* [PATCH v2] RISC-V: Remove integer vector eqne pattern
@ 2024-06-20 3:28 demin.han
2024-06-20 9:38 ` 钟居哲
2024-06-23 4:04 ` Jeff Law
0 siblings, 2 replies; 3+ messages in thread
From: demin.han @ 2024-06-20 3:28 UTC (permalink / raw)
To: gcc-patches; +Cc: juzhe.zhong, kito.cheng, pan2.li, jeffreyalaw, rdapp.gcc
We can unify eqne and other comparison operations.
Tested on RV32 and RV64.
gcc/ChangeLog:
* config/riscv/predicates.md (comparison_except_eqge_operator): Only
exclude ge
(comparison_except_ge_operator): Ditto
* config/riscv/riscv-string.cc (expand_rawmemchr): Use cmp pattern
(expand_strcmp): Ditto
* config/riscv/riscv-vector-builtins-bases.cc: Remove eqne cond
* config/riscv/vector.md (@pred_eqne<mode>_scalar): Remove eqne
patterns
(*pred_eqne<mode>_scalar_merge_tie_mask): Ditto
(*pred_eqne<mode>_scalar): Ditto
(*pred_eqne<mode>_scalar_narrow): Ditto
(*pred_eqne<mode>_extended_scalar_merge_tie_mask): Ditto
(*pred_eqne<mode>_extended_scalar): Ditto
(*pred_eqne<mode>_extended_scalar_narrow): Ditto
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/base/integer-cmp-eqne.c: New test.
Signed-off-by: demin.han <demin.han@starfivetech.com>
---
v2 changes:
1. add test
gcc/config/riscv/predicates.md | 4 +-
gcc/config/riscv/riscv-string.cc | 4 +-
.../riscv/riscv-vector-builtins-bases.cc | 3 -
gcc/config/riscv/vector.md | 279 +-----------------
.../riscv/rvv/base/integer-cmp-eqne.c | 66 +++++
5 files changed, 81 insertions(+), 275 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/integer-cmp-eqne.c
diff --git a/gcc/config/riscv/predicates.md b/gcc/config/riscv/predicates.md
index 0fb5729fdcf..9971fabc587 100644
--- a/gcc/config/riscv/predicates.md
+++ b/gcc/config/riscv/predicates.md
@@ -568,8 +568,8 @@ (define_predicate "ltge_operator"
(define_predicate "comparison_except_ltge_operator"
(match_code "eq,ne,le,leu,gt,gtu"))
-(define_predicate "comparison_except_eqge_operator"
- (match_code "le,leu,gt,gtu,lt,ltu"))
+(define_predicate "comparison_except_ge_operator"
+ (match_code "eq,ne,le,leu,gt,gtu,lt,ltu"))
(define_predicate "ge_operator"
(match_code "ge,geu"))
diff --git a/gcc/config/riscv/riscv-string.cc b/gcc/config/riscv/riscv-string.cc
index 83e7afbd693..4702001bd9b 100644
--- a/gcc/config/riscv/riscv-string.cc
+++ b/gcc/config/riscv/riscv-string.cc
@@ -1342,7 +1342,7 @@ expand_rawmemchr (machine_mode mode, rtx dst, rtx haystack, rtx needle,
/* Compare needle with haystack and store in a mask. */
rtx eq = gen_rtx_EQ (mask_mode, gen_const_vec_duplicate (vmode, needle), vec);
rtx vmsops[] = {mask, eq, vec, needle};
- emit_nonvlmax_insn (code_for_pred_eqne_scalar (vmode),
+ emit_nonvlmax_insn (code_for_pred_cmp_scalar (vmode),
riscv_vector::COMPARE_OP, vmsops, cnt);
/* Find the first bit in the mask. */
@@ -1468,7 +1468,7 @@ expand_strcmp (rtx result, rtx src1, rtx src2, rtx nbytes,
= gen_rtx_EQ (mask_mode, gen_const_vec_duplicate (vmode, CONST0_RTX (mode)),
vec1);
rtx vmsops1[] = {mask0, eq0, vec1, CONST0_RTX (mode)};
- emit_nonvlmax_insn (code_for_pred_eqne_scalar (vmode),
+ emit_nonvlmax_insn (code_for_pred_cmp_scalar (vmode),
riscv_vector::COMPARE_OP, vmsops1, cnt);
/* Look for vec1 != vec2 (includes vec2[i] == 0). */
diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc
index 596b88cc8a3..6483faba39c 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
@@ -718,9 +718,6 @@ public:
if (CODE == GE || CODE == GEU)
return e.use_compare_insn (CODE, code_for_pred_ge_scalar (
e.vector_mode ()));
- else 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 f8fae6557d9..fe18ee5b5f7 100644
--- a/gcc/config/riscv/vector.md
+++ b/gcc/config/riscv/vector.md
@@ -4704,7 +4704,7 @@ (define_expand "@pred_cmp<mode>_scalar"
(match_operand 8 "const_int_operand")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 3 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_QHS 4 "register_operand")
