RISC-V: Support FP roundeven auto-vectorization

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

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

* vfcvt.x.f v3, v1, RNE
* 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 roundeven |
  +-----------+---------------+-----------------+
  | 8388607.5 | 0x4affffff    | 8388608.0       |
  | 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-roundeven-1.c:21:1: missed: couldn't vectorize loop
  ...
.L3:
  flw     fa0,0(s0)
  addi    s0,s0,4
  addi    s1,s1,4
  call    roundeven
  fsw     fa0,-4(s1)
  bne     s0,s2,.L3

After this patch:
  ...
  fsrmi       0   // Rounding to nearest, ties to even
.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.  We will add more run test with zfa support later.

gcc/ChangeLog:

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

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/autovec/unop/math-roundeven-0.c: New test.
	* gcc.target/riscv/rvv/autovec/unop/math-roundeven-1.c: New test.
	* gcc.target/riscv/rvv/autovec/unop/math-roundeven-2.c: New test.
	* gcc.target/riscv/rvv/autovec/unop/math-roundeven-3.c: New test.
	* gcc.target/riscv/rvv/autovec/vls/math-roundeven-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 680a3374972cbdad72ce7527f2443c25bd3ffa96..cd0cbdd288961784f454ba29b172191748ac9069 100644 (file)
--- a/gcc/config/riscv/autovec.md
+++ b/gcc/config/riscv/autovec.md
@@ -2271,3 +2271,13 @@
     DONE;
   }
 )
+
+(define_expand "roundeven<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_roundeven (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 536e70bdcd3aa20fb1327a5150ee91e93c50250a..368982a447bee416567d263ebca5d0bfaf246193 100644 (file)
--- a/gcc/config/riscv/riscv-protos.h
+++ b/gcc/config/riscv/riscv-protos.h
@@ -259,6 +259,9 @@ enum insn_flags : unsigned int
 
   /* Means INSN has FRM operand and the value is FRM_RMM.  */
   FRM_RMM_P = 1 << 18,
+
+  /* Means INSN has FRM operand and the value is FRM_RNE.  */
+  FRM_RNE_P = 1 << 19,
 };
 
 enum insn_type : unsigned int
@@ -303,6 +306,7 @@ enum insn_type : unsigned int
   UNARY_OP_TAMU_FRM_RUP = UNARY_OP_TAMU | FRM_RUP_P,
   UNARY_OP_TAMU_FRM_RDN = UNARY_OP_TAMU | FRM_RDN_P,
   UNARY_OP_TAMU_FRM_RMM = UNARY_OP_TAMU | FRM_RMM_P,
+  UNARY_OP_TAMU_FRM_RNE = UNARY_OP_TAMU | FRM_RNE_P,
 
   /* Binary operator.  */
   BINARY_OP = __NORMAL_OP | BINARY_OP_P,
@@ -469,6 +473,7 @@ void expand_vec_nearbyint (rtx, rtx, machine_mode, machine_mode);
 void expand_vec_rint (rtx, rtx, machine_mode, machine_mode);
 void expand_vec_round (rtx, rtx, machine_mode, machine_mode);
 void expand_vec_trunc (rtx, rtx, machine_mode, machine_mode);
+void expand_vec_roundeven (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 8992977a51d2b33ada500a6582b52108fda97041..359fb2ced8b746cf6c56cebd456bcc5690dee52a 100644 (file)
--- a/gcc/config/riscv/riscv-v.cc
+++ b/gcc/config/riscv/riscv-v.cc
@@ -332,6 +332,8 @@ public:
       add_rounding_mode_operand (FRM_RDN);
     else if (m_insn_flags & FRM_RMM_P)
       add_rounding_mode_operand (FRM_RMM);
+    else if (m_insn_flags & FRM_RNE_P)
+      add_rounding_mode_operand (FRM_RNE);
 
     gcc_assert (insn_data[(int) icode].n_operands == m_opno);
     expand (icode, any_mem_p);
@@ -3776,4 +3778,26 @@ expand_vec_trunc (rtx op_0, rtx op_1, machine_mode vec_fp_mode,
   emit_vec_copysign (op_0, op_0, op_1, vec_fp_mode);
 }
 
