arm: Auto-vectorization for MVE: vand

This patch enables MVE vandq instructions for auto-vectorization.  MVE
vandq insns in mve.md are modified to use 'and' instead of unspec
expression to support and<mode>3.  The and<mode>3 expander is added to
vec-common.md

2020-12-03  Christophe Lyon  <christophe.lyon@linaro.org>

	gcc/
	* config/arm/iterators.md (supf): Remove VANDQ_S and VANDQ_U.
	(VANQ): Remove.
	(VDQ): Add TARGET_HAVE_MVE condition where relevant.
	* config/arm/mve.md (mve_vandq_u<mode>): New entry for vand
	instruction using expression 'and'.
	(mve_vandq_s<mode>): New expander.
	(mve_vaddq_n_f<mode>): Use 'and' code instead of unspec.
	* config/arm/neon.md (and<mode>3): Rename into and<mode>3_neon.
	* config/arm/predicates.md (imm_for_neon_inv_logic_operand):
	Enable for MVE.
	* config/arm/unspecs.md (VANDQ_S, VANDQ_U, VANDQ_F): Remove.
	* config/arm/vec-common.md (and<mode>3): New expander.

	gcc/testsuite/
	* gcc.target/arm/simd/mve-vand.c: New test.

diff --git a/gcc/config/arm/iterators.md b/gcc/config/arm/iterators.md
index 592af35f038f48b5f4ac622a0ed944ffc2a140f2..badad2bf2936f7fe403f8e9e12d6328fef501392 100644 (file)
--- a/gcc/config/arm/iterators.md
+++ b/gcc/config/arm/iterators.md
@@ -147,7 +147,12 @@
 (define_mode_iterator VN [V8HI V4SI V2DI])
 
 ;; All supported vector modes (except singleton DImode).
-(define_mode_iterator VDQ [V8QI V16QI V4HI V8HI V2SI V4SI V4HF V8HF V2SF V4SF V2DI])
+(define_mode_iterator VDQ [(V8QI "!TARGET_HAVE_MVE") V16QI
+                          (V4HI "!TARGET_HAVE_MVE") V8HI
+                          (V2SI "!TARGET_HAVE_MVE") V4SI
+                          (V4HF "!TARGET_HAVE_MVE") V8HF
+                          (V2SF "!TARGET_HAVE_MVE") V4SF
+                          (V2DI "!TARGET_HAVE_MVE")])
 
 ;; All supported floating-point vector modes (except V2DF).
 (define_mode_iterator VF [(V4HF "TARGET_NEON_FP16INST")
@@ -1232,8 +1237,7 @@
                       (VADDLVQ_P_U "u") (VCMPNEQ_U "u") (VCMPNEQ_S "s")
                       (VABDQ_M_S "s") (VABDQ_M_U "u") (VABDQ_S "s")
                       (VABDQ_U "u") (VADDQ_N_S "s") (VADDQ_N_U "u")
-                      (VADDVQ_P_S "s") (VADDVQ_P_U "u") (VANDQ_S "s")
-                      (VANDQ_U "u") (VBICQ_S "s") (VBICQ_U "u")
+                      (VADDVQ_P_S "s") (VADDVQ_P_U "u") (VBICQ_S "s") (VBICQ_U "u")
                       (VBRSRQ_N_S "s") (VBRSRQ_N_U "u") (VCADDQ_ROT270_S "s")
                       (VCADDQ_ROT270_U "u") (VCADDQ_ROT90_S "s")
                       (VCMPEQQ_S "s") (VCMPEQQ_U "u") (VCADDQ_ROT90_U "u")
@@ -1501,7 +1505,6 @@
 (define_int_iterator VADDQ_N [VADDQ_N_S VADDQ_N_U])
 (define_int_iterator VADDVAQ [VADDVAQ_S VADDVAQ_U])
 (define_int_iterator VADDVQ_P [VADDVQ_P_U VADDVQ_P_S])
-(define_int_iterator VANDQ [VANDQ_U VANDQ_S])
 (define_int_iterator VBICQ [VBICQ_S VBICQ_U])
 (define_int_iterator VBRSRQ_N [VBRSRQ_N_U VBRSRQ_N_S])
 (define_int_iterator VCADDQ_ROT270 [VCADDQ_ROT270_S VCADDQ_ROT270_U])

diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
index ecbaaa9150132fa6568b5d2217e7233e2ec6ebb6..1ec0d1aa323bf8427601bddaadc2d07af9b6cd8f 100644 (file)
--- a/gcc/config/arm/mve.md
+++ b/gcc/config/arm/mve.md
@@ -894,17 +894,30 @@
 ;;
 ;; [vandq_u, vandq_s])
 ;;
-(define_insn "mve_vandq_<supf><mode>"
+;; signed and unsigned versions are the same: define the unsigned
+;; insn, and use an expander for the signed one as we still reference
+;; both names from arm_mve.h.
+;; We use the same code as in neon.md (TODO: avoid this duplication).
+(define_insn "mve_vandq_u<mode>"
   [
-   (set (match_operand:MVE_2 0 "s_register_operand" "=w")
-       (unspec:MVE_2 [(match_operand:MVE_2 1 "s_register_operand" "w")
-                      (match_operand:MVE_2 2 "s_register_operand" "w")]
-        VANDQ))
+   (set (match_operand:MVE_2 0 "s_register_operand" "=w,w")
+       (and:MVE_2 (match_operand:MVE_2 1 "s_register_operand" "w,0")
+                  (match_operand:MVE_2 2 "neon_inv_logic_op2" "w,DL")))
   ]
   "TARGET_HAVE_MVE"
-  "vand %q0, %q1, %q2"
+  "@
+   vand\t%q0, %q1, %q2
+   * return neon_output_logic_immediate (\"vand\", &operands[2], <MODE>mode, 1, VALID_NEON_QREG_MODE (<MODE>mode));"
   [(set_attr "type" "mve_move")
 ])
+(define_expand "mve_vandq_s<mode>"
+  [
+   (set (match_operand:MVE_2 0 "s_register_operand")
+       (and:MVE_2 (match_operand:MVE_2 1 "s_register_operand")
+                  (match_operand:MVE_2 2 "neon_inv_logic_op2")))
+  ]
+  "TARGET_HAVE_MVE"
+)
 
 ;;
 ;; [vbicq_s, vbicq_u])
@@ -2019,9 +2032,8 @@
 (define_insn "mve_vandq_f<mode>"
   [
    (set (match_operand:MVE_0 0 "s_register_operand" "=w")
-       (unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
-                      (match_operand:MVE_0 2 "s_register_operand" "w")]
-        VANDQ_F))
+       (and:MVE_0 (match_operand:MVE_0 1 "s_register_operand" "w")
+                  (match_operand:MVE_0 2 "s_register_operand" "w")))
   ]
   "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
   "vand %q0, %q1, %q2"

diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
index 2d76769837884be7bde7a4c4234607a559ea5499..dc4707d7447dfd4168d70823307c5c74bed1813f 100644 (file)
--- a/gcc/config/arm/neon.md
+++ b/gcc/config/arm/neon.md
@@ -712,7 +712,7 @@
 ;; corresponds to the canonical form the middle-end expects to use for
 ;; immediate bitwise-ANDs.
 
-(define_insn "and<mode>3"
+(define_insn "and<mode>3_neon"
   [(set (match_operand:VDQ 0 "s_register_operand" "=w,w")
        (and:VDQ (match_operand:VDQ 1 "s_register_operand" "w,0")
                 (match_operand:VDQ 2 "neon_inv_logic_op2" "w,DL")))]

diff --git a/gcc/config/arm/predicates.md b/gcc/config/arm/predicates.md
index 2144520829cc4a28cd7ac1ef528ecd54f0af13c1..5f58f7c837ea75eb5acb8eb5e26bac7f03aa34ae 100644 (file)
--- a/gcc/config/arm/predicates.md
+++ b/gcc/config/arm/predicates.md
@@ -107,7 +107,7 @@
 (define_predicate "imm_for_neon_inv_logic_operand"
   (match_code "const_vector")
 {
-  return (TARGET_NEON
+  return ((TARGET_NEON || TARGET_HAVE_MVE)
           && neon_immediate_valid_for_logic (op, mode, 1, NULL, NULL));
 })
 

diff --git a/gcc/config/arm/unspecs.md b/gcc/config/arm/unspecs.md
index a3844e9a72a54489b17738d05d6c5280ae059ffa..18b304874359057f2f958c68a1292bc014f7add9 100644 (file)
--- a/gcc/config/arm/unspecs.md
+++ b/gcc/config/arm/unspecs.md
@@ -601,7 +601,6 @@
   VADDQ_N_S
   VADDVAQ_S
   VADDVQ_P_S
-  VANDQ_S
   VBICQ_S
   VBRSRQ_N_S
   VCADDQ_ROT270_S
@@ -648,7 +647,6 @@
   VADDQ_N_U
   VADDVAQ_U
   VADDVQ_P_U
-  VANDQ_U
   VBICQ_U
   VBRSRQ_N_U
   VCADDQ_ROT270_U
@@ -721,7 +719,6 @@
   VABDQ_M_U
   VABDQ_F
   VADDQ_N_F
-  VANDQ_F
   VBICQ_F
   VCADDQ_ROT270_F
   VCADDQ_ROT90_F

