Hi All,
This adds a simple pattern for combining right shifts and narrows into
shifted narrows.
i.e.
typedef short int16_t;
typedef unsigned short uint16_t;
void foo (uint16_t * restrict a, int16_t * restrict d, int n)
{
for( int i = 0; i < n; i++ )
d[i] = (a[i] * a[i]) >> 10;
}
now generates:
.L4:
ldr q0, [x0, x3]
umull v1.4s, v0.4h, v0.4h
umull2 v0.4s, v0.8h, v0.8h
shrn v1.4h, v1.4s, 10
shrn2 v1.8h, v0.4s, 10
str q1, [x1, x3]
add x3, x3, 16
cmp x4, x3
bne .L4
instead of:
.L4:
ldr q0, [x0, x3]
umull v1.4s, v0.4h, v0.4h
umull2 v0.4s, v0.8h, v0.8h
sshr v1.4s, v1.4s, 10
sshr v0.4s, v0.4s, 10
xtn v1.4h, v1.4s
xtn2 v1.8h, v0.4s
str q1, [x1, x3]
add x3, x3, 16
cmp x4, x3
bne .L4
Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.
Ok for master?
Thanks,
Tamar
gcc/ChangeLog:
* config/aarch64/aarch64-simd.md (*aarch64_<srn_op>shrn<mode>_vect,
*aarch64_<srn_op>shrn<mode>2_vect): New.
* config/aarch64/iterators.md (srn_op): New.
gcc/testsuite/ChangeLog:
* gcc.target/aarch64/shrn-combine.c: New test.
--- inline copy of patch --
diff --git a/gcc/config/aarch64/aarch64-simd.md
b/gcc/config/aarch64/aarch64-simd.md
index
48eddf64e05afe3788abfa05141f6544a9323ea1..d7b6cae424622d259f97a3d5fa9093c0fb0bd5ce
100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -1818,6 +1818,28 @@ (define_insn "aarch64_shrn<mode>_insn_be"
[(set_attr "type" "neon_shift_imm_narrow_q")]
)
+(define_insn "*aarch64_<srn_op>shrn<mode>_vect"
+ [(set (match_operand:<VNARROWQ> 0 "register_operand" "=w")
+ (truncate:<VNARROWQ>
+ (SHIFTRT:VQN (match_operand:VQN 1 "register_operand" "w")
+ (match_operand:VQN 2 "aarch64_simd_shift_imm_vec_<vn_mode>"))))]
+ "TARGET_SIMD"
+ "shrn\\t%0.<Vntype>, %1.<Vtype>, %2"
+ [(set_attr "type" "neon_shift_imm_narrow_q")]
+)
+
+(define_insn "*aarch64_<srn_op>shrn<mode>2_vect"
+ [(set (match_operand:<VNARROWQ2> 0 "register_operand" "=w")
+ (vec_concat:<VNARROWQ2>
+ (match_operand:<VNARROWQ> 1 "register_operand" "0")
+ (truncate:<VNARROWQ>
+ (SHIFTRT:VQN (match_operand:VQN 2 "register_operand" "w")
+ (match_operand:VQN 3 "aarch64_simd_shift_imm_vec_<vn_mode>")))))]
+ "TARGET_SIMD"
+ "shrn2\\t%0.<V2ntype>, %2.<Vtype>, %3"
+ [(set_attr "type" "neon_shift_imm_narrow_q")]
+)
+
(define_expand "aarch64_shrn<mode>"
[(set (match_operand:<VNARROWQ> 0 "register_operand")
(truncate:<VNARROWQ>
diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
index
caa42f8f169fbf2cf46a90cf73dee05619acc300..8dbeed3b0d4a44cdc17dd333ed397b39a33f386a
100644
--- a/gcc/config/aarch64/iterators.md
+++ b/gcc/config/aarch64/iterators.md
@@ -2003,6 +2003,9 @@ (define_code_attr shift [(ashift "lsl") (ashiftrt "asr")
;; Op prefix for shift right and accumulate.
(define_code_attr sra_op [(ashiftrt "s") (lshiftrt "u")])
+;; op prefix for shift right and narrow.