(vec_duplicate:V_VLSI_QHS
(match_operand:<VEL> 5 "register_operand"))])
@@ -4722,7 +4722,7 @@ (define_insn "*pred_cmp<mode>_scalar_merge_tie_mask"
(match_operand 7 "const_int_operand" " i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 2 "comparison_except_eqge_operator"
+ (match_operator:<VM> 2 "comparison_except_ge_operator"
[(match_operand:V_VLSI_QHS 3 "register_operand" " vr")
(vec_duplicate:V_VLSI_QHS
(match_operand:<VEL> 4 "register_operand" " r"))])
@@ -4747,7 +4747,7 @@ (define_insn "*pred_cmp<mode>_scalar"
(match_operand 8 "const_int_operand" " i, i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 3 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_QHS 4 "register_operand" " vr, vr, vr, vr")
(vec_duplicate:V_VLSI_QHS
(match_operand:<VEL> 5 "register_operand" " r, r, r, r"))])
@@ -4769,7 +4769,7 @@ (define_insn "*pred_cmp<mode>_scalar_narrow"
(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 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_QHS 4 "register_operand" " vr, 0, 0, vr, vr")
(vec_duplicate:V_VLSI_QHS
(match_operand:<VEL> 5 "register_operand" " r, r, r, r, r"))])
@@ -4780,92 +4780,6 @@ (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_VLSI_QHS
- (match_operand:<VEL> 5 "register_operand"))
- (match_operand:V_VLSI_QHS 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_VLSI_QHS
- (match_operand:<VEL> 4 "register_operand" " r"))
- (match_operand:V_VLSI_QHS 3 "register_operand" " vr")])
- (match_dup 1)))]
- "TARGET_VECTOR"
- "vms%B2.vx\t%0,%3,%4,v0.t"
- [(set_attr "type" "vicmp")
- (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_VLSI_QHS
- (match_operand:<VEL> 5 "register_operand" " r, r, r, r"))
- (match_operand:V_VLSI_QHS 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)"
- "vms%B3.vx\t%0,%4,%5%p1"
- [(set_attr "type" "vicmp")
- (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_VLSI_QHS
- (match_operand:<VEL> 5 "register_operand" " r, r, r, r, r"))
- (match_operand:V_VLSI_QHS 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)"
- "vms%B3.vx\t%0,%4,%5%p1"
- [(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")
- (set_attr "spec_restriction" "none,thv,thv,none,none")])
-
;; Handle GET_MODE_INNER (mode) = DImode. We need to split them since
;; we need to deal with SEW = 64 in RV32 system.
(define_expand "@pred_cmp<mode>_scalar"
@@ -4878,7 +4792,7 @@ (define_expand "@pred_cmp<mode>_scalar"
(match_operand 8 "const_int_operand")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 3 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_D 4 "register_operand")
(vec_duplicate:V_VLSI_D
(match_operand:<VEL> 5 "reg_or_int_operand"))])
@@ -4908,39 +4822,6 @@ (define_expand "@pred_cmp<mode>_scalar"
DONE;
})
-(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_VLSI_D
- (match_operand:<VEL> 5 "reg_or_int_operand"))
- (match_operand:V_VLSI_D 4 "register_operand")])
- (match_operand:<VM> 2 "vector_merge_operand")))]
- "TARGET_VECTOR"
-{
- enum rtx_code code = GET_CODE (operands[3]);
- if (riscv_vector::sew64_scalar_helper (
- operands,
- /* scalar op */&operands[5],
- /* vl */operands[6],
- <MODE>mode,
- riscv_vector::has_vi_variant_p (code, operands[5]),
- [] (rtx *operands, rtx boardcast_scalar) {
- emit_insn (gen_pred_cmp<mode> (operands[0], operands[1],
- operands[2], operands[3], operands[4], boardcast_scalar,
- operands[6], operands[7], operands[8]));
- },
- (riscv_vector::avl_type) INTVAL (operands[8])))
- DONE;
-})
-
(define_insn "*pred_cmp<mode>_scalar_merge_tie_mask"
[(set (match_operand:<VM> 0 "register_operand" "=vm")
(if_then_else:<VM>
@@ -4951,7 +4832,7 @@ (define_insn "*pred_cmp<mode>_scalar_merge_tie_mask"
