RISC-V: Suport FP floor auto-vectorization

This patch would like to support auto-vectorization for the
floor API in math.h. It depends on the -ffast-math option.

When we would like to call floor/floorf like v2 = floor (v1), we will
convert it into below insns (reference the implementation of llvm).

* vfcvt.x.f v3, v1, RDN
* vfcvt.f.x v2, v3

However, the floating point value may not need the cvt as above if
its mantissa is zero. For example single precision floating point below.

  +-----------+---------------+-------------+
  | raw float | binary layout | after floor |
  +-----------+---------------+-------------+
  | 8388607.5 | 0x4affffff    | 8388607.0   |
  | 8388608.0 | 0x4b000000    | 8388608.0   |
  | 8388609.0 | 0x4b000001    | 8388609.0   |
  +-----------+---------------+-------------+

All single floating point glte 8388608.0 will have all zero mantisaa.
We leverage vmflt and mask to filter them out in vector and only do the
cvt on mask.

Befor this patch:
math-floor-1.c:21:1: missed: couldn't vectorize loop
  ...
.L3:
  flw     fa0,0(s0)
  addi    s0,s0,4
  addi    s1,s1,4
  call    ceilf
  fsw     fa0,-4(s1)
  bne     s0,s2,.L3

After this patch:
  ...
  fsrmi       2   // Rounding Down
.L4:
  vfabs.v     v1,v2
  vmflt.vf    v0,v1,fa5
  vfcvt.x.f.v v3,v2,v0.t
  vfcvt.f.x.v v1,v3,v0.t
  vfsgnj.vv   v1,v1,v2
  bne         .L4
.L14:
  fsrm        a6
  ret

Please note VLS mode is also involved in this patch and covered by the
test cases.

gcc/ChangeLog:

	* config/riscv/autovec.md (floor<mode>2): New pattern.
	* config/riscv/riscv-protos.h (enum insn_flags): New enum type.
	(enum insn_type): Ditto.
	(expand_vec_floor): New function decl.
	* config/riscv/riscv-v.cc (gen_floor_const_fp): New function impl.
	(expand_vec_floor): Ditto.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/autovec/unop/math-floor-0.c: New test.
	* gcc.target/riscv/rvv/autovec/unop/math-floor-1.c: New test.
	* gcc.target/riscv/rvv/autovec/unop/math-floor-2.c: New test.
	* gcc.target/riscv/rvv/autovec/unop/math-floor-3.c: New test.
	* gcc.target/riscv/rvv/autovec/unop/math-floor-run-1.c: New test.
	* gcc.target/riscv/rvv/autovec/unop/math-floor-run-2.c: New test.
	* gcc.target/riscv/rvv/autovec/vls/math-floor-1.c: New test.

Signed-off-by: Pan Li <pan2.li@intel.com>

diff --git a/gcc/config/riscv/autovec.md b/gcc/config/riscv/autovec.md
index 6f35fb1bd9e954b5aee47ad67318330bdca3a5dd..a005e17457e655c36e0ffcbf99fc7cc8a8d75a0d 100644 (file)
--- a/gcc/config/riscv/autovec.md
+++ b/gcc/config/riscv/autovec.md
@@ -2209,6 +2209,7 @@
 ;; -------------------------------------------------------------------------
 ;; Includes:
 ;; - ceil/ceilf
+;; - floor/floorf
 ;; -------------------------------------------------------------------------
 (define_expand "ceil<mode>2"
   [(match_operand:V_VLSF 0 "register_operand")
@@ -2219,3 +2220,13 @@
     DONE;
   }
 )
+
+(define_expand "floor<mode>2"
+  [(match_operand:V_VLSF 0 "register_operand")
+   (match_operand:V_VLSF 1 "register_operand")]
+  "TARGET_VECTOR && !flag_trapping_math && !flag_rounding_math"
+  {
+    riscv_vector::expand_vec_floor (operands[0], operands[1], <MODE>mode, <VCONVERT>mode);
+    DONE;
+  }
+)

diff --git a/gcc/config/riscv/riscv-protos.h b/gcc/config/riscv/riscv-protos.h
index 34becfbaba89f082063a0c4032d29f1ade1c168a..63eb24757057c0203b8f636296d4163970554f03 100644 (file)
--- a/gcc/config/riscv/riscv-protos.h
+++ b/gcc/config/riscv/riscv-protos.h
@@ -253,6 +253,9 @@ enum insn_flags : unsigned int
 
