case ARM_PCS_SIMD:
/* The vector PCS saves the low 128 bits (which is the full
register on non-SVE targets). */
- return TFmode;
+ return V16QImode;
case ARM_PCS_SVE:
/* Use vectors of DImode for registers that need frame
return gen_storewb_pairtf_di (base, base, reg, reg2,
GEN_INT (-adjustment),
GEN_INT (UNITS_PER_VREG - adjustment));
+ case E_V16QImode:
+ return gen_storewb_pairv16qi_di (base, base, reg, reg2,
+ GEN_INT (-adjustment),
+ GEN_INT (UNITS_PER_VREG - adjustment));
default:
gcc_unreachable ();
}
case E_TFmode:
return gen_loadwb_pairtf_di (base, base, reg, reg2, GEN_INT (adjustment),
GEN_INT (UNITS_PER_VREG));
+ case E_V16QImode:
+ return gen_loadwb_pairv16qi_di (base, base, reg, reg2,
+ GEN_INT (adjustment),
+ GEN_INT (UNITS_PER_VREG));
default:
gcc_unreachable ();
}
case E_V4SImode:
return gen_load_pairv4siv4si (reg1, mem1, reg2, mem2);
+ case E_V16QImode:
+ return gen_load_pairv16qiv16qi (reg1, mem1, reg2, mem2);
+
default:
gcc_unreachable ();
}
[(set_attr "type" "neon_load1_2reg")]
)
-(define_insn "loadwb_pair<TX:mode>_<P:mode>"
+(define_insn "loadwb_pair<TX_V16QI:mode>_<P:mode>"
[(parallel
[(set (match_operand:P 0 "register_operand" "=k")
- (plus:P (match_operand:P 1 "register_operand" "0")
- (match_operand:P 4 "aarch64_mem_pair_offset" "n")))
- (set (match_operand:TX 2 "register_operand" "=w")
- (mem:TX (match_dup 1)))
- (set (match_operand:TX 3 "register_operand" "=w")
- (mem:TX (plus:P (match_dup 1)
+ (plus:P (match_operand:P 1 "register_operand" "0")
+ (match_operand:P 4 "aarch64_mem_pair_offset" "n")))
+ (set (match_operand:TX_V16QI 2 "register_operand" "=w")
+ (mem:TX_V16QI (match_dup 1)))
+ (set (match_operand:TX_V16QI 3 "register_operand" "=w")
+ (mem:TX_V16QI (plus:P (match_dup 1)
(match_operand:P 5 "const_int_operand" "n"))))])]
- "TARGET_SIMD && INTVAL (operands[5]) == GET_MODE_SIZE (<TX:MODE>mode)"
+ "TARGET_SIMD
+ && known_eq (INTVAL (operands[5]), GET_MODE_SIZE (<TX_V16QI:MODE>mode))"
"ldp\\t%q2, %q3, [%1], %4"
[(set_attr "type" "neon_ldp_q")]
)
[(set_attr "type" "neon_store1_2reg<q>")]
)
-(define_insn "storewb_pair<TX:mode>_<P:mode>"
+(define_insn "storewb_pair<TX_V16QI:mode>_<P:mode>"
[(parallel
[(set (match_operand:P 0 "register_operand" "=&k")
- (plus:P (match_operand:P 1 "register_operand" "0")
- (match_operand:P 4 "aarch64_mem_pair_offset" "n")))
- (set (mem:TX (plus:P (match_dup 0)
+ (plus:P (match_operand:P 1 "register_operand" "0")
+ (match_operand:P 4 "aarch64_mem_pair_offset" "n")))
+ (set (mem:TX_V16QI (plus:P (match_dup 0)
(match_dup 4)))
- (match_operand:TX 2 "register_operand" "w"))
- (set (mem:TX (plus:P (match_dup 0)
+ (match_operand:TX_V16QI 2 "register_operand" "w"))
+ (set (mem:TX_V16QI (plus:P (match_dup 0)
(match_operand:P 5 "const_int_operand" "n")))
- (match_operand:TX 3 "register_operand" "w"))])]
+ (match_operand:TX_V16QI 3 "register_operand" "w"))])]
"TARGET_SIMD
- && INTVAL (operands[5])
- == INTVAL (operands[4]) + GET_MODE_SIZE (<TX:MODE>mode)"
+ && known_eq (INTVAL (operands[5]),
+ INTVAL (operands[4]) + GET_MODE_SIZE (<TX_V16QI:MODE>mode))"
"stp\\t%q2, %q3, [%0, %4]!"
[(set_attr "type" "neon_stp_q")]
)
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target fopenmp } */
+/* { dg-options "-ffast-math -fstack-protector-strong -fopenmp" } */
+typedef struct {
+ long size_z;
+ int width;
+} dt_bilateral_t;
+typedef float dt_aligned_pixel_t[4];
+#pragma omp declare simd
+void dt_bilateral_splat(dt_bilateral_t *b) {
+ float *buf;
+ long offsets[8];
+ for (; b;) {
+ int firstrow;
+ for (int j = firstrow; j; j++)
+ for (int i; i < b->width; i++) {
+ dt_aligned_pixel_t contrib;
+ for (int k = 0; k < 4; k++)
+ buf[offsets[k]] += contrib[k];
+ }
+ float *dest;
+ for (int j = (long)b; j; j++) {
+ float *src = (float *)b->size_z;
+ for (int i = 0; i < (long)b; i++)
+ dest[i] += src[i];
+ }
+ }
+}