+void
+expand_vec_roundeven (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 = get_fp_rounding_coefficient (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, rounding to nearest, ties to even.  */
+  rtx tmp = gen_reg_rtx (vec_int_mode);
+  emit_vec_cvt_x_f (tmp, op_1, mask, UNARY_OP_TAMU_FRM_RNE, vec_fp_mode);
+
+  /* Step-4: Convert to floating-point on mask for the rint result.  */
+  emit_vec_cvt_f_x (op_0, tmp, mask, UNARY_OP_TAMU_FRM_RNE, vec_fp_mode);
+
+  /* Step-5: Retrieve the sign bit for -0.0.  */
+  emit_vec_copysign (op_0, op_0, op_1, vec_fp_mode);
+}
+
 } // namespace riscv_vector

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-roundeven-0.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-roundeven-0.c
new file mode 100644 (file)
index 0000000..ab65e37
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-roundeven-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_roundevenf16:
+**   frrm\s+[atx][0-9]+
+**   ...
+**   fsrmi\s+0
+**   ...
+**   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_roundevenf16)

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-roundeven-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-roundeven-1.c
new file mode 100644 (file)
index 0000000..fac85ed
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-roundeven-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_roundevenf:
+**   frrm\s+[atx][0-9]+
+**   ...
+**   fsrmi\s+0
+**   ...
+**   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_roundevenf)

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-roundeven-2.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-roundeven-2.c
new file mode 100644 (file)
index 0000000..074f1b4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-roundeven-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_roundeven:
+**   frrm\s+[atx][0-9]+
+**   ...
+**   fsrmi\s+0
+**   ...
+**   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_roundeven)

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-roundeven-3.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-roundeven-3.c
new file mode 100644 (file)
index 0000000..c95e8ec
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-roundeven-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_roundevenf:
+**   frrm\s+[atx][0-9]+
+**   ...
+**   fsrmi\s+0
+**   ...
+**   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_roundevenf)

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-roundeven-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-roundeven-1.c
new file mode 100644 (file)
index 0000000..8489d39
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-roundeven-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 (roundevenf16, 1, _Float16, __builtin_roundevenf16)
+DEF_OP_V (roundevenf16, 2, _Float16, __builtin_roundevenf16)
+DEF_OP_V (roundevenf16, 4, _Float16, __builtin_roundevenf16)
+DEF_OP_V (roundevenf16, 8, _Float16, __builtin_roundevenf16)
+DEF_OP_V (roundevenf16, 16, _Float16, __builtin_roundevenf16)
+DEF_OP_V (roundevenf16, 32, _Float16, __builtin_roundevenf16)
+DEF_OP_V (roundevenf16, 64, _Float16, __builtin_roundevenf16)
+DEF_OP_V (roundevenf16, 128, _Float16, __builtin_roundevenf16)
+DEF_OP_V (roundevenf16, 256, _Float16, __builtin_roundevenf16)
+DEF_OP_V (roundevenf16, 512, _Float16, __builtin_roundevenf16)
+DEF_OP_V (roundevenf16, 1024, _Float16, __builtin_roundevenf16)
+DEF_OP_V (roundevenf16, 2048, _Float16, __builtin_roundevenf16)
+
+DEF_OP_V (roundevenf, 1, float, __builtin_roundevenf)
+DEF_OP_V (roundevenf, 2, float, __builtin_roundevenf)
+DEF_OP_V (roundevenf, 4, float, __builtin_roundevenf)
+DEF_OP_V (roundevenf, 8, float, __builtin_roundevenf)
+DEF_OP_V (roundevenf, 16, float, __builtin_roundevenf)
+DEF_OP_V (roundevenf, 32, float, __builtin_roundevenf)
+DEF_OP_V (roundevenf, 64, float, __builtin_roundevenf)
+DEF_OP_V (roundevenf, 128, float, __builtin_roundevenf)
+DEF_OP_V (roundevenf, 256, float, __builtin_roundevenf)
+DEF_OP_V (roundevenf, 512, float, __builtin_roundevenf)
+DEF_OP_V (roundevenf, 1024, float, __builtin_roundevenf)
+
+DEF_OP_V (roundeven, 1, double, __builtin_roundeven)
+DEF_OP_V (roundeven, 2, double, __builtin_roundeven)
+DEF_OP_V (roundeven, 4, double, __builtin_roundeven)
+DEF_OP_V (roundeven, 8, double, __builtin_roundeven)
+DEF_OP_V (roundeven, 16, double, __builtin_roundeven)
+DEF_OP_V (roundeven, 32, double, __builtin_roundeven)
+DEF_OP_V (roundeven, 64, double, __builtin_roundeven)
+DEF_OP_V (roundeven, 128, double, __builtin_roundeven)
+DEF_OP_V (roundeven, 256, double, __builtin_roundeven)
+DEF_OP_V (roundeven, 512, double, __builtin_roundeven)
+
+/* { 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 } } */