lgtm from my side but plz wait for robin the last review. thanks.
----------Reply to Message----------
On Wed, Jun 19, 2024 20:30 PM demin.han<demin....@starfivetech.com> wrote:
We can unify eqne and other comparison operations.
Tested on RV32 and RV64
gcc/ChangeLog:
* config/riscv/riscv-vector-builtins-bases.cc: Remove eqne cond
* config/riscv/vector.md (@pred_eqne<mode>_scalar): Remove patterns
(*pred_eqne<mode>_scalar_merge_tie_mask): Ditto
(*pred_eqne<mode>_scalar): Ditto
(*pred_eqne<mode>_scalar_narrow): Ditto
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/base/float-point-cmp-eqne.c: New test.
Signed-off-by: demin.han <demin....@starfivetech.com>
---
v2 changes:
1. add test
Only intrinsics utilize those removed vf patterns.
Auto vectorization use vv format now.
The NaN will optimized out before expand in autovec as I tested.
.../riscv/riscv-vector-builtins-bases.cc
| 4 -
gcc/config/riscv/vector.md
| 86 -------------------
.../riscv/rvv/base/float-point-cmp-eqne.c | 54
++++++++++++
3 files changed, 54 insertions(+), 90 deletions(-)
create mode 100644
gcc/testsuite/gcc.target/riscv/rvv/base/float-point-cmp-eqne.c
diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc
b/gcc/config/riscv/riscv-vector-builtins-bases.cc
index b6f6e4ff37e..d414721ede8 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
@@ -1420,10 +1420,6 @@ public:
switch (e.op_info->op)
{
case OP_TYPE_vf: {
- if (CODE == EQ || CODE == NE)
- return e.use_compare_insn (CODE, code_for_pred_eqne_scalar (
- e.vector_mode ()));
- else
return e.use_compare_insn (CODE,
code_for_pred_cmp_scalar (
e.vector_mode ()));
}
diff --git a/gcc/config/riscv/vector.md b/gcc/config/riscv/vector.md
index fbcdf96f038..f8fae6557d9 100644
--- a/gcc/config/riscv/vector.md
+++ b/gcc/config/riscv/vector.md
@@ -7545,92 +7545,6 @@ (define_insn "*pred_cmp<mode>_scalar_narrow"
(set_attr "mode" "<MODE>")
(set_attr "spec_restriction" "none,thv,thv,none,none")])
-(define_expand "@pred_eqne<mode>_scalar"
- [(set (match_operand:<VM> 0 "register_operand")
-(if_then_else:<VM>
- (unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand")
- (match_operand 6 "vector_length_operand")
- (match_operand 7 "const_int_operand")
- (match_operand 8 "const_int_operand")
- (reg:SI VL_REGNUM)
- (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 3 "equality_operator"
- [(vec_duplicate:V_VLSF
- (match_operand:<VEL> 5
"register_operand"))
- (match_operand:V_VLSF 4 "register_operand")])
- (match_operand:<VM> 2 "vector_merge_operand")))]
- "TARGET_VECTOR"
- {})
-
-(define_insn "*pred_eqne<mode>_scalar_merge_tie_mask"
- [(set (match_operand:<VM> 0
"register_operand"
"=vm")
-(if_then_else:<VM>
- (unspec:<VM>
- [(match_operand:<VM> 1
"register_operand" " 0")
- (match_operand 5
"vector_length_operand" " rK")
- (match_operand 6
"const_int_operand"
" i")
- (match_operand 7
"const_int_operand"
" i")
- (reg:SI VL_REGNUM)
- (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 2 "equality_operator"
- [(vec_duplicate:V_VLSF
- (match_operand:<VEL> 4
"register_operand" " f"))
- (match_operand:V_VLSF 3
"register_operand" " vr")])
- (match_dup 1)))]
- "TARGET_VECTOR"
- "vmf%B2.vf\t%0,%3,%4,v0.t"
- [(set_attr "type" "vfcmp")
- (set_attr "mode" "<MODE>")
- (set_attr "merge_op_idx" "1")
- (set_attr "vl_op_idx" "5")
- (set (attr "ma") (symbol_ref "riscv_vector::get_ma(operands[6])"))
- (set (attr "avl_type_idx") (const_int 7))])
-
-;; We don't use early-clobber for LMUL <= 1 to get better codegen.
-(define_insn "*pred_eqne<mode>_scalar"
- [(set (match_operand:<VM> 0
"register_operand"
"=vr, vr, &vr, &vr")
-(if_then_else:<VM>
- (unspec:<VM>
- [(match_operand:<VM> 1
"vector_mask_operand" "vmWc1,vmWc1,vmWc1,vmWc1")
- (match_operand 6
"vector_length_operand"
" rK, rK, rK, rK")
- (match_operand 7
"const_int_operand"
" i, i,
i, i")
- (match_operand 8
"const_int_operand"
" i, i,
i, i")
- (reg:SI VL_REGNUM)
- (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 3 "equality_operator"
- [(vec_duplicate:V_VLSF
- (match_operand:<VEL> 5
"register_operand" "
f, f, f, f"))
- (match_operand:V_VLSF 4
"register_operand" " vr,
vr, vr, vr")])
- (match_operand:<VM> 2
"vector_merge_operand" "
vu, 0, vu, 0")))]
- "TARGET_VECTOR && riscv_vector::cmp_lmul_le_one (<MODE>mode)"
- "vmf%B3.vf\t%0,%4,%5%p1"
- [(set_attr "type" "vfcmp")
- (set_attr "mode" "<MODE>")
- (set_attr "spec_restriction" "thv,thv,rvv,rvv")])
-
-;; We use early-clobber for source LMUL > dest LMUL.