diff --git a/gcc/config/arm/vec-common.md b/gcc/config/arm/vec-common.md
index 250e503876ac9491234b225d6fdac16acc48c41f..2117e5be5c26cd8e7425c0b0c60dec90367add99 100644 (file)
--- a/gcc/config/arm/vec-common.md
+++ b/gcc/config/arm/vec-common.md
@@ -172,3 +172,11 @@
                                               GEN_INT (elem), operands[0]));
   DONE;
 })
+
+(define_expand "and<mode>3"
+  [(set (match_operand:VDQ 0 "s_register_operand" "")
+       (and:VDQ (match_operand:VDQ 1 "s_register_operand" "")
+                (match_operand:VDQ 2 "neon_inv_logic_op2" "")))]
+  "TARGET_NEON
+   || TARGET_HAVE_MVE"
+)

diff --git a/gcc/testsuite/gcc.target/arm/simd/mve-vand.c b/gcc/testsuite/gcc.target/arm/simd/mve-vand.c
new file mode 100644 (file)
index 0000000..26247dc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/mve-vand.c
@@ -0,0 +1,63 @@
+/* { dg-do assemble } */
+/* { 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, BITS, NB, OP, NAME)                           \
+  void test_ ## NAME ##_ ## SIGN ## BITS ## x ## NB (TYPE##BITS##_t * __restrict__ dest, TYPE##BITS##_t *a, TYPE##BITS##_t *b) { \
+    int i;                                                             \
+    for (i=0; i<NB; i++) {                                             \
+      dest[i] = a[i] OP b[i];                                          \
+    }                                                                  \
+}
+
+#define FUNC_IMM(SIGN, TYPE, BITS, NB, OP, NAME)                               \
+  void test_ ## NAME ##_ ## SIGN ## BITS ## x ## NB (TYPE##BITS##_t * __restrict__ dest, TYPE##BITS##_t *a) { \
+    int i;                                                             \
+    for (i=0; i<NB; i++) {                                             \
+      dest[i] = a[i] OP 1;                                             \
+    }                                                                  \
+}
+
+/* 64-bit vectors.  */
+FUNC(s, int, 32, 2, &, vand)
+FUNC(u, uint, 32, 2, &, vand)
+FUNC(s, int, 16, 4, &, vand)
+FUNC(u, uint, 16, 4, &, vand)
+FUNC(s, int, 8, 8, &, vand)
+FUNC(u, uint, 8, 8, &, vand)
+
+/* 128-bit vectors.  */
+FUNC(s, int, 32, 4, &, vand)
+FUNC(u, uint, 32, 4, &, vand)
+FUNC(s, int, 16, 8, &, vand)
+FUNC(u, uint, 16, 8, &, vand)
+FUNC(s, int, 8, 16, &, vand)
+FUNC(u, uint, 8, 16, &, vand)
+
+/* 64-bit vectors.  */
+FUNC_IMM(s, int, 32, 2, &, vandimm)
+FUNC_IMM(u, uint, 32, 2, &, vandimm)
+FUNC_IMM(s, int, 16, 4, &, vandimm)
+FUNC_IMM(u, uint, 16, 4, &, vandimm)
+FUNC_IMM(s, int, 8, 8, &, vandimm)
+FUNC_IMM(u, uint, 8, 8, &, vandimm)
+
+/* 128-bit vectors.  */
+FUNC_IMM(s, int, 32, 4, &, vandimm)
+FUNC_IMM(u, uint, 32, 4, &, vandimm)
+FUNC_IMM(s, int, 16, 8, &, vandimm)
+FUNC_IMM(u, uint, 16, 8, &, vandimm)
+FUNC_IMM(s, int, 8, 16, &, vandimm)
+FUNC_IMM(u, uint, 8, 16, &, vandimm)
+
+/* MVE has only 128-bit vectors, so we can vectorize only half of the
+   functions above.  */
+/* Although float16 and float32 types are supported at assembly level,
+   we cannot test them with the '&' operator, so we check only the
+   integer variants.  */
+/* For some reason, we do not generate the immediate version, we still
+   use vldr to load the vector of immediates.  */
+/* { dg-final { scan-assembler-times {vand\tq[0-9]+, q[0-9]+, q[0-9]+} 12 } } */