From: Jun Sha (Joshua) Date: Fri, 12 Jan 2024 03:22:10 +0000 (+0800) Subject: RISC-V: Handle differences between XTheadvector and Vector X-Git-Tag: basepoints/gcc-15~1894 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=2d7205eb2c3b175a86aab92bb652314f308f9c05;p=thirdparty%2Fgcc.git RISC-V: Handle differences between XTheadvector and Vector This patch is to handle the differences in instruction generation between Vector and XTheadVector. In this version, we only support partial xtheadvector instructions that leverage directly from current RVV1.0 with simple adding "th." prefix. For different name xtheadvector instructions but share same patterns as RVV1.0 instructions, we will use ASM targethook to rewrite the whole string of the instructions in the following patches. For some vector patterns that cannot be avoided, we use "!TARGET_XTHEADVECTOR" to disable them in vector.md in order not to generate instructions that xtheadvector does not support, like vmv1r. gcc/ChangeLog: * config.gcc: Add files for XTheadVector intrinsics. * config/riscv/autovec.md: Guard XTheadVector. * config/riscv/predicates.md: Disable immediate vl for XTheadVector. * config/riscv/riscv-c.cc (riscv_pragma_intrinsic): Add pragma for XTheadVector. * config/riscv/riscv-string.cc (riscv_expand_block_move): Guard XTheadVector. * config/riscv/riscv-v.cc (vls_mode_valid_p): Avoid autovec. * config/riscv/riscv-vector-builtins-bases.cc: Do not normalize vsetvl instructions for XTheadVector. * config/riscv/riscv-vector-builtins-shapes.cc (check_type): New check type function. (build_one): Adjust for XTheadVector. * config/riscv/riscv-vector-switch.def (ENTRY): Disable fractional mode for the XTheadVector extension. (TUPLE_ENTRY): Likewise. * config/riscv/riscv.cc (riscv_v_adjust_bytesize): Guard XTheadVector. (riscv_preferred_simd_mode): Likewsie. (riscv_autovectorize_vector_modes): Likewise. (riscv_vector_mode_supported_any_target_p): Likewise. (TARGET_VECTOR_MODE_SUPPORTED_ANY_TARGET_P): Likewise. * config/riscv/thead.cc (th_asm_output_opcode): Rewrite vsetvl instructions. * config/riscv/vector.md: Include thead-vector.md and change fractional LMUL into 1 for vbool. * config/riscv/riscv_th_vector.h: New file. * config/riscv/thead-vector.md: New file. gcc/testsuite/ChangeLog: * gcc.target/riscv/rvv/base/pragma-1.c: Add XTheadVector. * gcc.target/riscv/rvv/base/abi-1.c: Exclude XTheadVector. * lib/target-supports.exp: Add target for XTheadVector. Co-authored-by: Jin Ma Co-authored-by: Xianmiao Qu Co-authored-by: Christoph Müllner --- diff --git a/gcc/config.gcc b/gcc/config.gcc index 00355509c92b..b2d7d7dd4754 100644 --- a/gcc/config.gcc +++ b/gcc/config.gcc @@ -549,7 +549,7 @@ riscv*) extra_objs="${extra_objs} riscv-vector-builtins.o riscv-vector-builtins-shapes.o riscv-vector-builtins-bases.o" extra_objs="${extra_objs} thead.o riscv-target-attr.o" d_target_objs="riscv-d.o" - extra_headers="riscv_vector.h riscv_crypto.h riscv_bitmanip.h" + extra_headers="riscv_vector.h riscv_crypto.h riscv_bitmanip.h riscv_th_vector.h" target_gtfiles="$target_gtfiles \$(srcdir)/config/riscv/riscv-vector-builtins.cc" target_gtfiles="$target_gtfiles \$(srcdir)/config/riscv/riscv-vector-builtins.h" ;; diff --git a/gcc/config/riscv/autovec.md b/gcc/config/riscv/autovec.md index 5ec1c59bdd44..3b32369f68c5 100644 --- a/gcc/config/riscv/autovec.md +++ b/gcc/config/riscv/autovec.md @@ -2605,7 +2605,7 @@ [(match_operand 0 "register_operand") (match_operand 1 "memory_operand") (match_operand:ANYI 2 "const_int_operand")] - "TARGET_VECTOR" + "TARGET_VECTOR && !TARGET_XTHEADVECTOR" { riscv_vector::expand_rawmemchr(mode, operands[0], operands[1], operands[2]); diff --git a/gcc/config/riscv/predicates.md b/gcc/config/riscv/predicates.md index b1a79cae50ac..0337da882841 100644 --- a/gcc/config/riscv/predicates.md +++ b/gcc/config/riscv/predicates.md @@ -428,7 +428,9 @@ ;; Predicates for the V extension. (define_special_predicate "vector_length_operand" (ior (match_operand 0 "pmode_register_operand") - (match_operand 0 "const_csr_operand"))) + (and (ior (match_test "TARGET_XTHEADVECTOR && rtx_equal_p (op, const0_rtx)") + (match_test "!TARGET_XTHEADVECTOR")) + (match_operand 0 "const_csr_operand")))) (define_special_predicate "autovec_length_operand" (ior (match_operand 0 "pmode_register_operand") diff --git a/gcc/config/riscv/riscv-c.cc b/gcc/config/riscv/riscv-c.cc index 422ddc2c308a..2e306057347e 100644 --- a/gcc/config/riscv/riscv-c.cc +++ b/gcc/config/riscv/riscv-c.cc @@ -195,7 +195,8 @@ riscv_pragma_intrinsic (cpp_reader *) const char *name = TREE_STRING_POINTER (x); - if (strcmp (name, "vector") == 0) + if (strcmp (name, "vector") == 0 + || strcmp (name, "xtheadvector") == 0) { if (!TARGET_VECTOR) { diff --git a/gcc/config/riscv/riscv-string.cc b/gcc/config/riscv/riscv-string.cc index f227b8667ced..b09b51d7526b 100644 --- a/gcc/config/riscv/riscv-string.cc +++ b/gcc/config/riscv/riscv-string.cc @@ -773,7 +773,8 @@ riscv_expand_block_move_scalar (rtx dest, rtx src, rtx length) bool riscv_expand_block_move (rtx dest, rtx src, rtx length) { - if (TARGET_VECTOR && stringop_strategy & STRATEGY_VECTOR) + if ((TARGET_VECTOR && !TARGET_XTHEADVECTOR) + && stringop_strategy & STRATEGY_VECTOR) { bool ok = riscv_vector::expand_block_move (dest, src, length); if (ok) diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc index 7ae579ba8901..93a1238a5abb 100644 --- a/gcc/config/riscv/riscv-v.cc +++ b/gcc/config/riscv/riscv-v.cc @@ -4403,7 +4403,7 @@ cmp_lmul_gt_one (machine_mode mode) bool vls_mode_valid_p (machine_mode vls_mode) { - if (!TARGET_VECTOR) + if (!TARGET_VECTOR || TARGET_XTHEADVECTOR) return false; if (riscv_autovec_preference == RVV_SCALABLE) diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc index fba981244739..1aa6e3c66655 100644 --- a/gcc/config/riscv/riscv-vector-builtins-bases.cc +++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc @@ -131,23 +131,37 @@ public: tree type = builtin_types[e.type.index].vector; machine_mode mode = TYPE_MODE (type); - /* Normalize same RATO (SEW/LMUL) into same vsetvl instruction. - - - e8,mf8/e16,mf4/e32,mf2/e64,m1 --> e8mf8 - - e8,mf4/e16,mf2/e32,m1/e64,m2 --> e8mf4 - - e8,mf2/e16,m1/e32,m2/e64,m4 --> e8mf2 - - e8,m1/e16,m2/e32,m4/e64,m8 --> e8m1 - - e8,m2/e16,m4/e32,m8 --> e8m2 - - e8,m4/e16,m8 --> e8m4 - - e8,m8 --> e8m8 - */ - /* SEW. */ - e.add_input_operand (Pmode, gen_int_mode (8, Pmode)); - - /* LMUL. */ - machine_mode e8_mode - = get_vector_mode (QImode, GET_MODE_NUNITS (mode)).require (); - e.add_input_operand (Pmode, gen_int_mode (get_vlmul (e8_mode), Pmode)); + + if (TARGET_XTHEADVECTOR) + { + machine_mode inner_mode = GET_MODE_INNER (mode); + /* SEW. */ + e.add_input_operand (Pmode, + gen_int_mode (GET_MODE_BITSIZE (inner_mode), Pmode)); + /* LMUL. */ + e.add_input_operand (Pmode, + gen_int_mode (get_vlmul (mode), Pmode)); + } + else + { + /* Normalize same RATO (SEW/LMUL) into same vsetvl instruction. + + - e8,mf8/e16,mf4/e32,mf2/e64,m1 --> e8mf8 + - e8,mf4/e16,mf2/e32,m1/e64,m2 --> e8mf4 + - e8,mf2/e16,m1/e32,m2/e64,m4 --> e8mf2 + - e8,m1/e16,m2/e32,m4/e64,m8 --> e8m1 + - e8,m2/e16,m4/e32,m8 --> e8m2 + - e8,m4/e16,m8 --> e8m4 + - e8,m8 --> e8m8 + */ + /* SEW. */ + e.add_input_operand (Pmode, gen_int_mode (8, Pmode)); + + /* LMUL. */ + machine_mode e8_mode + = get_vector_mode (QImode, GET_MODE_NUNITS (mode)).require (); + e.add_input_operand (Pmode, gen_int_mode (get_vlmul (e8_mode), Pmode)); + } /* TAIL_ANY. */ e.add_input_operand (Pmode, diff --git a/gcc/config/riscv/riscv-vector-builtins-shapes.cc b/gcc/config/riscv/riscv-vector-builtins-shapes.cc index ee8058dcdb10..1e4f4d53de6f 100644 --- a/gcc/config/riscv/riscv-vector-builtins-shapes.cc +++ b/gcc/config/riscv/riscv-vector-builtins-shapes.cc @@ -33,6 +33,25 @@ namespace riscv_vector { +/* Check whether the RETURN_TYPE and ARGUMENT_TYPES are + valid for the function. */ + +static bool +check_type (tree return_type, vec &argument_types) +{ + tree arg; + unsigned i; + + if (!return_type) + return false; + + FOR_EACH_VEC_ELT (argument_types, i, arg) + if (!arg) + return false; + + return true; +} + /* Add one function instance for GROUP, using operand suffix at index OI, mode suffix at index PAIR && bi and predication suffix at index pred_idx. */ static void @@ -49,6 +68,10 @@ build_one (function_builder &b, const function_group_info &group, group.ops_infos.types[vec_type_idx].index); b.allocate_argument_types (function_instance, argument_types); b.apply_predication (function_instance, return_type, argument_types); + + if (TARGET_XTHEADVECTOR && !check_type (return_type, argument_types)) + return; + b.add_overloaded_function (function_instance, *group.shape); b.add_unique_function (function_instance, (*group.shape), return_type, argument_types); diff --git a/gcc/config/riscv/riscv-vector-switch.def b/gcc/config/riscv/riscv-vector-switch.def index 1ad26c2a3b29..452283b74166 100644 --- a/gcc/config/riscv/riscv-vector-switch.def +++ b/gcc/config/riscv/riscv-vector-switch.def @@ -68,9 +68,9 @@ Encode the ratio of SEW/LMUL into the mask types. #endif /* Disable modes if TARGET_MIN_VLEN == 32. */ -ENTRY (RVVMF64BI, TARGET_MIN_VLEN > 32, LMUL_F8, 64) -ENTRY (RVVMF32BI, true, LMUL_F4, 32) -ENTRY (RVVMF16BI, true, LMUL_F2, 16) +ENTRY (RVVMF64BI, TARGET_MIN_VLEN > 32, TARGET_XTHEADVECTOR ? LMUL_1 :LMUL_F8, 64) +ENTRY (RVVMF32BI, true, TARGET_XTHEADVECTOR ? LMUL_1 :LMUL_F4, 32) +ENTRY (RVVMF16BI, true, TARGET_XTHEADVECTOR ? LMUL_1 : LMUL_F2 , 16) ENTRY (RVVMF8BI, true, LMUL_1, 8) ENTRY (RVVMF4BI, true, LMUL_2, 4) ENTRY (RVVMF2BI, true, LMUL_4, 2) @@ -81,39 +81,39 @@ ENTRY (RVVM8QI, true, LMUL_8, 1) ENTRY (RVVM4QI, true, LMUL_4, 2) ENTRY (RVVM2QI, true, LMUL_2, 4) ENTRY (RVVM1QI, true, LMUL_1, 8) -ENTRY (RVVMF2QI, true, LMUL_F2, 16) -ENTRY (RVVMF4QI, true, LMUL_F4, 32) -ENTRY (RVVMF8QI, TARGET_MIN_VLEN > 32, LMUL_F8, 64) +ENTRY (RVVMF2QI, !TARGET_XTHEADVECTOR, LMUL_F2, 16) +ENTRY (RVVMF4QI, !TARGET_XTHEADVECTOR, LMUL_F4, 32) +ENTRY (RVVMF8QI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, LMUL_F8, 64) /* Disable modes if TARGET_MIN_VLEN == 32. */ ENTRY (RVVM8HI, true, LMUL_8, 2) ENTRY (RVVM4HI, true, LMUL_4, 4) ENTRY (RVVM2HI, true, LMUL_2, 8) ENTRY (RVVM1HI, true, LMUL_1, 16) -ENTRY (RVVMF2HI, true, LMUL_F2, 32) -ENTRY (RVVMF4HI, TARGET_MIN_VLEN > 32, LMUL_F4, 64) +ENTRY (RVVMF2HI, !TARGET_XTHEADVECTOR, LMUL_F2, 32) +ENTRY (RVVMF4HI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, LMUL_F4, 64) /* Disable modes if TARGET_MIN_VLEN == 32 or !TARGET_VECTOR_ELEN_FP_16. */ ENTRY (RVVM8HF, TARGET_VECTOR_ELEN_FP_16, LMUL_8, 2) ENTRY (RVVM4HF, TARGET_VECTOR_ELEN_FP_16, LMUL_4, 4) ENTRY (RVVM2HF, TARGET_VECTOR_ELEN_FP_16, LMUL_2, 8) ENTRY (RVVM1HF, TARGET_VECTOR_ELEN_FP_16, LMUL_1, 16) -ENTRY (RVVMF2HF, TARGET_VECTOR_ELEN_FP_16, LMUL_F2, 32) -ENTRY (RVVMF4HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32, LMUL_F4, 64) +ENTRY (RVVMF2HF, TARGET_VECTOR_ELEN_FP_16 && !TARGET_XTHEADVECTOR, LMUL_F2, 32) +ENTRY (RVVMF4HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, LMUL_F4, 64) /* Disable modes if TARGET_MIN_VLEN == 32. */ ENTRY (RVVM8SI, true, LMUL_8, 4) ENTRY (RVVM4SI, true, LMUL_4, 8) ENTRY (RVVM2SI, true, LMUL_2, 16) ENTRY (RVVM1SI, true, LMUL_1, 32) -ENTRY (RVVMF2SI, TARGET_MIN_VLEN > 32, LMUL_F2, 64) +ENTRY (RVVMF2SI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, LMUL_F2, 64) /* Disable modes if TARGET_MIN_VLEN == 32 or !TARGET_VECTOR_ELEN_FP_32. */ ENTRY (RVVM8SF, TARGET_VECTOR_ELEN_FP_32, LMUL_8, 4) ENTRY (RVVM4SF, TARGET_VECTOR_ELEN_FP_32, LMUL_4, 8) ENTRY (RVVM2SF, TARGET_VECTOR_ELEN_FP_32, LMUL_2, 16) ENTRY (RVVM1SF, TARGET_VECTOR_ELEN_FP_32, LMUL_1, 32) -ENTRY (RVVMF2SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32, LMUL_F2, 64) +ENTRY (RVVMF2SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, LMUL_F2, 64) /* Disable modes if !TARGET_VECTOR_ELEN_64. */ ENTRY (RVVM8DI, TARGET_VECTOR_ELEN_64, LMUL_8, 8) @@ -140,127 +140,127 @@ ENTRY (RVVM1DF, TARGET_VECTOR_ELEN_FP_64, LMUL_1, 64) #endif TUPLE_ENTRY (RVVM1x8QI, true, RVVM1QI, 8, LMUL_1, 8) -TUPLE_ENTRY (RVVMF2x8QI, true, RVVMF2QI, 8, LMUL_F2, 16) -TUPLE_ENTRY (RVVMF4x8QI, true, RVVMF4QI, 8, LMUL_F4, 32) -TUPLE_ENTRY (RVVMF8x8QI, TARGET_MIN_VLEN > 32, RVVMF8QI, 8, LMUL_F8, 64) +TUPLE_ENTRY (RVVMF2x8QI, !TARGET_XTHEADVECTOR, RVVMF2QI, 8, LMUL_F2, 16) +TUPLE_ENTRY (RVVMF4x8QI, !TARGET_XTHEADVECTOR, RVVMF4QI, 8, LMUL_F4, 32) +TUPLE_ENTRY (RVVMF8x8QI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF8QI, 8, LMUL_F8, 64) TUPLE_ENTRY (RVVM1x7QI, true, RVVM1QI, 7, LMUL_1, 8) -TUPLE_ENTRY (RVVMF2x7QI, true, RVVMF2QI, 7, LMUL_F2, 16) -TUPLE_ENTRY (RVVMF4x7QI, true, RVVMF4QI, 7, LMUL_F4, 32) -TUPLE_ENTRY (RVVMF8x7QI, TARGET_MIN_VLEN > 32, RVVMF8QI, 7, LMUL_F8, 64) +TUPLE_ENTRY (RVVMF2x7QI, !TARGET_XTHEADVECTOR, RVVMF2QI, 7, LMUL_F2, 16) +TUPLE_ENTRY (RVVMF4x7QI, !TARGET_XTHEADVECTOR, RVVMF4QI, 7, LMUL_F4, 32) +TUPLE_ENTRY (RVVMF8x7QI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF8QI, 7, LMUL_F8, 64) TUPLE_ENTRY (RVVM1x6QI, true, RVVM1QI, 6, LMUL_1, 8) -TUPLE_ENTRY (RVVMF2x6QI, true, RVVMF2QI, 6, LMUL_F2, 16) -TUPLE_ENTRY (RVVMF4x6QI, true, RVVMF4QI, 6, LMUL_F4, 32) -TUPLE_ENTRY (RVVMF8x6QI, TARGET_MIN_VLEN > 32, RVVMF8QI, 6, LMUL_F8, 64) +TUPLE_ENTRY (RVVMF2x6QI, !TARGET_XTHEADVECTOR, RVVMF2QI, 6, LMUL_F2, 16) +TUPLE_ENTRY (RVVMF4x6QI, !TARGET_XTHEADVECTOR, RVVMF4QI, 6, LMUL_F4, 32) +TUPLE_ENTRY (RVVMF8x6QI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF8QI, 6, LMUL_F8, 64) TUPLE_ENTRY (RVVM1x5QI, true, RVVM1QI, 5, LMUL_1, 8) -TUPLE_ENTRY (RVVMF2x5QI, true, RVVMF2QI, 5, LMUL_F2, 16) -TUPLE_ENTRY (RVVMF4x5QI, true, RVVMF4QI, 5, LMUL_F4, 32) -TUPLE_ENTRY (RVVMF8x5QI, TARGET_MIN_VLEN > 32, RVVMF8QI, 5, LMUL_F8, 64) +TUPLE_ENTRY (RVVMF2x5QI, !TARGET_XTHEADVECTOR, RVVMF2QI, 5, LMUL_F2, 16) +TUPLE_ENTRY (RVVMF4x5QI, !TARGET_XTHEADVECTOR, RVVMF4QI, 5, LMUL_F4, 32) +TUPLE_ENTRY (RVVMF8x5QI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF8QI, 5, LMUL_F8, 64) TUPLE_ENTRY (RVVM2x4QI, true, RVVM2QI, 4, LMUL_2, 4) TUPLE_ENTRY (RVVM1x4QI, true, RVVM1QI, 4, LMUL_1, 8) -TUPLE_ENTRY (RVVMF2x4QI, true, RVVMF2QI, 4, LMUL_F2, 16) -TUPLE_ENTRY (RVVMF4x4QI, true, RVVMF4QI, 4, LMUL_F4, 32) -TUPLE_ENTRY (RVVMF8x4QI, TARGET_MIN_VLEN > 32, RVVMF8QI, 4, LMUL_F8, 64) +TUPLE_ENTRY (RVVMF2x4QI, !TARGET_XTHEADVECTOR, RVVMF2QI, 4, LMUL_F2, 16) +TUPLE_ENTRY (RVVMF4x4QI, !TARGET_XTHEADVECTOR, RVVMF4QI, 4, LMUL_F4, 32) +TUPLE_ENTRY (RVVMF8x4QI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF8QI, 4, LMUL_F8, 64) TUPLE_ENTRY (RVVM2x3QI, true, RVVM2QI, 3, LMUL_2, 4) TUPLE_ENTRY (RVVM1x3QI, true, RVVM1QI, 3, LMUL_1, 8) -TUPLE_ENTRY (RVVMF2x3QI, true, RVVMF2QI, 3, LMUL_F2, 16) -TUPLE_ENTRY (RVVMF4x3QI, true, RVVMF4QI, 3, LMUL_F4, 32) -TUPLE_ENTRY (RVVMF8x3QI, TARGET_MIN_VLEN > 32, RVVMF8QI, 3, LMUL_F8, 64) +TUPLE_ENTRY (RVVMF2x3QI, !TARGET_XTHEADVECTOR, RVVMF2QI, 3, LMUL_F2, 