neon.md (div<mode>3): New pattern.

2018-11-09  Prathamesh Kulkarni  <prathamesh.kulkarni@linaro.org>

	* config/arm/neon.md (div<mode>3): New pattern.

testsuite/
	* gcc.target/arm/neon-vect-div-1.c: New test.
	* gcc.target/arm/neon-vect-div-2.c: Likewise.

From-SVN: r265948

5 files changed, 73 insertions, 0 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 8961e80..800a115 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,7 @@
+2018-11-09  Prathamesh Kulkarni  <prathamesh.kulkarni@linaro.org>
+
+	* config/arm/neon.md (div<mode>3): New pattern.
+
 2018-11-08  Andi Kleen  <ak@linux.intel.com>
 
 	* common/config/i386/i386-common.c (OPTION_MASK_ISA_PTWRITE_SET): New.
diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
index 5aeee4b..07572e4 100644
--- a/gcc/config/arm/neon.md
+++ b/gcc/config/arm/neon.md
@@ -620,6 +620,38 @@
                     (const_string "neon_mul_<V_elem_ch><q>")))]
 )
 
+/* Perform division using multiply-by-reciprocal.
+   Reciprocal is calculated using Newton-Raphson method.
+   Enabled with -funsafe-math-optimizations -freciprocal-math
+   and disabled for -Os since it increases code size .  */
+
+(define_expand "div<mode>3"
+  [(set (match_operand:VCVTF 0 "s_register_operand" "=w")
+        (div:VCVTF (match_operand:VCVTF 1 "s_register_operand" "w")
+		  (match_operand:VCVTF 2 "s_register_operand" "w")))]
+  "TARGET_NEON && !optimize_size
+   && flag_reciprocal_math"
+  {
+    rtx rec = gen_reg_rtx (<MODE>mode);
+    rtx vrecps_temp = gen_reg_rtx (<MODE>mode);
+
+    /* Reciprocal estimate.  */
+    emit_insn (gen_neon_vrecpe<mode> (rec, operands[2]));
+
+    /* Perform 2 iterations of newton-raphson method.  */
+    for (int i = 0; i < 2; i++)
+      {
+	emit_insn (gen_neon_vrecps<mode> (vrecps_temp, rec, operands[2]));
+	emit_insn (gen_mul<mode>3 (rec, rec, vrecps_temp));
+      }
+
+    /* We now have reciprocal in rec, perform operands[0] = operands[1] * rec.  */
+    emit_insn (gen_mul<mode>3 (operands[0], operands[1], rec));
+    DONE;
+  }
+)
+
+
 (define_insn "mul<mode>3add<mode>_neon"
   [(set (match_operand:VDQW 0 "s_register_operand" "=w")
         (plus:VDQW (mult:VDQW (match_operand:VDQW 2 "s_register_operand" "w")
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index e5641fe..aa79847 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2018-11-09  Prathamesh Kulkarni  <prathamesh.kulkarni@linaro.org>
+
+	* gcc.target/arm/neon-vect-div-1.c: New test.
+	* gcc.target/arm/neon-vect-div-2.c: Likewise.
+
 2018-11-08  Andi Kleen  <ak@linux.intel.com>
 
 	* gcc.target/i386/ptwrite1.c: New test.
diff --git a/gcc/testsuite/gcc.target/arm/neon-vect-div-1.c b/gcc/testsuite/gcc.target/arm/neon-vect-div-1.c
new file mode 100644
index 0000000..50d04b4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/neon-vect-div-1.c
@@ -0,0 +1,16 @@
+/* Test pattern div<mode>3.  */
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-require-effective-target vect_hw_misalign } */
+/* { dg-options "-O2 -ftree-vectorize -funsafe-math-optimizations -fdump-tree-vect-details" } */
+/* { dg-add-options arm_neon } */
+
+void
+foo (int len, float * __restrict p, float *__restrict x)
+{
+  len = len & ~31;
+  for (int i = 0; i < len; i++)
+    p[i] = p[i] / x[i];
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.target/arm/neon-vect-div-2.c b/gcc/testsuite/gcc.target/arm/neon-vect-div-2.c
new file mode 100644
index 0000000..606f54b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/neon-vect-div-2.c
@@ -0,0 +1,16 @@
+/* Test pattern div<mode>3.  */
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-require-effective-target vect_hw_misalign } */
+/* { dg-options "-O3 -ftree-vectorize -funsafe-math-optimizations -fdump-tree-vect-details -fno-reciprocal-math" } */
+/* { dg-add-options arm_neon } */
+
+void
+foo (int len, float * __restrict p, float *__restrict x)
+{
+  len = len & ~31;
+  for (int i = 0; i < len; i++)
+    p[i] = p[i] / x[i];
+}
+
+/* { dg-final { scan-tree-dump-not "vectorized 1 loops" "vect" } } */