(match_operand 7 "const_int_operand" " i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 2 "comparison_except_eqge_operator"
+ (match_operator:<VM> 2 "comparison_except_ge_operator"
[(match_operand:V_VLSI_D 3 "register_operand" " vr")
(vec_duplicate:V_VLSI_D
(match_operand:<VEL> 4 "register_operand" " r"))])
@@ -4965,30 +4846,6 @@ (define_insn "*pred_cmp<mode>_scalar_merge_tie_mask"
(set (attr "ma") (symbol_ref "riscv_vector::get_ma(operands[6])"))
(set (attr "avl_type_idx") (const_int 7))])
-(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_VLSI_D
- (match_operand:<VEL> 4 "register_operand" " r"))
- (match_operand:V_VLSI_D 3 "register_operand" " vr")])
- (match_dup 1)))]
- "TARGET_VECTOR"
- "vms%B2.vx\t%0,%3,%4,v0.t"
- [(set_attr "type" "vicmp")
- (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_cmp<mode>_scalar"
[(set (match_operand:<VM> 0 "register_operand" "=vr, vr, &vr, &vr")
@@ -5000,7 +4857,7 @@ (define_insn "*pred_cmp<mode>_scalar"
(match_operand 8 "const_int_operand" " i, i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 3 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_D 4 "register_operand" " vr, vr, vr, vr")
(vec_duplicate:V_VLSI_D
(match_operand:<VEL> 5 "register_operand" " r, r, r, r"))])
@@ -5022,7 +4879,7 @@ (define_insn "*pred_cmp<mode>_scalar_narrow"
(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 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_D 4 "register_operand" " vr, 0, 0, vr, vr")
(vec_duplicate:V_VLSI_D
(match_operand:<VEL> 5 "register_operand" " r, r, r, r, r"))])
@@ -5033,50 +4890,6 @@ (define_insn "*pred_cmp<mode>_scalar_narrow"
(set_attr "mode" "<MODE>")
(set_attr "spec_restriction" "none,thv,thv,none,none")])
-;; 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_VLSI_D
- (match_operand:<VEL> 5 "register_operand" " r, r, r, r"))
- (match_operand:V_VLSI_D 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)"
- "vms%B3.vx\t%0,%4,%5%p1"
- [(set_attr "type" "vicmp")
- (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_VLSI_D
- (match_operand:<VEL> 5 "register_operand" " r, r, r, r, r"))
- (match_operand:V_VLSI_D 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)"
- "vms%B3.vx\t%0,%4,%5%p1"
- [(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")
- (set_attr "spec_restriction" "none,thv,thv,none,none")])
-
(define_insn "*pred_cmp<mode>_extended_scalar_merge_tie_mask"
[(set (match_operand:<VM> 0 "register_operand" "=vm")
(if_then_else:<VM>
@@ -5087,7 +4900,7 @@ (define_insn "*pred_cmp<mode>_extended_scalar_merge_tie_mask"
(match_operand 7 "const_int_operand" " i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 2 "comparison_except_eqge_operator"
+ (match_operator:<VM> 2 "comparison_except_ge_operator"
[(match_operand:V_VLSI_D 3 "register_operand" " vr")
(vec_duplicate:V_VLSI_D
(sign_extend:<VEL>
@@ -5113,7 +4926,7 @@ (define_insn "*pred_cmp<mode>_extended_scalar"
(match_operand 8 "const_int_operand" " i, i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 3 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_D 4 "register_operand" " vr, vr, vr, vr")
(vec_duplicate:V_VLSI_D
(sign_extend:<VEL>
@@ -5135,7 +4948,7 @@ (define_insn "*pred_cmp<mode>_extended_scalar_narrow"
(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 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_D 4 "register_operand" " vr, 0, 0, vr, vr")
(vec_duplicate:V_VLSI_D
(sign_extend:<VEL>
@@ -5147,76 +4960,6 @@ (define_insn "*pred_cmp<mode>_extended_scalar_narrow"
(set_attr "mode" "<MODE>")
(set_attr "spec_restriction" "none,thv,thv,none,none")])
-(define_insn "*pred_eqne<mode>_extended_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_VLSI_D
- (sign_extend:<VEL>
- (match_operand:<VSUBEL> 4 "register_operand" " r")))
- (match_operand:V_VLSI_D 3 "register_operand" " vr")])
- (match_dup 1)))]