-(define_insn "*pred_eqne<mode>_scalar_narrow"
- [(set (match_operand:<VM> 0
"register_operand"
"=vm, vr, vr, &vr, &vr")
-(if_then_else:<VM>
- (unspec:<VM>
- [(match_operand:<VM> 1
"vector_mask_operand" "
0,vmWc1,vmWc1,vmWc1,vmWc1")
- (match_operand 6
"vector_length_operand"
" rK, rK, rK, rK,
rK")
- (match_operand 7
"const_int_operand"
" i, i,
i, i, i")
- (match_operand 8
"const_int_operand"
" i, i,
i, i, i")
- (reg:SI VL_REGNUM)
- (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 3 "equality_operator"
- [(vec_duplicate:V_VLSF
- (match_operand:<VEL> 5
"register_operand" "
f, f, f,
f, f"))
- (match_operand:V_VLSF 4
"register_operand" "
vr, 0, 0, vr, vr")])
- (match_operand:<VM> 2
"vector_merge_operand" "
vu, vu, 0, vu,
0")))]
- "TARGET_VECTOR && riscv_vector::cmp_lmul_gt_one (<MODE>mode)"
- "vmf%B3.vf\t%0,%4,%5%p1"
- [(set_attr "type" "vfcmp")
- (set_attr "mode" "<MODE>")
- (set_attr "spec_restriction" "none,thv,thv,none,none")])
-
;;
-------------------------------------------------------------------------------
;; ---- Predicated floating-point merge
;;
-------------------------------------------------------------------------------
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-cmp-eqne.c
b/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-cmp-eqne.c
new file mode 100644
index 00000000000..572bcb8f291
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/float-point-cmp-eqne.c
@@ -0,0 +1,54 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64 -O3" } */
+
+#include "riscv_vector.h"
+
+#define CMP_FLOAT_VF_1(ID, S, OP,
IMM)
\
+ vbool##S##_t test_float_1_##ID##_##S (vfloat##S##m1_t op1, size_t
vl) \
+
{
\
+ return __riscv_vmf##OP##_vf_f##S##m1_b##S (op1, IMM,
vl);
\
+ }
+
+CMP_FLOAT_VF_1 (0, 32, eq, 0.0)
+CMP_FLOAT_VF_1 (1, 32, eq, 1.0)
+CMP_FLOAT_VF_1 (2, 32, eq, __builtin_nanf ("123"))
+CMP_FLOAT_VF_1 (3, 32, ne, 0.0)
+CMP_FLOAT_VF_1 (4, 32, ne, 1.0)
+CMP_FLOAT_VF_1 (5, 32, ne, __builtin_nanf ("123"))
+
+CMP_FLOAT_VF_1 (0, 64, eq, 0.0)
+CMP_FLOAT_VF_1 (1, 64, eq, 1.0)
+CMP_FLOAT_VF_1 (2, 64, eq, __builtin_nan ("123"))
+CMP_FLOAT_VF_1 (3, 64, ne, 0.0)
+CMP_FLOAT_VF_1 (4, 64, ne, 1.0)
+CMP_FLOAT_VF_1 (5, 64, ne, __builtin_nan ("123"))
+
+#define CMP_FLOAT_VF_2(ID, S, OP,
IMM)
\
+ vfloat##S##m1_t test_float_2_##ID##_##S (vfloat##S##m1_t
op1,
\
+ vfloat##S##m1_t op2, size_t vl) \
+
{
\
+ vfloat##S##m1_t op3 = __riscv_vfmv_s_f_f##S##m1 (IMM,
vl);
\
+ vbool##S##_t mask1 = __riscv_vmf##OP##_vf_f##S##m1_b##S
(op1, IMM, vl); \
+ vbool##S##_t mask2 = __riscv_vmf##OP##_vv_f##S##m1_b##S
(op1, op3, vl); \
+ vbool##S##_t mask3 = __riscv_vmor (mask1, mask2,
vl);
\
+ return __riscv_vmerge_vvm_f##S##m1_tu (op1, op1, op2,
mask3, vl); \
+ }
+
+CMP_FLOAT_VF_2 (0, 32, eq, 0.0)
+CMP_FLOAT_VF_2 (1, 32, eq, 1.0)
+CMP_FLOAT_VF_2 (2, 32, eq, __builtin_nanf ("123"))
+CMP_FLOAT_VF_2 (3, 32, ne, 0.0)
+CMP_FLOAT_VF_2 (4, 32, ne, 1.0)
+CMP_FLOAT_VF_2 (5, 32, ne, __builtin_nanf ("123"))
+
+CMP_FLOAT_VF_2 (0, 64, eq, 0.0)
+CMP_FLOAT_VF_2 (1, 64, eq, 1.0)
+CMP_FLOAT_VF_2 (2, 64, eq, __builtin_nan ("123"))
+CMP_FLOAT_VF_2 (3, 64, ne, 0.0)
+CMP_FLOAT_VF_2 (4, 64, ne, 1.0)
+CMP_FLOAT_VF_2 (5, 64, ne, __builtin_nan ("123"))
+
+/* { dg-final { scan-assembler-times {vmfeq\.vf} 12 } } */
+/* { dg-final { scan-assembler-times {vmfne\.vf} 12 } } */
+/* { dg-final { scan-assembler-times {vmfeq\.vv} 6 } } */
+/* { dg-final { scan-assembler-times {vmfne\.vv} 6 } } */
--
2.45.1
