This patch adds vec_load_lanes and vec_store_lanes patterns for NEON.
They feed directly into the corresponding intrinsic patterns.
Tested on x86_64-linux-gnu and arm-linux-gnueabi. OK to install?
Richard
gcc/
* config/arm/neon.md (vec_load_lanes<mode><mode>): New expanders,
(vec_store_lanes<mode><mode>): Likewise.
Index: gcc/config/arm/neon.md
===================================================================
--- gcc/config/arm/neon.md 2011-04-12 11:54:04.000000000 +0100
+++ gcc/config/arm/neon.md 2011-04-12 11:55:11.000000000 +0100
@@ -4258,6 +4258,12 @@ (define_expand "neon_vreinterpretv2di<mo
DONE;
})
+(define_expand "vec_load_lanes<mode><mode>"
+ [(set (match_operand:VDQX 0 "s_register_operand")
+ (unspec:VDQX [(match_operand:VDQX 1 "neon_struct_operand")]
+ UNSPEC_VLD1))]
+ "TARGET_NEON")
+
(define_insn "neon_vld1<mode>"
[(set (match_operand:VDQX 0 "s_register_operand" "=w")
(unspec:VDQX [(match_operand:VDQX 1 "neon_struct_operand" "Um")]
@@ -4355,6 +4361,12 @@ (define_insn "neon_vld1_dup<mode>"
(const_string "neon_vld1_1_2_regs")))]
)
+(define_expand "vec_store_lanes<mode><mode>"
+ [(set (match_operand:VDQX 0 "neon_struct_operand")
+ (unspec:VDQX [(match_operand:VDQX 1 "s_register_operand")]
+ UNSPEC_VST1))]
+ "TARGET_NEON")
+
(define_insn "neon_vst1<mode>"
[(set (match_operand:VDQX 0 "neon_struct_operand" "=Um")
(unspec:VDQX [(match_operand:VDQX 1 "s_register_operand" "w")]
@@ -4411,6 +4423,13 @@ (define_insn "neon_vst1_lane<mode>"
[(set_attr "neon_type" "neon_vst1_vst2_lane")]
)
+(define_expand "vec_load_lanesti<mode>"
+ [(set (match_operand:TI 0 "s_register_operand")
+ (unspec:TI [(match_operand:TI 1 "neon_struct_operand")
+ (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ UNSPEC_VLD2))]
+ "TARGET_NEON")
+
(define_insn "neon_vld2<mode>"
[(set (match_operand:TI 0 "s_register_operand" "=w")
(unspec:TI [(match_operand:TI 1 "neon_struct_operand" "Um")
@@ -4429,6 +4448,13 @@ (define_insn "neon_vld2<mode>"
(const_string "neon_vld2_2_regs_vld1_vld2_all_lanes")))]
)
+(define_expand "vec_load_lanesoi<mode>"
+ [(set (match_operand:OI 0 "s_register_operand")
+ (unspec:OI [(match_operand:OI 1 "neon_struct_operand")
+ (unspec:VQ [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ UNSPEC_VLD2))]
+ "TARGET_NEON")
+
(define_insn "neon_vld2<mode>"
[(set (match_operand:OI 0 "s_register_operand" "=w")
(unspec:OI [(match_operand:OI 1 "neon_struct_operand" "Um")
@@ -4511,6 +4537,13 @@ (define_insn "neon_vld2_dup<mode>"
(const_string "neon_vld1_1_2_regs")))]
)
+(define_expand "vec_store_lanesti<mode>"
+ [(set (match_operand:TI 0 "neon_struct_operand")
+ (unspec:TI [(match_operand:TI 1 "s_register_operand")
+ (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ UNSPEC_VST2))]
+ "TARGET_NEON")
+
(define_insn "neon_vst2<mode>"
[(set (match_operand:TI 0 "neon_struct_operand" "=Um")
(unspec:TI [(match_operand:TI 1 "s_register_operand" "w")
@@ -4529,6 +4562,13 @@ (define_insn "neon_vst2<mode>"
(const_string "neon_vst1_1_2_regs_vst2_2_regs")))]
)
+(define_expand "vec_store_lanesoi<mode>"
+ [(set (match_operand:OI 0 "neon_struct_operand")
+ (unspec:OI [(match_operand:OI 1 "s_register_operand")
+ (unspec:VQ [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ UNSPEC_VST2))]
+ "TARGET_NEON")
+
(define_insn "neon_vst2<mode>"
[(set (match_operand:OI 0 "neon_struct_operand" "=Um")
(unspec:OI [(match_operand:OI 1 "s_register_operand" "w")
@@ -4594,6 +4634,13 @@ (define_insn "neon_vst2_lane<mode>"
[(set_attr "neon_type" "neon_vst1_vst2_lane")]
)
+(define_expand "vec_load_lanesei<mode>"
+ [(set (match_operand:EI 0 "s_register_operand")
+ (unspec:EI [(match_operand:EI 1 "neon_struct_operand")
+ (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ UNSPEC_VLD3))]
+ "TARGET_NEON")