16) +TUPLE_ENTRY (RVVMF4x3QI, !TARGET_XTHEADVECTOR, RVVMF4QI, 3, LMUL_F4, 32) +TUPLE_ENTRY (RVVMF8x3QI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF8QI, 3, LMUL_F8, 64) TUPLE_ENTRY (RVVM4x2QI, true, RVVM4QI, 2, LMUL_4, 2) TUPLE_ENTRY (RVVM2x2QI, true, RVVM2QI, 2, LMUL_2, 4) TUPLE_ENTRY (RVVM1x2QI, true, RVVM1QI, 2, LMUL_1, 8) -TUPLE_ENTRY (RVVMF2x2QI, true, RVVMF2QI, 2, LMUL_F2, 16) -TUPLE_ENTRY (RVVMF4x2QI, true, RVVMF4QI, 2, LMUL_F4, 32) -TUPLE_ENTRY (RVVMF8x2QI, TARGET_MIN_VLEN > 32, RVVMF8QI, 2, LMUL_F8, 64) +TUPLE_ENTRY (RVVMF2x2QI, !TARGET_XTHEADVECTOR, RVVMF2QI, 2, LMUL_F2, 16) +TUPLE_ENTRY (RVVMF4x2QI, !TARGET_XTHEADVECTOR, RVVMF4QI, 2, LMUL_F4, 32) +TUPLE_ENTRY (RVVMF8x2QI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF8QI, 2, LMUL_F8, 64) TUPLE_ENTRY (RVVM1x8HI, true, RVVM1HI, 8, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x8HI, true, RVVMF2HI, 8, LMUL_F2, 32) -TUPLE_ENTRY (RVVMF4x8HI, TARGET_MIN_VLEN > 32, RVVMF4HI, 8, LMUL_F4, 64) +TUPLE_ENTRY (RVVMF2x8HI, !TARGET_XTHEADVECTOR, RVVMF2HI, 8, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF4x8HI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF4HI, 8, LMUL_F4, 64) TUPLE_ENTRY (RVVM1x7HI, true, RVVM1HI, 7, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x7HI, true, RVVMF2HI, 7, LMUL_F2, 32) -TUPLE_ENTRY (RVVMF4x7HI, TARGET_MIN_VLEN > 32, RVVMF4HI, 7, LMUL_F4, 64) +TUPLE_ENTRY (RVVMF2x7HI, !TARGET_XTHEADVECTOR, RVVMF2HI, 7, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF4x7HI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF4HI, 7, LMUL_F4, 64) TUPLE_ENTRY (RVVM1x6HI, true, RVVM1HI, 6, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x6HI, true, RVVMF2HI, 6, LMUL_F2, 32) -TUPLE_ENTRY (RVVMF4x6HI, TARGET_MIN_VLEN > 32, RVVMF4HI, 6, LMUL_F4, 64) +TUPLE_ENTRY (RVVMF2x6HI, !TARGET_XTHEADVECTOR, RVVMF2HI, 6, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF4x6HI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF4HI, 6, LMUL_F4, 64) TUPLE_ENTRY (RVVM1x5HI, true, RVVM1HI, 5, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x5HI, true, RVVMF2HI, 5, LMUL_F2, 32) -TUPLE_ENTRY (RVVMF4x5HI, TARGET_MIN_VLEN > 32, RVVMF4HI, 5, LMUL_F4, 64) +TUPLE_ENTRY (RVVMF2x5HI, !TARGET_XTHEADVECTOR, RVVMF2HI, 5, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF4x5HI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF4HI, 5, LMUL_F4, 64) TUPLE_ENTRY (RVVM2x4HI, true, RVVM2HI, 4, LMUL_2, 8) TUPLE_ENTRY (RVVM1x4HI, true, RVVM1HI, 4, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x4HI, true, RVVMF2HI, 4, LMUL_F2, 32) -TUPLE_ENTRY (RVVMF4x4HI, TARGET_MIN_VLEN > 32, RVVMF4HI, 4, LMUL_F4, 64) +TUPLE_ENTRY (RVVMF2x4HI, !TARGET_XTHEADVECTOR, RVVMF2HI, 4, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF4x4HI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF4HI, 4, LMUL_F4, 64) TUPLE_ENTRY (RVVM2x3HI, true, RVVM2HI, 3, LMUL_2, 8) TUPLE_ENTRY (RVVM1x3HI, true, RVVM1HI, 3, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x3HI, true, RVVMF2HI, 3, LMUL_F2, 32) -TUPLE_ENTRY (RVVMF4x3HI, TARGET_MIN_VLEN > 32, RVVMF4HI, 3, LMUL_F4, 64) +TUPLE_ENTRY (RVVMF2x3HI, !TARGET_XTHEADVECTOR, RVVMF2HI, 3, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF4x3HI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF4HI, 3, LMUL_F4, 64) TUPLE_ENTRY (RVVM4x2HI, true, RVVM4HI, 2, LMUL_4, 4) TUPLE_ENTRY (RVVM2x2HI, true, RVVM2HI, 2, LMUL_2, 8) TUPLE_ENTRY (RVVM1x2HI, true, RVVM1HI, 2, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x2HI, true, RVVMF2HI, 2, LMUL_F2, 32) -TUPLE_ENTRY (RVVMF4x2HI, TARGET_MIN_VLEN > 32, RVVMF4HI, 2, LMUL_F4, 64) +TUPLE_ENTRY (RVVMF2x2HI, !TARGET_XTHEADVECTOR, RVVMF2HI, 2, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF4x2HI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF4HI, 2, LMUL_F4, 64) TUPLE_ENTRY (RVVM1x8HF, TARGET_VECTOR_ELEN_FP_16, RVVM1HF, 8, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x8HF, TARGET_VECTOR_ELEN_FP_16, RVVMF2HF, 8, LMUL_F2, 32) -TUPLE_ENTRY (RVVMF4x8HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32, RVVMF4HF, 8, LMUL_F4, 64) +TUPLE_ENTRY (RVVMF2x8HF, TARGET_VECTOR_ELEN_FP_16 && !TARGET_XTHEADVECTOR, RVVMF2HF, 8, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF4x8HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF4HF, 8, LMUL_F4, 64) TUPLE_ENTRY (RVVM1x7HF, TARGET_VECTOR_ELEN_FP_16, RVVM1HF, 7, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x7HF, TARGET_VECTOR_ELEN_FP_16, RVVMF2HF, 7, LMUL_F2, 32) -TUPLE_ENTRY (RVVMF4x7HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32, RVVMF4HF, 7, LMUL_F4, 64) +TUPLE_ENTRY (RVVMF2x7HF, TARGET_VECTOR_ELEN_FP_16 && !TARGET_XTHEADVECTOR, RVVMF2HF, 7, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF4x7HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF4HF, 7, LMUL_F4, 64) TUPLE_ENTRY (RVVM1x6HF, TARGET_VECTOR_ELEN_FP_16, RVVM1HF, 6, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x6HF, TARGET_VECTOR_ELEN_FP_16, RVVMF2HF, 6, LMUL_F2, 