   /* Means INSN has FRM operand and the value is FRM_RUP.  */
   FRM_RUP_P = 1 << 16,
+
+  /* Means INSN has FRM operand and the value is FRM_RDN.  */
+  FRM_RDN_P = 1 << 17,
 };
 
 enum insn_type : unsigned int
@@ -294,6 +297,7 @@ enum insn_type : unsigned int
   UNARY_OP_TAMU = __MASK_OP_TAMU | UNARY_OP_P,
   UNARY_OP_FRM_DYN = UNARY_OP | FRM_DYN_P,
   UNARY_OP_TAMU_FRM_RUP = UNARY_OP_TAMU | FRM_RUP_P,
+  UNARY_OP_TAMU_FRM_RDN = UNARY_OP_TAMU | FRM_RDN_P,
 
   /* Binary operator.  */
   BINARY_OP = __NORMAL_OP | BINARY_OP_P,
@@ -455,6 +459,7 @@ void expand_cond_len_unop (unsigned, rtx *);
 void expand_cond_len_binop (unsigned, rtx *);
 void expand_reduction (unsigned, unsigned, rtx *, rtx);
 void expand_vec_ceil (rtx, rtx, machine_mode, machine_mode);
+void expand_vec_floor (rtx, rtx, machine_mode, machine_mode);
 #endif
 bool sew64_scalar_helper (rtx *, rtx *, rtx, machine_mode,
                          bool, void (*)(rtx *, rtx));

diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc
index 251d827d973d899efb10125b5b50e41a680c4696..c2466b1354febca98ac7172cf1a3981328e96c9a 100644 (file)
--- a/gcc/config/riscv/riscv-v.cc
+++ b/gcc/config/riscv/riscv-v.cc
@@ -326,8 +326,10 @@ public:
     /* Add rounding mode operand.  */
     if (m_insn_flags & FRM_DYN_P)
       add_rounding_mode_operand (FRM_DYN);
-    if (m_insn_flags & FRM_RUP_P)
+    else if (m_insn_flags & FRM_RUP_P)
       add_rounding_mode_operand (FRM_RUP);
+    else if (m_insn_flags & FRM_RDN_P)
+      add_rounding_mode_operand (FRM_RDN);
 
     gcc_assert (insn_data[(int) icode].n_operands == m_opno);
     expand (icode, any_mem_p);
@@ -3556,6 +3558,13 @@ gen_ceil_const_fp (machine_mode inner_mode)
   return const_double_from_real_value (real, inner_mode);
 }
 
+static rtx
+gen_floor_const_fp (machine_mode inner_mode)
+{
+  /* The floor needs the same floating point const as ceil.  */
+  return gen_ceil_const_fp (inner_mode);
+}
+
 static rtx
 emit_vec_float_cmp_mask (rtx fp_vector, rtx_code code, rtx fp_scalar,
                         machine_mode vec_fp_mode)
@@ -3635,7 +3644,29 @@ expand_vec_ceil (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
      to int conversion.  */
   emit_vec_cvt_f_x (op_0, tmp, mask, UNARY_OP_TAMU_FRM_RUP, vec_fp_mode);
 