- "TARGET_VECTOR && !TARGET_64BIT"
- "vms%B2.vx\t%0,%3,%4,v0.t"
- [(set_attr "type" "vicmp")
- (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>_extended_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_VLSI_D
- (sign_extend:<VEL>
- (match_operand:<VSUBEL> 5 "register_operand" " r, r, r, r")))
- (match_operand:V_VLSI_D 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) && !TARGET_64BIT"
- "vms%B3.vx\t%0,%4,%5%p1"
- [(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")
- (set_attr "spec_restriction" "thv,thv,rvv,rvv")])
-
-(define_insn "*pred_eqne<mode>_extended_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_VLSI_D
- (sign_extend:<VEL>
- (match_operand:<VSUBEL> 5 "register_operand" " r, r, r, r, r")))
- (match_operand:V_VLSI_D 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) && !TARGET_64BIT"
- "vms%B3.vx\t%0,%4,%5%p1"
- [(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")
- (set_attr "spec_restriction" "none,thv,thv,none,none")])
-
;; GE, vmsge.vx/vmsgeu.vx
;;
;; unmasked va >= x
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/integer-cmp-eqne.c b/gcc/testsuite/gcc.target/riscv/rvv/base/integer-cmp-eqne.c
new file mode 100644
index 00000000000..52b844cc29d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/integer-cmp-eqne.c
@@ -0,0 +1,66 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64 -O3" } */
+
+#include "riscv_vector.h"
+
+#define CMP_VF_1(ID, S, OP) \
+ vbool##S##_t test_1_##ID##_##S##_##OP (vint##S##m1_t op1, int##S##_t op2, \
+ size_t vl) \
+ { \
+ return __riscv_vms##OP##_vx_i##S##m1_b##S (op1, op2, vl); \
+ }
+
+CMP_VF_1 (0, 8, eq)
+CMP_VF_1 (1, 16, eq)
+CMP_VF_1 (2, 32, eq)
+CMP_VF_1 (3, 64, eq)
+
+CMP_VF_1 (0, 8, ne)
+CMP_VF_1 (1, 16, ne)
+CMP_VF_1 (2, 32, ne)
+CMP_VF_1 (3, 64, ne)
+
+#define CMP_VF_2(ID, S, OP, IMM) \
+ vbool##S##_t test_2_##ID##_##S##_##OP (vint##S##m1_t op1, size_t vl) \
+ { \
+ return __riscv_vms##OP##_vx_i##S##m1_b##S (op1, IMM, vl); \
+ }
+
+CMP_VF_2 (0, 8, eq, -16)
+CMP_VF_2 (1, 8, eq, 15)
+CMP_VF_2 (2, 8, eq, -17)
+CMP_VF_2 (3, 8, eq, 16)
+CMP_VF_2 (4, 16, eq, -16)
+CMP_VF_2 (5, 16, eq, 15)
+CMP_VF_2 (6, 16, eq, -17)
+CMP_VF_2 (7, 16, eq, 16)
+CMP_VF_2 (8, 32, eq, -16)
+CMP_VF_2 (9, 32, eq, 15)
+CMP_VF_2 (10, 32, eq, -17)
+CMP_VF_2 (11, 32, eq, 16)
+CMP_VF_2 (12, 64, eq, -16)
+CMP_VF_2 (13, 64, eq, 15)
+CMP_VF_2 (14, 64, eq, -17)
+CMP_VF_2 (15, 64, eq, 16)
+
+CMP_VF_2 (0, 8, ne, -16)
+CMP_VF_2 (1, 8, ne, 15)
+CMP_VF_2 (2, 8, ne, -17)
+CMP_VF_2 (3, 8, ne, 16)
+CMP_VF_2 (4, 16, ne, -16)
+CMP_VF_2 (5, 16, ne, 15)
+CMP_VF_2 (6, 16, ne, -17)
+CMP_VF_2 (7, 16, ne, 16)
+CMP_VF_2 (8, 32, ne, -16)
+CMP_VF_2 (9, 32, ne, 15)
+CMP_VF_2 (10, 32, ne, -17)
+CMP_VF_2 (11, 32, ne, 16)
+CMP_VF_2 (12, 64, ne, -16)
+CMP_VF_2 (13, 64, ne, 15)
+CMP_VF_2 (14, 64, ne, -17)
+CMP_VF_2 (15, 64, ne, 16)
+
+/* { dg-final { scan-assembler-times {vmseq\.vx} 12 } } */
+/* { dg-final { scan-assembler-times {vmsne\.vx} 12 } } */
+/* { dg-final { scan-assembler-times {vmseq\.vi} 8 } } */
+/* { dg-final { scan-assembler-times {vmsne\.vi} 8 } } */
--
2.45.1
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH v2] RISC-V: Remove integer vector eqne pattern
2024-06-20 3:28 [PATCH v2] RISC-V: Remove integer vector eqne pattern demin.han
@ 2024-06-20 9:38 ` 钟居哲
2024-06-23 4:04 ` Jeff Law
1 sibling, 0 replies; 3+ messages in thread
From: 钟居哲 @ 2024-06-20 9:38 UTC (permalink / raw)
To: demin.han, gcc-patches; +Cc: kito.cheng, pan2.li, Jeff Law, rdapp.gcc
[-- Attachment #1: Type: text/plain, Size: 26323 bytes --]
LGTM.
juzhe.zhong@rivai.ai
From: demin.han
Date: 2024-06-20 11:28
To: gcc-patches
CC: juzhe.zhong; kito.cheng; pan2.li; jeffreyalaw; rdapp.gcc
Subject: [PATCH v2] RISC-V: Remove integer vector eqne pattern
We can unify eqne and other comparison operations.
