arm: Auto-vectorization for MVE: vshr

This patch enables MVE vshr instructions for auto-vectorization.  New
MVE patterns are introduced that take a vector of constants as second
operand, all constants being equal.

The existing mve_vshrq_n_<supf><mode> is kept, as it takes a single
immediate as second operand, and is used by arm_mve.h.

The vashr<mode>3 and vlshr<mode>3 expanders are moved fron neon.md to
vec-common.md, updated to rely on the normal expansion scheme to
generate shifts by immediate.

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

	gcc/
	* config/arm/mve.md (mve_vshrq_n_s<mode>_imm): New entry.
	(mve_vshrq_n_u<mode>_imm): Likewise.
	* config/arm/neon.md (vashr<mode>3, vlshr<mode>3): Move to ...
	* config/arm/vec-common.md: ... here.

	gcc/testsuite/
	* gcc.target/arm/simd/mve-vshr.c: Add tests for vshr.

4 files changed, 130 insertions, 35 deletions

diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
index 89ee172..62ff123 100644
--- a/gcc/config/arm/mve.md
+++ b/gcc/config/arm/mve.md
@@ -763,6 +763,7 @@
 ;;
 ;; [vshrq_n_s, vshrq_n_u])
 ;;
+;; Version that takes an immediate as operand 2.
 (define_insn "mve_vshrq_n_<supf><mode>"
   [
    (set (match_operand:MVE_2 0 "s_register_operand" "=w")
@@ -775,6 +776,39 @@
   [(set_attr "type" "mve_move")
 ])
 
+;; Versions that take constant vectors as operand 2 (with all elements
+;; equal).
+(define_insn "mve_vshrq_n_s<mode>_imm"
+  [
+   (set (match_operand:MVE_2 0 "s_register_operand" "=w")
+	(ashiftrt:MVE_2 (match_operand:MVE_2 1 "s_register_operand" "w")
+			(match_operand:MVE_2 2 "imm_for_neon_rshift_operand" "i")))
+  ]
+  "TARGET_HAVE_MVE"
+  {
+    return neon_output_shift_immediate ("vshr", 's', &operands[2],
+					<MODE>mode,
+					VALID_NEON_QREG_MODE (<MODE>mode),
+					true);
+  }
+  [(set_attr "type" "mve_move")
+])
+(define_insn "mve_vshrq_n_u<mode>_imm"
+  [
+   (set (match_operand:MVE_2 0 "s_register_operand" "=w")
+	(lshiftrt:MVE_2 (match_operand:MVE_2 1 "s_register_operand" "w")
+			(match_operand:MVE_2 2 "imm_for_neon_rshift_operand" "i")))
+  ]
+  "TARGET_HAVE_MVE"
+  {
+    return neon_output_shift_immediate ("vshr", 'u', &operands[2],
+					<MODE>mode,
+					VALID_NEON_QREG_MODE (<MODE>mode),
+					true);
+  }
+  [(set_attr "type" "mve_move")
+])
+
 ;;
 ;; [vcvtq_n_from_f_s, vcvtq_n_from_f_u])
 ;;
diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
index b229834..e904db9 100644
--- a/gcc/config/arm/neon.md
+++ b/gcc/config/arm/neon.md
@@ -899,40 +899,6 @@
   [(set_attr "type" "neon_shift_reg<q>")]
 )
 
-(define_expand "vashr<mode>3"
-  [(set (match_operand:VDQIW 0 "s_register_operand")
-	(ashiftrt:VDQIW (match_operand:VDQIW 1 "s_register_operand")
-			(match_operand:VDQIW 2 "imm_rshift_or_reg_neon")))]
-  "TARGET_NEON"
-{
-  if (s_register_operand (operands[2], <MODE>mode))
-    {
-      rtx neg = gen_reg_rtx (<MODE>mode);
-      emit_insn (gen_neon_neg<mode>2 (neg, operands[2]));
-      emit_insn (gen_ashl<mode>3_signed (operands[0], operands[1], neg));
-    }
-  else
-    emit_insn (gen_vashr<mode>3_imm (operands[0], operands[1], operands[2]));
-  DONE;
-})
-
-(define_expand "vlshr<mode>3"
-  [(set (match_operand:VDQIW 0 "s_register_operand")
-	(lshiftrt:VDQIW (match_operand:VDQIW 1 "s_register_operand")
-			(match_operand:VDQIW 2 "imm_rshift_or_reg_neon")))]
-  "TARGET_NEON"
-{
-  if (s_register_operand (operands[2], <MODE>mode))
-    {
-      rtx neg = gen_reg_rtx (<MODE>mode);
-      emit_insn (gen_neon_neg<mode>2 (neg, operands[2]));
-      emit_insn (gen_ashl<mode>3_unsigned (operands[0], operands[1], neg));
-    }
-  else
-    emit_insn (gen_vlshr<mode>3_imm (operands[0], operands[1], operands[2]));
-  DONE;
-})
-
 ;; 64-bit shifts
 