-  /* Step-5: Retrieve the sign bit.  */
+  /* Step-5: Retrieve the sign bit for -0.0.  */
+  emit_vec_copysign (op_0, op_0, op_1, vec_fp_mode);
+}
+
+void
+expand_vec_floor (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
+                 machine_mode vec_int_mode)
+{
+  /* Step-1: Get the abs float value for mask generation.  */
+  emit_vec_abs (op_0, op_1, vec_fp_mode);
+
+  /* Step-2: Generate the mask on const fp.  */
+  rtx const_fp = gen_floor_const_fp (GET_MODE_INNER (vec_fp_mode));
+  rtx mask = emit_vec_float_cmp_mask (op_0, LT, const_fp, vec_fp_mode);
+
+  /* Step-3: Convert to integer on mask, with rounding down (aka floor).  */
+  rtx tmp = gen_reg_rtx (vec_int_mode);
+  emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMU_FRM_RDN, vec_fp_mode);
+
+  /* Step-4: Convert to floating-point on mask for the floor result.  */
+  emit_vec_cvt_f_x (op_0, tmp, mask, UNARY_OP_TAMU_FRM_RDN, vec_fp_mode);
+
+  /* Step-5: Retrieve the sign bit for -0.0.  */
   emit_vec_copysign (op_0, op_0, op_1, vec_fp_mode);
 }
 

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-0.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-0.c
new file mode 100644 (file)
index 0000000..33b1693
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-0.c
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvfh -mabi=lp64d -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math -fno-schedule-insns -fno-schedule-insns2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include "test-math.h"
+
+/*
+** test__Float16___builtin_floorf16:
+**   frrm\s+[atx][0-9]+
+**   ...
+**   fsrmi\s+2
+**   ...
+**   vsetvli\s+[atx][0-9]+,\s*zero,\s*e16,\s*m1,\s*ta,\s*mu
+**   vfabs\.v\s+v[0-9]+,\s*v[0-9]+
+**   vmflt\.vf\s+v0,\s*v[0-9]+,\s*[fa]+[0-9]+
+**   vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0\.t
+**   vfcvt\.f\.x\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0\.t
+**   vfsgnj\.vv\s+v[0-9]+,v[0-9]+,v[0-9]+
+**   ...
+**   fsrm\s+[atx][0-9]+
+**   ...
+*/
+TEST_UNARY_CALL (_Float16, __builtin_floorf16)

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-1.c
new file mode 100644 (file)
index 0000000..5c462c4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-1.c
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math -fno-schedule-insns -fno-schedule-insns2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include "test-math.h"
+
+/*
+** test_float___builtin_floorf:
+**   frrm\s+[atx][0-9]+
+**   ...
+**   fsrmi\s+2
+**   ...
+**   vsetvli\s+[atx][0-9]+,\s*zero,\s*e32,\s*m1,\s*ta,\s*mu
+**   vfabs\.v\s+v[0-9]+,\s*v[0-9]+
+**   vmflt\.vf\s+v0,\s*v[0-9]+,\s*[fa]+[0-9]+
+**   vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0\.t
+**   vfcvt\.f\.x\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0\.t
+**   vfsgnj\.vv\s+v[0-9]+,v[0-9]+,v[0-9]+
+**   ...
+**   fsrm\s+[atx][0-9]+
+**   ...
+*/
+TEST_UNARY_CALL (float, __builtin_floorf)

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-2.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-2.c
new file mode 100644 (file)
index 0000000..6f07add
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-2.c
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math -fno-schedule-insns -fno-schedule-insns2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include "test-math.h"
+
+/*
+** test_double___builtin_floor:
+**   frrm\s+[atx][0-9]+
+**   ...
+**   fsrmi\s+2
+**   ...
+**   vsetvli\s+[atx][0-9]+,\s*zero,\s*e64,\s*m1,\s*ta,\s*mu
+**   vfabs\.v\s+v[0-9]+,\s*v[0-9]+
+**   vmflt\.vf\s+v0,\s*v[0-9]+,\s*[fa]+[0-9]+
+**   vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0\.t
+**   vfcvt\.f\.x\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0\.t
+**   vfsgnj\.vv\s+v[0-9]+,v[0-9]+,v[0-9]+
+**   ...
+**   fsrm\s+[atx][0-9]+
+**   ...
+*/
+TEST_UNARY_CALL (double, __builtin_floor)