Tested on RV32 and RV64.
gcc/ChangeLog:
* config/riscv/predicates.md (comparison_except_eqge_operator): Only
exclude ge
(comparison_except_ge_operator): Ditto
* config/riscv/riscv-string.cc (expand_rawmemchr): Use cmp pattern
(expand_strcmp): Ditto
* config/riscv/riscv-vector-builtins-bases.cc: Remove eqne cond
* config/riscv/vector.md (@pred_eqne<mode>_scalar): Remove eqne
patterns
(*pred_eqne<mode>_scalar_merge_tie_mask): Ditto
(*pred_eqne<mode>_scalar): Ditto
(*pred_eqne<mode>_scalar_narrow): Ditto
(*pred_eqne<mode>_extended_scalar_merge_tie_mask): Ditto
(*pred_eqne<mode>_extended_scalar): Ditto
(*pred_eqne<mode>_extended_scalar_narrow): Ditto
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/base/integer-cmp-eqne.c: New test.
Signed-off-by: demin.han <demin.han@starfivetech.com>
---
v2 changes:
1. add test
gcc/config/riscv/predicates.md | 4 +-
gcc/config/riscv/riscv-string.cc | 4 +-
.../riscv/riscv-vector-builtins-bases.cc | 3 -
gcc/config/riscv/vector.md | 279 +-----------------
.../riscv/rvv/base/integer-cmp-eqne.c | 66 +++++
5 files changed, 81 insertions(+), 275 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/integer-cmp-eqne.c
diff --git a/gcc/config/riscv/predicates.md b/gcc/config/riscv/predicates.md
index 0fb5729fdcf..9971fabc587 100644
--- a/gcc/config/riscv/predicates.md
+++ b/gcc/config/riscv/predicates.md
@@ -568,8 +568,8 @@ (define_predicate "ltge_operator"
(define_predicate "comparison_except_ltge_operator"
(match_code "eq,ne,le,leu,gt,gtu"))
-(define_predicate "comparison_except_eqge_operator"
- (match_code "le,leu,gt,gtu,lt,ltu"))
+(define_predicate "comparison_except_ge_operator"
+ (match_code "eq,ne,le,leu,gt,gtu,lt,ltu"))
(define_predicate "ge_operator"
(match_code "ge,geu"))
diff --git a/gcc/config/riscv/riscv-string.cc b/gcc/config/riscv/riscv-string.cc
index 83e7afbd693..4702001bd9b 100644
--- a/gcc/config/riscv/riscv-string.cc
+++ b/gcc/config/riscv/riscv-string.cc
@@ -1342,7 +1342,7 @@ expand_rawmemchr (machine_mode mode, rtx dst, rtx haystack, rtx needle,
/* Compare needle with haystack and store in a mask. */
rtx eq = gen_rtx_EQ (mask_mode, gen_const_vec_duplicate (vmode, needle), vec);
rtx vmsops[] = {mask, eq, vec, needle};
- emit_nonvlmax_insn (code_for_pred_eqne_scalar (vmode),
+ emit_nonvlmax_insn (code_for_pred_cmp_scalar (vmode),
riscv_vector::COMPARE_OP, vmsops, cnt);
/* Find the first bit in the mask. */
@@ -1468,7 +1468,7 @@ expand_strcmp (rtx result, rtx src1, rtx src2, rtx nbytes,
= gen_rtx_EQ (mask_mode, gen_const_vec_duplicate (vmode, CONST0_RTX (mode)),
vec1);
rtx vmsops1[] = {mask0, eq0, vec1, CONST0_RTX (mode)};
- emit_nonvlmax_insn (code_for_pred_eqne_scalar (vmode),
+ emit_nonvlmax_insn (code_for_pred_cmp_scalar (vmode),
riscv_vector::COMPARE_OP, vmsops1, cnt);
/* Look for vec1 != vec2 (includes vec2[i] == 0). */
diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc
index 596b88cc8a3..6483faba39c 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
@@ -718,9 +718,6 @@ public:
if (CODE == GE || CODE == GEU)
return e.use_compare_insn (CODE, code_for_pred_ge_scalar (
e.vector_mode ()));
- else 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 f8fae6557d9..fe18ee5b5f7 100644
--- a/gcc/config/riscv/vector.md
+++ b/gcc/config/riscv/vector.md
@@ -4704,7 +4704,7 @@ (define_expand "@pred_cmp<mode>_scalar"
(match_operand 8 "const_int_operand")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 3 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_QHS 4 "register_operand")
(vec_duplicate:V_VLSI_QHS
(match_operand:<VEL> 5 "register_operand"))])
@@ -4722,7 +4722,7 @@ (define_insn "*pred_cmp<mode>_scalar_merge_tie_mask"
(match_operand 7 "const_int_operand" " i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 2 "comparison_except_eqge_operator"
+ (match_operator:<VM> 2 "comparison_except_ge_operator"
[(match_operand:V_VLSI_QHS 3 "register_operand" " vr")
(vec_duplicate:V_VLSI_QHS
(match_operand:<VEL> 4 "register_operand" " r"))])