32) -TUPLE_ENTRY (RVVMF4x6HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32, RVVMF4HF, 6, LMUL_F4, 64) +TUPLE_ENTRY (RVVMF2x6HF, TARGET_VECTOR_ELEN_FP_16 && !TARGET_XTHEADVECTOR, RVVMF2HF, 6, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF4x6HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF4HF, 6, LMUL_F4, 64) TUPLE_ENTRY (RVVM1x5HF, TARGET_VECTOR_ELEN_FP_16, RVVM1HF, 5, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x5HF, TARGET_VECTOR_ELEN_FP_16, RVVMF2HF, 5, LMUL_F2, 32) -TUPLE_ENTRY (RVVMF4x5HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32, RVVMF4HF, 5, LMUL_F4, 64) +TUPLE_ENTRY (RVVMF2x5HF, TARGET_VECTOR_ELEN_FP_16 && !TARGET_XTHEADVECTOR, RVVMF2HF, 5, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF4x5HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF4HF, 5, LMUL_F4, 64) TUPLE_ENTRY (RVVM2x4HF, TARGET_VECTOR_ELEN_FP_16, RVVM2HF, 4, LMUL_2, 8) TUPLE_ENTRY (RVVM1x4HF, TARGET_VECTOR_ELEN_FP_16, RVVM1HF, 4, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x4HF, TARGET_VECTOR_ELEN_FP_16, RVVMF2HF, 4, LMUL_F2, 32) -TUPLE_ENTRY (RVVMF4x4HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32, RVVMF4HF, 4, LMUL_F4, 64) +TUPLE_ENTRY (RVVMF2x4HF, TARGET_VECTOR_ELEN_FP_16 && !TARGET_XTHEADVECTOR, RVVMF2HF, 4, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF4x4HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF4HF, 4, LMUL_F4, 64) TUPLE_ENTRY (RVVM2x3HF, TARGET_VECTOR_ELEN_FP_16, RVVM2HF, 3, LMUL_2, 8) TUPLE_ENTRY (RVVM1x3HF, TARGET_VECTOR_ELEN_FP_16, RVVM1HF, 3, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x3HF, TARGET_VECTOR_ELEN_FP_16, RVVMF2HF, 3, LMUL_F2, 32) -TUPLE_ENTRY (RVVMF4x3HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32, RVVMF4HF, 3, LMUL_F4, 64) +TUPLE_ENTRY (RVVMF2x3HF, TARGET_VECTOR_ELEN_FP_16 && !TARGET_XTHEADVECTOR, RVVMF2HF, 3, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF4x3HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF4HF, 3, LMUL_F4, 64) TUPLE_ENTRY (RVVM4x2HF, TARGET_VECTOR_ELEN_FP_16, RVVM4HF, 2, LMUL_4, 4) TUPLE_ENTRY (RVVM2x2HF, TARGET_VECTOR_ELEN_FP_16, RVVM2HF, 2, LMUL_2, 8) TUPLE_ENTRY (RVVM1x2HF, TARGET_VECTOR_ELEN_FP_16, RVVM1HF, 2, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x2HF, TARGET_VECTOR_ELEN_FP_16, RVVMF2HF, 2, LMUL_F2, 32) -TUPLE_ENTRY (RVVMF4x2HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32, RVVMF4HF, 2, LMUL_F4, 64) +TUPLE_ENTRY (RVVMF2x2HF, TARGET_VECTOR_ELEN_FP_16 && !TARGET_XTHEADVECTOR, RVVMF2HF, 2, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF4x2HF, TARGET_VECTOR_ELEN_FP_16 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF4HF, 2, LMUL_F4, 64) TUPLE_ENTRY (RVVM1x8SI, true, RVVM1SI, 8, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x8SI, TARGET_MIN_VLEN > 32, RVVMF2SI, 8, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF2x8SI, (TARGET_MIN_VLEN > 32) && !TARGET_XTHEADVECTOR, RVVMF2SI, 8, LMUL_F2, 32) TUPLE_ENTRY (RVVM1x7SI, true, RVVM1SI, 7, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x7SI, TARGET_MIN_VLEN > 32, RVVMF2SI, 7, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF2x7SI, (TARGET_MIN_VLEN > 32) && !TARGET_XTHEADVECTOR, RVVMF2SI, 7, LMUL_F2, 32) TUPLE_ENTRY (RVVM1x6SI, true, RVVM1SI, 6, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x6SI, TARGET_MIN_VLEN > 32, RVVMF2SI, 6, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF2x6SI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF2SI, 6, LMUL_F2, 32) TUPLE_ENTRY (RVVM1x5SI, true, RVVM1SI, 5, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x5SI, TARGET_MIN_VLEN > 32, RVVMF2SI, 5, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF2x5SI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF2SI, 5, LMUL_F2, 32) TUPLE_ENTRY (RVVM2x4SI, true, RVVM2SI, 4, LMUL_2, 8) TUPLE_ENTRY (RVVM1x4SI, true, RVVM1SI, 4, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x4SI, TARGET_MIN_VLEN > 32, RVVMF2SI, 4, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF2x4SI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF2SI, 4, LMUL_F2, 32) TUPLE_ENTRY (RVVM2x3SI, true, RVVM2SI, 3, LMUL_2, 8) TUPLE_ENTRY (RVVM1x3SI, true, RVVM1SI, 3, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x3SI, TARGET_MIN_VLEN > 32, RVVMF2SI, 3, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF2x3SI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF2SI, 3, LMUL_F2, 32) TUPLE_ENTRY (RVVM4x2SI, true, RVVM4SI, 2, LMUL_4, 4) TUPLE_ENTRY (RVVM2x2SI, true, RVVM2SI, 2, LMUL_2, 8) TUPLE_ENTRY (RVVM1x2SI, true, RVVM1SI, 2, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x2SI, TARGET_MIN_VLEN > 32, RVVMF2SI, 2, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF2x2SI, TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF2SI, 2, LMUL_F2, 32) TUPLE_ENTRY (RVVM1x8SF, TARGET_VECTOR_ELEN_FP_32, RVVM1SF, 8, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x8SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32, RVVMF2SF, 8, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF2x8SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF2SF, 8, LMUL_F2, 32) TUPLE_ENTRY (RVVM1x7SF, TARGET_VECTOR_ELEN_FP_32, RVVM1SF, 7, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x7SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32, RVVMF2SF, 7, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF2x7SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF2SF, 7, LMUL_F2, 32) TUPLE_ENTRY (RVVM1x6SF, TARGET_VECTOR_ELEN_FP_32, RVVM1SF, 6, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x6SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32, RVVMF2SF, 6, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF2x6SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF2SF, 6, LMUL_F2, 32) TUPLE_ENTRY (RVVM1x5SF, TARGET_VECTOR_ELEN_FP_32, RVVM1SF, 5, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x5SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32, RVVMF2SF, 5, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF2x5SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF2SF, 5, LMUL_F2, 32) TUPLE_ENTRY (RVVM2x4SF, TARGET_VECTOR_ELEN_FP_32, RVVM2SF, 4, LMUL_2, 8) TUPLE_ENTRY (RVVM1x4SF, TARGET_VECTOR_ELEN_FP_32, RVVM1SF, 4, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x4SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32, RVVMF2SF, 4, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF2x4SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF2SF, 4, LMUL_F2, 32) TUPLE_ENTRY (RVVM2x3SF, TARGET_VECTOR_ELEN_FP_32, RVVM2SF, 3, LMUL_2, 8) TUPLE_ENTRY (RVVM1x3SF, TARGET_VECTOR_ELEN_FP_32, RVVM1SF, 3, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x3SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32, RVVMF2SF, 3, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF2x3SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF2SF, 3, LMUL_F2, 32) TUPLE_ENTRY (RVVM4x2SF, TARGET_VECTOR_ELEN_FP_32, RVVM4SF, 2, LMUL_4, 4) TUPLE_ENTRY (RVVM2x2SF, TARGET_VECTOR_ELEN_FP_32, RVVM2SF, 2, LMUL_2, 8) TUPLE_ENTRY (RVVM1x2SF, TARGET_VECTOR_ELEN_FP_32, RVVM1SF, 2, LMUL_1, 16) -TUPLE_ENTRY (RVVMF2x2SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32, RVVMF2SF, 2, LMUL_F2, 32) +TUPLE_ENTRY (RVVMF2x2SF, TARGET_VECTOR_ELEN_FP_32 && TARGET_MIN_VLEN > 32 && !TARGET_XTHEADVECTOR, RVVMF2SF, 2, LMUL_F2, 32) TUPLE_ENTRY (RVVM1x8DI, TARGET_VECTOR_ELEN_64, RVVM1DI, 8, LMUL_1, 16) TUPLE_ENTRY (RVVM1x7DI, TARGET_VECTOR_ELEN_64, RVVM1DI, 7, LMUL_1, 16) diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc index 0ce0bab1ca83..f1d5129397fb 100644 --- a/gcc/config/riscv/riscv.cc +++ b/gcc/config/riscv/riscv.cc @@ -1426,6 +1426,9 @@ riscv_v_adjust_bytesize (machine_mode mode, int scale) { if (riscv_v_ext_vector_mode_p (mode)) { + if (TARGET_XTHEADVECTOR) + return BYTES_PER_RISCV_VECTOR; + poly_int64 nunits = GET_MODE_NUNITS (mode); poly_int64 mode_size = GET_MODE_SIZE (mode); @@ -9989,7 +9992,7 @@ riscv_use_divmod_expander (void) static machine_mode riscv_preferred_simd_mode (scalar_mode mode) { - if (TARGET_VECTOR) + if (TARGET_VECTOR && !TARGET_XTHEADVECTOR) return riscv_vector::preferred_simd_mode (mode); return word_mode; @@ -10340,7 +10343,7 @@ riscv_mode_priority (int, int n) unsigned int riscv_autovectorize_vector_modes (vector_modes *modes, bool all) { - if (TARGET_VECTOR) + if (TARGET_VECTOR && !TARGET_XTHEADVECTOR) return riscv_vector::autovectorize_vector_modes (modes, all); return default_autovectorize_vector_modes (modes, all); @@ -10528,6 +10531,16 @@ extract_base_offset_in_addr (rtx mem, rtx *base, rtx *offset) return false; } +/* Implements target hook vector_mode_supported_any_target_p. */ + +static bool +riscv_vector_mode_supported_any_target_p (machine_mode mode) +{ + if (TARGET_XTHEADVECTOR) + return false; + return true; +} + /* Initialize the GCC target structure. */ #undef TARGET_ASM_ALIGNED_HI_OP #define TARGET_ASM_ALIGNED_HI_OP "\t.half\t" @@ -10871,6 +10884,9 @@ extract_base_offset_in_addr (rtx mem, rtx *base, rtx *offset) #undef TARGET_PREFERRED_ELSE_VALUE #define TARGET_PREFERRED_ELSE_VALUE riscv_preferred_else_value +#undef TARGET_VECTOR_MODE_SUPPORTED_ANY_TARGET_P +#define TARGET_VECTOR_MODE_SUPPORTED_ANY_TARGET_P riscv_vector_mode_supported_any_target_p + struct gcc_target targetm = TARGET_INITIALIZER; #include "gt-riscv.h" diff --git a/gcc/config/riscv/riscv_th_vector.h b/gcc/config/riscv/riscv_th_vector.h new file mode 100644 index 000000000000..b6b6738bddaa --- /dev/null +++ b/gcc/config/riscv/riscv_th_vector.h @@ -0,0 +1,49 @@ +/* RISC-V 'XTheadVector' Extension intrinsics include file. + Copyright (C) 2024 Free Software Foundation, Inc. + + This file is part of GCC. + + GCC is free software; you can redistribute it and/or modify it + under the terms of the GNU General Public License as published + by the Free Software Foundation; either version 3, or (at your + option) any later version. + + GCC is distributed in the hope that it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY + or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public + License for more details. + + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see + . */ + +#ifndef __RISCV_TH_VECTOR_H +#define __RISCV_TH_VECTOR_H + +#include +#include + +#ifndef __riscv_xtheadvector +#error "XTheadVector intrinsics require the xtheadvector extension." +#else +#ifdef __cplusplus +extern "C" { +#endif + +/* NOTE: This implementation of riscv_th_vector.h is intentionally short. It does + not define the RVV types and intrinsic functions directly in C and C++ + code, but instead uses the following pragma to tell GCC to insert the + necessary type and function definitions itself. The net effect is the + same, and the file is a complete implementation of riscv_th_vector.h. */ +#pragma riscv intrinsic "xtheadvector" + +#ifdef __cplusplus +} +#endif // __cplusplus +#endif // __riscv_xtheadvector +#endif // __RISCV_TH_ECTOR_H diff --git a/gcc/config/riscv/thead-vector.md b/gcc/config/riscv/thead-vector.md new file mode 100644 index 000000000000..696b815252d4 --- /dev/null +++ b/gcc/config/riscv/thead-vector.md @@ -0,0 +1,102 @@ +(define_c_enum "unspec" [ + UNSPEC_TH_VWLDST +]) + +(define_mode_iterator V_VLS_VT [V VLS VT]) +(define_mode_iterator V_VB_VLS_VT [V VB VLS VT]) + +(define_split + [(set (match_operand:V_VB_VLS_VT 0 "reg_or_mem_operand") + (match_operand:V_VB_VLS_VT 1 "reg_or_mem_operand"))] + "TARGET_XTHEADVECTOR" + [(const_int 0)] + { + emit_insn (gen_pred_th_whole_mov (mode, operands[0], operands[1], + RVV_VLMAX, GEN_INT(riscv_vector::VLMAX))); + DONE; + }) + +(define_insn_and_split "@pred_th_whole_mov" + [(set (match_operand:V_VLS_VT 0 "reg_or_mem_operand" "=vr,vr, m") + (unspec:V_VLS_VT + [(match_operand:V_VLS_VT 1 "reg_or_mem_operand" " vr, m,vr") + (match_operand 2 "vector_length_operand" " rK, rK, rK") + (match_operand 3 "const_1_operand" " i, i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] + UNSPEC_TH_VWLDST))] + "TARGET_XTHEADVECTOR" + "@ + vmv.v.v\t%0,%1 + vle.v\t%0,%1 + vse.v\t%1,%0" + "&& REG_P (operands[0]) && REG_P (operands[1]) + && REGNO (operands[0]) == REGNO (operands[1])" + [(const_int 0)] + "" + [(set_attr "type" "vimov,vlds,vlds") + (set_attr "mode" "") + (set (attr "ta") (symbol_ref "riscv_vector::TAIL_UNDISTURBED")) + (set (attr "ma") (symbol_ref "riscv_vector::MASK_UNDISTURBED")) + (set (attr "avl_type_idx") (const_int 3)) + (set_attr "vl_op_idx" "2")]) + +(define_insn_and_split "@pred_th_whole_mov" + [(set (match_operand:VB 0 "reg_or_mem_operand" "=vr,vr, m") + (unspec:VB + [(match_operand:VB 1 "reg_or_mem_operand" " vr, m,vr") + (match_operand 2 "vector_length_operand" " rK, rK, rK") + (match_operand 3 "const_1_operand" " i, i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] + UNSPEC_TH_VWLDST))] + "TARGET_XTHEADVECTOR" + "@ + vmv.v.v\t%0,%1 + vle.v\t%0,%1 + vse.v\t%1,%0" + "&& REG_P (operands[0]) && REG_P (operands[1]) + && REGNO (operands[0]) == REGNO (operands[1])" + [(const_int 0)] + "" + [(set_attr "type" "vimov,vlds,vlds") + (set_attr "mode" "") + (set (attr "ta") (symbol_ref "riscv_vector::TAIL_UNDISTURBED")) + (set (attr "ma") (symbol_ref "riscv_vector::MASK_UNDISTURBED")) + (set (attr "avl_type_idx") (const_int 3)) + (set_attr "vl_op_idx" "2") + (set (attr "sew") (const_int 8)) + (set (attr "vlmul") (symbol_ref "riscv_vector::LMUL_1"))]) + +(define_insn_and_split "*pred_th_mov" + [(set (match_operand:VB_VLS 0 "nonimmediate_operand" "=vr, m, vr, vr, vr") + (if_then_else:VB_VLS + (unspec:VB_VLS + [(match_operand:VB_VLS 1 "vector_all_trues_mask_operand" "Wc1, Wc1, Wc1, Wc1, Wc1") + (match_operand 4 "vector_length_operand" " rK, rK, rK, rK, rK") + (match_operand 5 "const_int_operand" " i, i, i, i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (match_operand:VB_VLS 3 "vector_move_operand" " m, vr, vr, Wc0, Wc1") + (match_operand:VB_VLS 2 "vector_undef_operand" " vu, vu, vu, vu, vu")))] + "TARGET_XTHEADVECTOR" + "@ + # + # + vmcpy.m\t%0,%3 + vmclr.m\t%0 + vmset.m\t%0" + "&& !reload_completed" + [(const_int 0)] + { + if ((MEM_P (operands[0]) || MEM_P (operands[3])) + || (REG_P (operands[0]) && REG_P (operands[3]) + && INTVAL (operands[5]) == riscv_vector::VLMAX)) + { + emit_move_insn (operands[0], operands[3]); + DONE; + } + FAIL; + } + [(set_attr "type" "vldm,vstm,vmalu,vmalu,vmalu") + (set_attr "mode" "")]) diff --git a/gcc/config/riscv/thead.cc b/gcc/config/riscv/thead.cc index 7b0842af1c7e..85250f771672 100644 --- a/gcc/config/riscv/thead.cc +++ b/gcc/config/riscv/thead.cc @@ -27,6 +27,7 @@ #include "backend.h" #include "tree.h" #include "rtl.h" +#include "insn-attr.h" #include "explow.h" #include "memmodel.h" #include "emit-rtl.h" @@ -890,8 +891,26 @@ th_asm_output_opcode (FILE *asm_out_file, const char *p) { /* We need to add th. prefix to all the xtheadvector instructions here.