 ;; This pattern loads a 32-bit shift count into a 64-bit NEON register,
diff --git a/gcc/config/arm/vec-common.md b/gcc/config/arm/vec-common.md
index 5dfdf99..ff448da 100644
--- a/gcc/config/arm/vec-common.md
+++ b/gcc/config/arm/vec-common.md
@@ -259,4 +259,40 @@
 {
   emit_insn (gen_mve_vshlq_u<mode> (operands[0], operands[1], operands[2]));
   DONE;
-})
\ No newline at end of file
+})
+
+;; When operand 2 is an immediate, use the normal expansion to match
+;; gen_vashr<mode>3_imm for Neon and gen_mve_vshrq_n_s<mode>_imm for
+;; MVE.
+(define_expand "vashr<mode>3"
+  [(set (match_operand:VDQIW 0 "s_register_operand")
+	(ashiftrt:VDQIW (match_operand:VDQIW 1 "s_register_operand")
+			(match_operand:VDQIW 2 "imm_rshift_or_reg_neon")))]
+  "ARM_HAVE_<MODE>_ARITH"
+{
+  if (s_register_operand (operands[2], <MODE>mode))
+    {
+      rtx neg = gen_reg_rtx (<MODE>mode);
+      emit_insn (gen_neg<mode>2 (neg, operands[2]));
+      emit_insn (gen_mve_vshlq_s<mode> (operands[0], operands[1], neg));
+      DONE;
+    }
+})
+
+;; When operand 2 is an immediate, use the normal expansion to match
+;; gen_vashr<mode>3_imm for Neon and gen_mve_vshrq_n_u<mode>_imm for
+;; MVE.
+(define_expand "vlshr<mode>3"
+  [(set (match_operand:VDQIW 0 "s_register_operand")
+	(lshiftrt:VDQIW (match_operand:VDQIW 1 "s_register_operand")
+			(match_operand:VDQIW 2 "imm_rshift_or_reg_neon")))]
+  "ARM_HAVE_<MODE>_ARITH"
+{
+  if (s_register_operand (operands[2], <MODE>mode))
+    {
+      rtx neg = gen_reg_rtx (<MODE>mode);
+      emit_insn (gen_neg<mode>2 (neg, operands[2]));
+      emit_insn (gen_mve_vshlq_u<mode> (operands[0], operands[1], neg));
+      DONE;
+    }
+})
diff --git a/gcc/testsuite/gcc.target/arm/simd/mve-vshr.c b/gcc/testsuite/gcc.target/arm/simd/mve-vshr.c
new file mode 100644
index 0000000..d4e658c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/mve-vshr.c
@@ -0,0 +1,59 @@
+/* { 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 5;						\
+    }									\
+}
+
+/* 64-bit vectors.  */
+FUNC(s, int, 32, 2, >>, vshr)
+FUNC(u, uint, 32, 2, >>, vshr)
+FUNC(s, int, 16, 4, >>, vshr)
+FUNC(u, uint, 16, 4, >>, vshr)
+FUNC(s, int, 8, 8, >>, vshr)
+FUNC(u, uint, 8, 8, >>, vshr)
+
+/* 128-bit vectors.  */
+FUNC(s, int, 32, 4, >>, vshr)
+FUNC(u, uint, 32, 4, >>, vshr)
+FUNC(s, int, 16, 8, >>, vshr)
+FUNC(u, uint, 16, 8, >>, vshr)
+FUNC(s, int, 8, 16, >>, vshr)
+FUNC(u, uint, 8, 16, >>, vshr)
+
+/* 64-bit vectors.  */
+FUNC_IMM(s, int, 32, 2, >>, vshrimm)
+FUNC_IMM(u, uint, 32, 2, >>, vshrimm)
+FUNC_IMM(s, int, 16, 4, >>, vshrimm)
+FUNC_IMM(u, uint, 16, 4, >>, vshrimm)
+FUNC_IMM(s, int, 8, 8, >>, vshrimm)
+FUNC_IMM(u, uint, 8, 8, >>, vshrimm)
+
+/* 128-bit vectors.  */
+FUNC_IMM(s, int, 32, 4, >>, vshrimm)
+FUNC_IMM(u, uint, 32, 4, >>, vshrimm)
+FUNC_IMM(s, int, 16, 8, >>, vshrimm)
+FUNC_IMM(u, uint, 16, 8, >>, vshrimm)
+FUNC_IMM(s, int, 8, 16, >>, vshrimm)
+FUNC_IMM(u, uint, 8, 16, >>, vshrimm)
+
+/* MVE has only 128-bit vectors, so we can vectorize only half of the
+   functions above.  */
+/* { dg-final { scan-assembler-times {vshr.s[0-9]+\tq[0-9]+, q[0-9]+} 3 } } */
+/* { dg-final { scan-assembler-times {vshr.u[0-9]+\tq[0-9]+, q[0-9]+} 3 } } */