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-3.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-3.c
new file mode 100644 (file)
index 0000000..a091ffd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-3.c
@@ -0,0 +1,25 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math -fno-schedule-insns -fno-schedule-insns2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include "test-math.h"
+
+/*
+** test_float___builtin_floorf:
+**   frrm\s+[atx][0-9]+
+**   ...
+**   fsrmi\s+2
+**   ...
+**   vsetvli\s+[atx][0-9]+,\s*zero,\s*e32,\s*m1,\s*ta,\s*mu
+**   vfabs\.v\s+v[0-9]+,\s*v[0-9]+
+**   vmflt\.vf\s+v0,\s*v[0-9]+,\s*[fa]+[0-9]+
+**   vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0\.t
+**   vfcvt\.f\.x\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0\.t
+**   vfsgnj\.vv\s+v[0-9]+,v[0-9]+,v[0-9]+
+**   ...
+**   vmerge\.vvm\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+,\s*v0
+**   ...
+**   fsrm\s+[atx][0-9]+
+**   ...
+*/
+TEST_COND_UNARY_CALL (float, __builtin_floorf)

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-run-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-run-1.c
new file mode 100644 (file)
index 0000000..d66905d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-run-1.c
@@ -0,0 +1,39 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "-std=c99 -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math" } */
+
+#include "test-math.h"
+
+#define ARRAY_SIZE 128
+
+float in[ARRAY_SIZE];
+float out[ARRAY_SIZE];
+float ref[ARRAY_SIZE];
+
+TEST_UNARY_CALL (float, __builtin_floorf)
+TEST_ASSERT (float)
+
+TEST_INIT (float, 1.2, 1.0, 1)
+TEST_INIT (float, -1.2, -2.0, 2)
+TEST_INIT (float, 3.0, 3.0, 3)
+TEST_INIT (float, 8388607.5, 8388607.0, 4)
+TEST_INIT (float, 8388609.0, 8388609.0, 5)
+TEST_INIT (float, 0.0, 0.0, 6)
+TEST_INIT (float, -0.0, -0.0, 7)
+TEST_INIT (float, -8388607.5, -8388608.0, 8)
+TEST_INIT (float, -8388608.0, -8388608.0, 9)
+
+int
+main ()
+{
+  RUN_TEST (float, 1, __builtin_floorf, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (float, 2, __builtin_floorf, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (float, 3, __builtin_floorf, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (float, 4, __builtin_floorf, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (float, 5, __builtin_floorf, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (float, 6, __builtin_floorf, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (float, 7, __builtin_floorf, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (float, 8, __builtin_floorf, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (float, 9, __builtin_floorf, in, out, ref, ARRAY_SIZE);
+
+  return 0;
+}

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-run-2.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-run-2.c
new file mode 100644 (file)
index 0000000..367a16d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-floor-run-2.c
@@ -0,0 +1,39 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "-std=c99 -O3 -ftree-vectorize -fno-vect-cost-model -ffast-math" } */
+
+#include "test-math.h"
+
+#define ARRAY_SIZE 128
+
+double in[ARRAY_SIZE];
+double out[ARRAY_SIZE];
+double ref[ARRAY_SIZE];
+
+TEST_UNARY_CALL (double, __builtin_floor)
+TEST_ASSERT (double)
+
+TEST_INIT (double, 1.2, 1.0, 1)
+TEST_INIT (double, -1.2, -2.0, 2)
+TEST_INIT (double, 3.0, 3.0, 3)
+TEST_INIT (double, 4503599627370495.5, 4503599627370495.0, 4)
+TEST_INIT (double, 4503599627370497.0, 4503599627370497.0, 5)
+TEST_INIT (double, 0.0, 0.0, 6)
+TEST_INIT (double, -0.0, -0.0, 7)
+TEST_INIT (double, -4503599627370495.5, -4503599627370496.0, 8)
+TEST_INIT (double, -4503599627370496.0, -4503599627370496.0, 9)
+
+int
+main ()
+{
+  RUN_TEST (double, 1, __builtin_floor, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (double, 2, __builtin_floor, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (double, 3, __builtin_floor, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (double, 4, __builtin_floor, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (double, 5, __builtin_floor, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (double, 6, __builtin_floor, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (double, 7, __builtin_floor, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (double, 8, __builtin_floor, in, out, ref, ARRAY_SIZE);
+  RUN_TEST (double, 9, __builtin_floor, in, out, ref, ARRAY_SIZE);
+
+  return 0;
+}