@@ -4747,7 +4747,7 @@ (define_insn "*pred_cmp<mode>_scalar"
(match_operand 8 "const_int_operand" " i, i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 3 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_QHS 4 "register_operand" " vr, vr, vr, vr")
(vec_duplicate:V_VLSI_QHS
(match_operand:<VEL> 5 "register_operand" " r, r, r, r"))])
@@ -4769,7 +4769,7 @@ (define_insn "*pred_cmp<mode>_scalar_narrow"
(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 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_QHS 4 "register_operand" " vr, 0, 0, vr, vr")
(vec_duplicate:V_VLSI_QHS
(match_operand:<VEL> 5 "register_operand" " r, r, r, r, r"))])
@@ -4780,92 +4780,6 @@ (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_VLSI_QHS
- (match_operand:<VEL> 5 "register_operand"))
- (match_operand:V_VLSI_QHS 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_VLSI_QHS
- (match_operand:<VEL> 4 "register_operand" " r"))
- (match_operand:V_VLSI_QHS 3 "register_operand" " vr")])
- (match_dup 1)))]
- "TARGET_VECTOR"
- "vms%B2.vx\t%0,%3,%4,v0.t"
- [(set_attr "type" "vicmp")
- (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_VLSI_QHS
- (match_operand:<VEL> 5 "register_operand" " r, r, r, r"))
- (match_operand:V_VLSI_QHS 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)"
- "vms%B3.vx\t%0,%4,%5%p1"
- [(set_attr "type" "vicmp")
- (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_VLSI_QHS
- (match_operand:<VEL> 5 "register_operand" " r, r, r, r, r"))
- (match_operand:V_VLSI_QHS 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)"
- "vms%B3.vx\t%0,%4,%5%p1"
- [(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")
- (set_attr "spec_restriction" "none,thv,thv,none,none")])
-
;; Handle GET_MODE_INNER (mode) = DImode. We need to split them since
;; we need to deal with SEW = 64 in RV32 system.
(define_expand "@pred_cmp<mode>_scalar"
@@ -4878,7 +4792,7 @@ (define_expand "@pred_cmp<mode>_scalar"
(match_operand 8 "const_int_operand")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 3 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_D 4 "register_operand")
(vec_duplicate:V_VLSI_D
(match_operand:<VEL> 5 "reg_or_int_operand"))])
@@ -4908,39 +4822,6 @@ (define_expand "@pred_cmp<mode>_scalar"
DONE;
})
-(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_VLSI_D
- (match_operand:<VEL> 5 "reg_or_int_operand"))
- (match_operand:V_VLSI_D 4 "register_operand")])
- (match_operand:<VM> 2 "vector_merge_operand")))]
- "TARGET_VECTOR"
-{
- enum rtx_code code = GET_CODE (operands[3]);
- if (riscv_vector::sew64_scalar_helper (
- operands,
- /* scalar op */&operands[5],
- /* vl */operands[6],
- <MODE>mode,
- riscv_vector::has_vi_variant_p (code, operands[5]),
- [] (rtx *operands, rtx boardcast_scalar) {
- emit_insn (gen_pred_cmp<mode> (operands[0], operands[1],
- operands[2], operands[3], operands[4], boardcast_scalar,
- operands[6], operands[7], operands[8]));
- },
- (riscv_vector::avl_type) INTVAL (operands[8])))
- DONE;
-})
-
(define_insn "*pred_cmp<mode>_scalar_merge_tie_mask"
[(set (match_operand:<VM> 0 "register_operand" "=vm")
(if_then_else:<VM>
@@ -4951,7 +4832,7 @@ (define_insn "*pred_cmp<mode>_scalar_merge_tie_mask"
(match_operand 7 "const_int_operand" " i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 2 "comparison_except_eqge_operator"
+ (match_operator:<VM> 2 "comparison_except_ge_operator"
[(match_operand:V_VLSI_D 3 "register_operand" " vr")
(vec_duplicate:V_VLSI_D
(match_operand:<VEL> 4 "register_operand" " r"))])
@@ -4965,30 +4846,6 @@ (define_insn "*pred_cmp<mode>_scalar_merge_tie_mask"
(set (attr "ma") (symbol_ref "riscv_vector::get_ma(operands[6])"))
(set (attr "avl_type_idx") (const_int 7))])
-(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_VLSI_D
- (match_operand:<VEL> 4 "register_operand" " r"))
- (match_operand:V_VLSI_D 3 "register_operand" " vr")])
- (match_dup 1)))]
- "TARGET_VECTOR"
- "vms%B2.vx\t%0,%3,%4,v0.t"