+
(define_insn "neon_vld3<mode>"
[(set (match_operand:EI 0 "s_register_operand" "=w")
(unspec:EI [(match_operand:EI 1 "neon_struct_operand" "Um")
@@ -4612,6 +4659,16 @@ (define_insn "neon_vld3<mode>"
(const_string "neon_vld3_vld4")))]
)
+(define_expand "vec_load_lanesci<mode>"
+ [(match_operand:CI 0 "s_register_operand")
+ (match_operand:CI 1 "neon_struct_operand")
+ (unspec:VQ [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ "TARGET_NEON"
+{
+ emit_insn (gen_neon_vld3<mode> (operands[0], operands[1]));
+ DONE;
+})
+
(define_expand "neon_vld3<mode>"
[(match_operand:CI 0 "s_register_operand")
(match_operand:CI 1 "neon_struct_operand")
@@ -4751,6 +4808,13 @@ (define_insn "neon_vld3_dup<mode>"
(const_string "neon_vld3_vld4_all_lanes")
(const_string "neon_vld1_1_2_regs")))])
+(define_expand "vec_store_lanesei<mode>"
+ [(set (match_operand:EI 0 "neon_struct_operand")
+ (unspec:EI [(match_operand:EI 1 "s_register_operand")
+ (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ UNSPEC_VST3))]
+ "TARGET_NEON")
+
(define_insn "neon_vst3<mode>"
[(set (match_operand:EI 0 "neon_struct_operand" "=Um")
(unspec:EI [(match_operand:EI 1 "s_register_operand" "w")
@@ -4768,6 +4832,16 @@ (define_insn "neon_vst3<mode>"
(const_string "neon_vst1_1_2_regs_vst2_2_regs")
(const_string "neon_vst2_4_regs_vst3_vst4")))])
+(define_expand "vec_store_lanesci<mode>"
+ [(match_operand:CI 0 "neon_struct_operand")
+ (match_operand:CI 1 "s_register_operand")
+ (unspec:VQ [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ "TARGET_NEON"
+{
+ emit_insn (gen_neon_vst3<mode> (operands[0], operands[1]));
+ DONE;
+})
+
(define_expand "neon_vst3<mode>"
[(match_operand:CI 0 "neon_struct_operand")
(match_operand:CI 1 "s_register_operand")
@@ -4879,6 +4953,13 @@ (define_insn "neon_vst3_lane<mode>"
}
[(set_attr "neon_type" "neon_vst3_vst4_lane")])
+(define_expand "vec_load_lanesoi<mode>"
+ [(set (match_operand:OI 0 "s_register_operand")
+ (unspec:OI [(match_operand:OI 1 "neon_struct_operand")
+ (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ UNSPEC_VLD4))]
+ "TARGET_NEON")
+
(define_insn "neon_vld4<mode>"
[(set (match_operand:OI 0 "s_register_operand" "=w")
(unspec:OI [(match_operand:OI 1 "neon_struct_operand" "Um")
@@ -4897,6 +4978,16 @@ (define_insn "neon_vld4<mode>"
(const_string "neon_vld3_vld4")))]
)
+(define_expand "vec_load_lanesxi<mode>"
+ [(match_operand:XI 0 "s_register_operand")
+ (match_operand:XI 1 "neon_struct_operand")
+ (unspec:VQ [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ "TARGET_NEON"
+{
+ emit_insn (gen_neon_vld4<mode> (operands[0], operands[1]));
+ DONE;
+})
+
(define_expand "neon_vld4<mode>"
[(match_operand:XI 0 "s_register_operand")
(match_operand:XI 1 "neon_struct_operand")
@@ -5043,6 +5134,13 @@ (define_insn "neon_vld4_dup<mode>"
(const_string "neon_vld1_1_2_regs")))]
)
+(define_expand "vec_store_lanesoi<mode>"
+ [(set (match_operand:OI 0 "neon_struct_operand")
+ (unspec:OI [(match_operand:OI 1 "s_register_operand")
+ (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ UNSPEC_VST4))]
+ "TARGET_NEON")
+
(define_insn "neon_vst4<mode>"
[(set (match_operand:OI 0 "neon_struct_operand" "=Um")
(unspec:OI [(match_operand:OI 1 "s_register_operand" "w")
@@ -5061,6 +5159,16 @@ (define_insn "neon_vst4<mode>"
(const_string "neon_vst2_4_regs_vst3_vst4")))]
)
+(define_expand "vec_store_lanesxi<mode>"
+ [(match_operand:XI 0 "neon_struct_operand")
+ (match_operand:XI 1 "s_register_operand")
+ (unspec:VQ [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ "TARGET_NEON"
+{
+ emit_insn (gen_neon_vst4<mode> (operands[0], operands[1]));
+ DONE;
+})
+
(define_expand "neon_vst4<mode>"
[(match_operand:XI 0 "neon_struct_operand")
(match_operand:XI 1 "s_register_operand")