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-floor-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-floor-1.c
new file mode 100644 (file)
index 0000000..076580e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-floor-1.c
@@ -0,0 +1,56 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvfh_zvl4096b -mabi=lp64d -O3 --param=riscv-autovec-lmul=m8 -ffast-math -fdump-tree-optimized" } */
+
+#include "def.h"
+
+DEF_OP_V (floorf16, 1, _Float16, __builtin_floorf16)
+DEF_OP_V (floorf16, 2, _Float16, __builtin_floorf16)
+DEF_OP_V (floorf16, 4, _Float16, __builtin_floorf16)
+DEF_OP_V (floorf16, 8, _Float16, __builtin_floorf16)
+DEF_OP_V (floorf16, 16, _Float16, __builtin_floorf16)
+DEF_OP_V (floorf16, 32, _Float16, __builtin_floorf16)
+DEF_OP_V (floorf16, 64, _Float16, __builtin_floorf16)
+DEF_OP_V (floorf16, 128, _Float16, __builtin_floorf16)
+DEF_OP_V (floorf16, 256, _Float16, __builtin_floorf16)
+DEF_OP_V (floorf16, 512, _Float16, __builtin_floorf16)
+DEF_OP_V (floorf16, 1024, _Float16, __builtin_floorf16)
+DEF_OP_V (floorf16, 2048, _Float16, __builtin_floorf16)
+
+DEF_OP_V (floorf, 1, float, __builtin_floorf)
+DEF_OP_V (floorf, 2, float, __builtin_floorf)
+DEF_OP_V (floorf, 4, float, __builtin_floorf)
+DEF_OP_V (floorf, 8, float, __builtin_floorf)
+DEF_OP_V (floorf, 16, float, __builtin_floorf)
+DEF_OP_V (floorf, 32, float, __builtin_floorf)
+DEF_OP_V (floorf, 64, float, __builtin_floorf)
+DEF_OP_V (floorf, 128, float, __builtin_floorf)
+DEF_OP_V (floorf, 256, float, __builtin_floorf)
+DEF_OP_V (floorf, 512, float, __builtin_floorf)
+DEF_OP_V (floorf, 1024, float, __builtin_floorf)
+
+DEF_OP_V (floor, 1, double, __builtin_floor)
+DEF_OP_V (floor, 2, double, __builtin_floor)
+DEF_OP_V (floor, 4, double, __builtin_floor)
+DEF_OP_V (floor, 8, double, __builtin_floor)
+DEF_OP_V (floor, 16, double, __builtin_floor)
+DEF_OP_V (floor, 32, double, __builtin_floor)
+DEF_OP_V (floor, 64, double, __builtin_floor)
+DEF_OP_V (floor, 128, double, __builtin_floor)
+DEF_OP_V (floor, 256, double, __builtin_floor)
+DEF_OP_V (floor, 512, double, __builtin_floor)
+
+/* { dg-final { scan-assembler-not {csrr} } } */
+/* { dg-final { scan-tree-dump-not "1,1" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "2,2" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "4,4" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "16,16" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "32,32" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "64,64" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "128,128" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "256,256" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "512,512" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "1024,1024" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "2048,2048" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "4096,4096" "optimized" } } */
+/* { dg-final { scan-assembler-times {vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0\.t} 30 } } */
+/* { dg-final { scan-assembler-times {vfcvt\.f\.x\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0\.t} 30 } } */