- [(set_attr "type" "vicmp")
- (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_cmp<mode>_scalar"
[(set (match_operand:<VM> 0 "register_operand" "=vr, vr, &vr, &vr")
@@ -5000,7 +4857,7 @@ (define_insn "*pred_cmp<mode>_scalar"
(match_operand 8 "const_int_operand" " i, i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 3 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_D 4 "register_operand" " vr, vr, vr, vr")
(vec_duplicate:V_VLSI_D
(match_operand:<VEL> 5 "register_operand" " r, r, r, r"))])
@@ -5022,7 +4879,7 @@ (define_insn "*pred_cmp<mode>_scalar_narrow"
(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 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_D 4 "register_operand" " vr, 0, 0, vr, vr")
(vec_duplicate:V_VLSI_D
(match_operand:<VEL> 5 "register_operand" " r, r, r, r, r"))])
@@ -5033,50 +4890,6 @@ (define_insn "*pred_cmp<mode>_scalar_narrow"
(set_attr "mode" "<MODE>")
(set_attr "spec_restriction" "none,thv,thv,none,none")])
-;; 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_VLSI_D
- (match_operand:<VEL> 5 "register_operand" " r, r, r, r"))
- (match_operand:V_VLSI_D 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)"
- "vms%B3.vx\t%0,%4,%5%p1"
- [(set_attr "type" "vicmp")
- (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_VLSI_D
- (match_operand:<VEL> 5 "register_operand" " r, r, r, r, r"))
- (match_operand:V_VLSI_D 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)"
- "vms%B3.vx\t%0,%4,%5%p1"
- [(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")
- (set_attr "spec_restriction" "none,thv,thv,none,none")])
-
(define_insn "*pred_cmp<mode>_extended_scalar_merge_tie_mask"
[(set (match_operand:<VM> 0 "register_operand" "=vm")
(if_then_else:<VM>
@@ -5087,7 +4900,7 @@ (define_insn "*pred_cmp<mode>_extended_scalar_merge_tie_mask"
(match_operand 7 "const_int_operand" " i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 2 "comparison_except_eqge_operator"
+ (match_operator:<VM> 2 "comparison_except_ge_operator"
[(match_operand:V_VLSI_D 3 "register_operand" " vr")
(vec_duplicate:V_VLSI_D
(sign_extend:<VEL>
@@ -5113,7 +4926,7 @@ (define_insn "*pred_cmp<mode>_extended_scalar"
(match_operand 8 "const_int_operand" " i, i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
- (match_operator:<VM> 3 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_D 4 "register_operand" " vr, vr, vr, vr")
(vec_duplicate:V_VLSI_D
(sign_extend:<VEL>
@@ -5135,7 +4948,7 @@ (define_insn "*pred_cmp<mode>_extended_scalar_narrow"
(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 "comparison_except_eqge_operator"
+ (match_operator:<VM> 3 "comparison_except_ge_operator"
[(match_operand:V_VLSI_D 4 "register_operand" " vr, 0, 0, vr, vr")
(vec_duplicate:V_VLSI_D
(sign_extend:<VEL>
@@ -5147,76 +4960,6 @@ (define_insn "*pred_cmp<mode>_extended_scalar_narrow"
(set_attr "mode" "<MODE>")
(set_attr "spec_restriction" "none,thv,thv,none,none")])
-(define_insn "*pred_eqne<mode>_extended_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_VLSI_D
- (sign_extend:<VEL>
- (match_operand:<VSUBEL> 4 "register_operand" " r")))
- (match_operand:V_VLSI_D 3 "register_operand" " vr")])
- (match_dup 1)))]
- "TARGET_VECTOR && !TARGET_64BIT"
- "vms%B2.vx\t%0,%3,%4,v0.t"
- [(set_attr "type" "vicmp")
- (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>_extended_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_VLSI_D
- (sign_extend:<VEL>
- (match_operand:<VSUBEL> 5 "register_operand" " r, r, r, r")))
- (match_operand:V_VLSI_D 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) && !TARGET_64BIT"
- "vms%B3.vx\t%0,%4,%5%p1"
- [(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")
- (set_attr "spec_restriction" "thv,thv,rvv,rvv")])
-
-(define_insn "*pred_eqne<mode>_extended_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_VLSI_D
- (sign_extend:<VEL>
- (match_operand:<VSUBEL> 5 "register_operand" " r, r, r, r, r")))