+(define_code_attr srn_op [(ashiftrt "r") (lshiftrt "")])
+
;; Map shift operators onto underlying bit-field instructions
(define_code_attr bfshift [(ashift "ubfiz") (ashiftrt "sbfx")
(lshiftrt "ubfx") (rotatert "extr")])
diff --git a/gcc/testsuite/gcc.target/aarch64/shrn-combine.c
b/gcc/testsuite/gcc.target/aarch64/shrn-combine.c
new file mode 100644
index
0000000000000000000000000000000000000000..0187f49f4dcc76182c90366caaf00d294e835707
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/shrn-combine.c
@@ -0,0 +1,14 @@
+/* { dg-do assemble } */
+/* { dg-options "-O3 --save-temps --param=vect-epilogues-nomask=0" } */
+
+typedef short int16_t;
+typedef unsigned short uint16_t;
+
+void foo (uint16_t * restrict a, int16_t * restrict d, int n)
+{
+ for( int i = 0; i < n; i++ )
+ d[i] = (a[i] * a[i]) >> 10;
+}
+
+/* { dg-final { scan-assembler-times {\tshrn\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tshrn2\t} 1 } } */
--
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 48eddf64e05afe3788abfa05141f6544a9323ea1..d7b6cae424622d259f97a3d5fa9093c0fb0bd5ce 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -1818,6 +1818,28 @@ (define_insn "aarch64_shrn<mode>_insn_be"
[(set_attr "type" "neon_shift_imm_narrow_q")]
)
+(define_insn "*aarch64_<srn_op>shrn<mode>_vect"
+ [(set (match_operand:<VNARROWQ> 0 "register_operand" "=w")
+ (truncate:<VNARROWQ>
+ (SHIFTRT:VQN (match_operand:VQN 1 "register_operand" "w")
+ (match_operand:VQN 2 "aarch64_simd_shift_imm_vec_<vn_mode>"))))]
+ "TARGET_SIMD"
+ "shrn\\t%0.<Vntype>, %1.<Vtype>, %2"
+ [(set_attr "type" "neon_shift_imm_narrow_q")]
+)
+
+(define_insn "*aarch64_<srn_op>shrn<mode>2_vect"
+ [(set (match_operand:<VNARROWQ2> 0 "register_operand" "=w")
+ (vec_concat:<VNARROWQ2>
+ (match_operand:<VNARROWQ> 1 "register_operand" "0")
+ (truncate:<VNARROWQ>
+ (SHIFTRT:VQN (match_operand:VQN 2 "register_operand" "w")
+ (match_operand:VQN 3 "aarch64_simd_shift_imm_vec_<vn_mode>")))))]
+ "TARGET_SIMD"
+ "shrn2\\t%0.<V2ntype>, %2.<Vtype>, %3"
+ [(set_attr "type" "neon_shift_imm_narrow_q")]
+)
+
(define_expand "aarch64_shrn<mode>"
[(set (match_operand:<VNARROWQ> 0 "register_operand")
(truncate:<VNARROWQ>
diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
index caa42f8f169fbf2cf46a90cf73dee05619acc300..8dbeed3b0d4a44cdc17dd333ed397b39a33f386a 100644
--- a/gcc/config/aarch64/iterators.md
+++ b/gcc/config/aarch64/iterators.md
@@ -2003,6 +2003,9 @@ (define_code_attr shift [(ashift "lsl") (ashiftrt "asr")
;; Op prefix for shift right and accumulate.
(define_code_attr sra_op [(ashiftrt "s") (lshiftrt "u")])
+;; op prefix for shift right and narrow.
+(define_code_attr srn_op [(ashiftrt "r") (lshiftrt "")])
+
;; Map shift operators onto underlying bit-field instructions
(define_code_attr bfshift [(ashift "ubfiz") (ashiftrt "sbfx")
(lshiftrt "ubfx") (rotatert "extr")])
diff --git a/gcc/testsuite/gcc.target/aarch64/shrn-combine.c b/gcc/testsuite/gcc.target/aarch64/shrn-combine.c
new file mode 100644
index 0000000000000000000000000000000000000000..0187f49f4dcc76182c90366caaf00d294e835707
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/shrn-combine.c
@@ -0,0 +1,14 @@
+/* { dg-do assemble } */
+/* { dg-options "-O3 --save-temps --param=vect-epilogues-nomask=0" } */
+
+typedef short int16_t;
+typedef unsigned short uint16_t;
+
+void foo (uint16_t * restrict a, int16_t * restrict d, int n)
+{
+ for( int i = 0; i < n; i++ )
+ d[i] = (a[i] * a[i]) >> 10;
+}
+
+/* { dg-final { scan-assembler-times {\tshrn\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tshrn2\t} 1 } } */
