEL (<MODE>mode, v);
+ }
+)
+
+;; vmovl[tb] are not available for V4SI on MVE
+(define_expand "vec_unpack<US>_lo_<mode>"
+ [(set (match_operand:<V_unpack> 0 "register_operand")
+ (SE:<V_unpack> (vec_select:<V_HALF>
+ (match_operand:VU 1 "register_operand")
+ (match_dup 2))))]
+ "ARM_HAVE_<MODE>_ARITH
+ && !TARGET_REALLY_IWMMXT
+ && ! (<MODE>mode == V4SImode && TARGET_HAVE_MVE)
+ && !BYTES_BIG_ENDIAN"
+ {
+ rtvec v = rtvec_alloc (<V_mode_nunits>/2);
+ int i;
+ for (i = 0; i < (<V_mode_nunits>/2) ; i++)
+ RTVEC_ELT (v, i) = GEN_INT (i);
+
+ operands[2] = gen_rtx_PARALLEL (<MODE>mode, v);
+
+ }
+)
+
+;; vmovn[tb] are not available for V2DI on MVE
+(define_expand "vec_pack_trunc_<mode>"
+ [(set (match_operand:<V_narrow_pack> 0 "register_operand")
+ (vec_concat:<V_narrow_pack>
+ (truncate:<V_narrow>
+ (match_operand:VN 1 "register_operand"))
+ (truncate:<V_narrow>
+ (match_operand:VN 2 "register_operand"))))]
+ "ARM_HAVE_<MODE>_ARITH
+ && !TARGET_REALLY_IWMMXT
+ && ! (<MODE>mode == V2DImode && TARGET_HAVE_MVE)
+ && !BYTES_BIG_ENDIAN"
+ {
+ if (TARGET_NEON)
+ {
+ emit_insn (gen_neon_quad_vec_pack_trunc_<mode> (operands[0], operands[1],
+ operands[2]));
+ }
+ else
+ {
+ rtx tmpreg = gen_reg_rtx (<V_narrow_pack>mode);
+ emit_insn (gen_mve_vec_pack_trunc_lo (<MODE>mode, tmpreg, operands[1]));
+ emit_insn (gen_mve_vmovntq (VMOVNTQ_S, <MODE>mode,
+ operands[0], tmpreg, operands[2]));
+ }
+ DONE;
+ }
+)
FUNC(s, int, 8, clz)
FUNC(u, uint, 8, clz)
-/* 16 and 8-bit versions are not vectorized because they need pack/unpack
- patterns since __builtin_clz uses 32-bit parameter and return value. */
-/* { dg-final { scan-assembler-times {vclz\.i32 q[0-9]+, q[0-9]+} 2 } } */
+/* 16 and 8-bit versions still use 32-bit intermediate temporaries, so for
+ instance instead of using vclz.i8, we need 4 vclz.i32, leading to a total of
+ 14 vclz.i32 expected in this testcase. */
+/* { dg-final { scan-assembler-times {vclz\.i32 q[0-9]+, q[0-9]+} 14 } } */
/* { dg-final { scan-assembler-times {vclz\.i16 q[0-9]+, q[0-9]+} 2 { xfail *-*-* } } } */
/* { dg-final { scan-assembler-times {vclz\.i8 q[0-9]+, q[0-9]+} 2 { xfail *-*-* } } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O3" } */
+
+#include <stdint.h>
+
+#define FUNC(SIGN, TYPE, DSTBITS, BITS, NAME) \
+ void test_ ## NAME ##_ ## SIGN ## BITS (TYPE##DSTBITS##_t * __restrict__ dest, \
+ TYPE##BITS##_t *a) { \
+ int i; \
+ for (i=0; i < (256 / BITS); i++) { \
+ dest[i] = a[i]; \
+ } \
+ }
+
+FUNC(s, int, 16, 32, pack)
+FUNC(u, uint, 16, 32, pack)
+FUNC(s, int, 8, 16, pack)
+FUNC(u, uint, 8, 16, pack)
+
+/* { dg-final { scan-assembler-times {vmovnt\.i32\tq[0-9]+, q[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vmovnb\.i32\tq[0-9]+, q[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vmovnt\.i16\tq[0-9]+, q[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {vmovnb\.i16\tq[0-9]+, q[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-not {vldr\.64\td[0-9]+, \.L} } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O3" } */
+
+#include <stdint.h>
+
+#define FUNC(SIGN, TYPE, DSTBITS, BITS, NAME) \
+ void test_ ## NAME ##_ ## SIGN ## BITS (TYPE##DSTBITS##_t * __restrict__ dest, \
+ TYPE##BITS##_t *a) { \
+ int i; \
+ for (i=0; i < (128 / BITS); i++) { \
+ dest[i] = a[i]; \
+ } \
+ }
+
+FUNC(s, int, 32, 16, unpack)
+FUNC(u, uint, 32, 16, unpack)
+FUNC(s, int, 16, 8, unpack)
+FUNC(u, uint, 16, 8, unpack)
+
+/* { dg-final { scan-assembler-times {vmovlt\.s16 q[0-9]+, q[0-9]+} 1 } } */
+/* { dg-final { scan-assembler-times {vmovlb\.s16 q[0-9]+, q[0-9]+} 1 } } */
+/* { dg-final { scan-assembler-times {vmovlt\.u16 q[0-9]+, q[0-9]+} 1 } } */
+/* { dg-final { scan-assembler-times {vmovlb\.u16 q[0-9]+, q[0-9]+} 1 } } */
+/* { dg-final { scan-assembler-times {vmovlt\.s8 q[0-9]+, q[0-9]+} 1 } } */
+/* { dg-final { scan-assembler-times {vmovlb\.s8 q[0-9]+, q[0-9]+} 1 } } */
+/* { dg-final { scan-assembler-times {vmovlt\.u8 q[0-9]+, q[0-9]+} 1 } } */
+/* { dg-final { scan-assembler-times {vmovlb\.u8 q[0-9]+, q[0-9]+} 1 } } */
/* MVE has only 128-bit vectors, so we can vectorize only half of the
functions above. */
/* We only emit vshl.u, which is equivalent to vshl.s anyway. */
-/* { dg-final { scan-assembler-times {vshl.u[0-9]+\tq[0-9]+, q[0-9]+} 2 } } */
+/* 16 and 8-bit versions still use 32-bit intermediate temporaries, so for
+ instance instead of using vshl.u8, we need 4 vshl.i32, leading to a total of
+ 14 vshl.i32 expected in this testcase. */
+/* { dg-final { scan-assembler-times {vshl.u[0-9]+\tq[0-9]+, q[0-9]+} 14 } } */
/* We emit vshl.i when the shift amount is an immediate. */
/* { dg-final { scan-assembler-times {vshl.i[0-9]+\tq[0-9]+, q[0-9]+} 6 } } */