- (match_operand:V_VLSI_D 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) && !TARGET_64BIT"
- "vms%B3.vx\t%0,%4,%5%p1"
- [(set_attr "type" "vicmp")
- (set_attr "mode" "<MODE>")
- (set_attr "spec_restriction" "none,thv,thv,none,none")])
-
;; GE, vmsge.vx/vmsgeu.vx
;;
;; unmasked va >= x
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/integer-cmp-eqne.c b/gcc/testsuite/gcc.target/riscv/rvv/base/integer-cmp-eqne.c
new file mode 100644
index 00000000000..52b844cc29d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/integer-cmp-eqne.c
@@ -0,0 +1,66 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64 -O3" } */
+
+#include "riscv_vector.h"
+
+#define CMP_VF_1(ID, S, OP) \
+ vbool##S##_t test_1_##ID##_##S##_##OP (vint##S##m1_t op1, int##S##_t op2, \
+ size_t vl) \
+ { \
+ return __riscv_vms##OP##_vx_i##S##m1_b##S (op1, op2, vl); \
+ }
+
+CMP_VF_1 (0, 8, eq)
+CMP_VF_1 (1, 16, eq)
+CMP_VF_1 (2, 32, eq)
+CMP_VF_1 (3, 64, eq)
+
+CMP_VF_1 (0, 8, ne)
+CMP_VF_1 (1, 16, ne)
+CMP_VF_1 (2, 32, ne)
+CMP_VF_1 (3, 64, ne)
+
+#define CMP_VF_2(ID, S, OP, IMM) \
+ vbool##S##_t test_2_##ID##_##S##_##OP (vint##S##m1_t op1, size_t vl) \
+ { \
+ return __riscv_vms##OP##_vx_i##S##m1_b##S (op1, IMM, vl); \
+ }
+
+CMP_VF_2 (0, 8, eq, -16)
+CMP_VF_2 (1, 8, eq, 15)
+CMP_VF_2 (2, 8, eq, -17)
+CMP_VF_2 (3, 8, eq, 16)
+CMP_VF_2 (4, 16, eq, -16)
+CMP_VF_2 (5, 16, eq, 15)
+CMP_VF_2 (6, 16, eq, -17)
+CMP_VF_2 (7, 16, eq, 16)
+CMP_VF_2 (8, 32, eq, -16)
+CMP_VF_2 (9, 32, eq, 15)
+CMP_VF_2 (10, 32, eq, -17)
+CMP_VF_2 (11, 32, eq, 16)
+CMP_VF_2 (12, 64, eq, -16)
+CMP_VF_2 (13, 64, eq, 15)
+CMP_VF_2 (14, 64, eq, -17)
+CMP_VF_2 (15, 64, eq, 16)
+
+CMP_VF_2 (0, 8, ne, -16)
+CMP_VF_2 (1, 8, ne, 15)
+CMP_VF_2 (2, 8, ne, -17)
+CMP_VF_2 (3, 8, ne, 16)
+CMP_VF_2 (4, 16, ne, -16)
+CMP_VF_2 (5, 16, ne, 15)
+CMP_VF_2 (6, 16, ne, -17)
+CMP_VF_2 (7, 16, ne, 16)
+CMP_VF_2 (8, 32, ne, -16)
+CMP_VF_2 (9, 32, ne, 15)
+CMP_VF_2 (10, 32, ne, -17)
+CMP_VF_2 (11, 32, ne, 16)
+CMP_VF_2 (12, 64, ne, -16)
+CMP_VF_2 (13, 64, ne, 15)
+CMP_VF_2 (14, 64, ne, -17)
+CMP_VF_2 (15, 64, ne, 16)
+
+/* { dg-final { scan-assembler-times {vmseq\.vx} 12 } } */
+/* { dg-final { scan-assembler-times {vmsne\.vx} 12 } } */
+/* { dg-final { scan-assembler-times {vmseq\.vi} 8 } } */
+/* { dg-final { scan-assembler-times {vmsne\.vi} 8 } } */
--
2.45.1
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH v2] RISC-V: Remove integer vector eqne pattern
2024-06-20 3:28 [PATCH v2] RISC-V: Remove integer vector eqne pattern demin.han
2024-06-20 9:38 ` 钟居哲
@ 2024-06-23 4:04 ` Jeff Law
1 sibling, 0 replies; 3+ messages in thread
From: Jeff Law @ 2024-06-23 4:04 UTC (permalink / raw)
To: demin.han, gcc-patches; +Cc: juzhe.zhong, kito.cheng, pan2.li, rdapp.gcc
On 6/19/24 9:28 PM, demin.han wrote:
> We can unify eqne and other comparison operations.
>
> Tested on RV32 and RV64.
>
> gcc/ChangeLog:
>
> * config/riscv/predicates.md (comparison_except_eqge_operator): Only
> exclude ge
> (comparison_except_ge_operator): Ditto
> * config/riscv/riscv-string.cc (expand_rawmemchr): Use cmp pattern
> (expand_strcmp): Ditto
> * config/riscv/riscv-vector-builtins-bases.cc: Remove eqne cond
> * config/riscv/vector.md (@pred_eqne<mode>_scalar): Remove eqne
> patterns
> (*pred_eqne<mode>_scalar_merge_tie_mask): Ditto
> (*pred_eqne<mode>_scalar): Ditto
> (*pred_eqne<mode>_scalar_narrow): Ditto
> (*pred_eqne<mode>_extended_scalar_merge_tie_mask): Ditto
> (*pred_eqne<mode>_extended_scalar): Ditto
> (*pred_eqne<mode>_extended_scalar_narrow): Ditto
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/riscv/rvv/base/integer-cmp-eqne.c: New test.
Thanks. I've pushed this to the trunk.
jeff
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2024-06-23 4:04 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2024-06-20 3:28 [PATCH v2] RISC-V: Remove integer vector eqne pattern demin.han
2024-06-20 9:38 ` 钟居哲
2024-06-23 4:04 ` Jeff Law
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).