*/ - if (current_output_insn != NULL && p[0] == 'v') - fputs ("th.", asm_out_file); + if (current_output_insn != NULL) + { + if (get_attr_type (current_output_insn) == TYPE_VSETVL) + { + if (strstr (p, "zero")) + { + if (strstr (p, "zero,zero")) + return "th.vsetvli\tzero,zero,e%0,%m1"; + else + return "th.vsetvli\tzero,%0,e%1,%m2"; + } + else + { + return "th.vsetvli\t%0,%1,e%2,%m3"; + } + } + + if (p[0] == 'v') + fputs ("th.", asm_out_file); + } return p; } diff --git a/gcc/config/riscv/vector.md b/gcc/config/riscv/vector.md index ee4ee059a505..aa2b0cca8123 100644 --- a/gcc/config/riscv/vector.md +++ b/gcc/config/riscv/vector.md @@ -87,7 +87,7 @@ ;; check. However, we need default value of SEW for vsetvl instruction since there ;; is no field for ratio in the vsetvl instruction encoding. (define_attr "sew" "" - (cond [(eq_attr "mode" "RVVMF64BI,RVVMF32BI,RVVMF16BI,RVVMF8BI,RVVMF4BI,RVVMF2BI,RVVM1BI,\ + (cond [(eq_attr "mode" "RVVMF8BI,RVVMF4BI,RVVMF2BI,RVVM1BI,\ RVVM8QI,RVVM4QI,RVVM2QI,RVVM1QI,RVVMF2QI,RVVMF4QI,RVVMF8QI,\ RVVM1x8QI,RVVMF2x8QI,RVVMF4x8QI,RVVMF8x8QI,\ RVVM1x7QI,RVVMF2x7QI,RVVMF4x7QI,RVVMF8x7QI,\ @@ -99,6 +99,18 @@ V1QI,V2QI,V4QI,V8QI,V16QI,V32QI,V64QI,V128QI,V256QI,V512QI,V1024QI,V2048QI,V4096QI,\ V1BI,V2BI,V4BI,V8BI,V16BI,V32BI,V64BI,V128BI,V256BI,V512BI,V1024BI,V2048BI,V4096BI") (const_int 8) + (eq_attr "mode" "RVVMF16BI") + (if_then_else (match_test "TARGET_XTHEADVECTOR") + (const_int 16) + (const_int 8)) + (eq_attr "mode" "RVVMF32BI") + (if_then_else (match_test "TARGET_XTHEADVECTOR") + (const_int 32) + (const_int 8)) + (eq_attr "mode" "RVVMF64BI") + (if_then_else (match_test "TARGET_XTHEADVECTOR") + (const_int 64) + (const_int 8)) (eq_attr "mode" "RVVM8HI,RVVM4HI,RVVM2HI,RVVM1HI,RVVMF2HI,RVVMF4HI,\ RVVM1x8HI,RVVMF2x8HI,RVVMF4x8HI,\ RVVM1x7HI,RVVMF2x7HI,RVVMF4x7HI,\ @@ -159,9 +171,9 @@ (eq_attr "mode" "RVVM4QI,RVVMF2BI") (symbol_ref "riscv_vector::LMUL_4") (eq_attr "mode" "RVVM2QI,RVVMF4BI") (symbol_ref "riscv_vector::LMUL_2") (eq_attr "mode" "RVVM1QI,RVVMF8BI") (symbol_ref "riscv_vector::LMUL_1") - (eq_attr "mode" "RVVMF2QI,RVVMF16BI") (symbol_ref "riscv_vector::LMUL_F2") - (eq_attr "mode" "RVVMF4QI,RVVMF32BI") (symbol_ref "riscv_vector::LMUL_F4") - (eq_attr "mode" "RVVMF8QI,RVVMF64BI") (symbol_ref "riscv_vector::LMUL_F8") + (eq_attr "mode" "RVVMF2QI,RVVMF16BI") (symbol_ref "TARGET_XTHEADVECTOR ? riscv_vector::LMUL_1 : riscv_vector::LMUL_F2") + (eq_attr "mode" "RVVMF4QI,RVVMF32BI") (symbol_ref "TARGET_XTHEADVECTOR ? riscv_vector::LMUL_1 : riscv_vector::LMUL_F4") + (eq_attr "mode" "RVVMF8QI,RVVMF64BI") (symbol_ref "TARGET_XTHEADVECTOR ? riscv_vector::LMUL_1 : riscv_vector::LMUL_F8") (eq_attr "mode" "RVVM8HI") (symbol_ref "riscv_vector::LMUL_8") (eq_attr "mode" "RVVM4HI") (symbol_ref "riscv_vector::LMUL_4") (eq_attr "mode" "RVVM2HI") (symbol_ref "riscv_vector::LMUL_2") @@ -436,6 +448,10 @@ vaeskf1,vaeskf2,vaesz,vsha2ms,vsha2ch,vsha2cl,vsm4k,vsm4r,\ vsm3me,vsm3c") (const_int INVALID_ATTRIBUTE) + (and (eq_attr "type" "vlde,vste,vlsegde,vssegte,vlsegds,vssegts,\ + vlsegdff,vssegtux,vlsegdox,vlsegdux") + (match_test "TARGET_XTHEADVECTOR")) + (const_int INVALID_ATTRIBUTE) (eq_attr "mode" "RVVM8QI,RVVM1BI") (const_int 1) (eq_attr "mode" "RVVM4QI,RVVMF2BI") (const_int 2) (eq_attr "mode" "RVVM2QI,RVVMF4BI") (const_int 4) @@ -905,6 +921,8 @@ (symbol_ref "riscv_vector::FRM_DYN")] (symbol_ref "riscv_vector::FRM_NONE"))) +(include "thead-vector.md") + ;; ----------------------------------------------------------------- ;; ---- Miscellaneous Operations ;; ----------------------------------------------------------------- @@ -1078,6 +1096,12 @@ - We can not leave it to TARGET_SECONDARY_RELOAD since it happens before spilling. The clobber scratch is used by spilling fractional registers in IRA/LRA so it's too early. */ + if (TARGET_XTHEADVECTOR) + { + emit_insn (gen_pred_th_whole_mov (mode, operands[0], operands[1], + RVV_VLMAX, GEN_INT(riscv_vector::VLMAX))); + DONE; + } if (riscv_vector::legitimize_move (operands[0], &operands[1])) DONE; @@ -1114,7 +1138,7 @@ (define_insn "*mov_whole" [(set (match_operand:V_WHOLE 0 "reg_or_mem_operand" "=vr, m,vr") (match_operand:V_WHOLE 1 "reg_or_mem_operand" " m,vr,vr"))] - "TARGET_VECTOR" + "TARGET_VECTOR && !TARGET_XTHEADVECTOR" "@ vl%m1re.v\t%0,%1 vs%m1r.v\t%1,%0 @@ -1135,6 +1159,13 @@ (match_operand:VB 1 "general_operand"))] "TARGET_VECTOR" { + if (TARGET_XTHEADVECTOR) + { + emit_insn (gen_pred_th_whole_mov (mode, operands[0], operands[1], + RVV_VLMAX, GEN_INT(riscv_vector::VLMAX))); + DONE; + } + if (riscv_vector::legitimize_move (operands[0], &operands[1])) DONE; }) @@ -1142,7 +1173,7 @@ (define_insn "*mov" [(set (match_operand:VB 0 "register_operand" "=vr") (match_operand:VB 1 "register_operand" " vr"))] - "TARGET_VECTOR" + "TARGET_VECTOR && !TARGET_XTHEADVECTOR" "vmv1r.v\t%0,%1" [(set_attr "type" "vmov") (set_attr "mode" "")]) diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/abi-1.c b/gcc/testsuite/gcc.target/riscv/rvv/base/abi-1.c index 2e0e12aa0451..2eef9e1e1a8c 100644 --- a/gcc/testsuite/gcc.target/riscv/rvv/base/abi-1.c +++ b/gcc/testsuite/gcc.target/riscv/rvv/base/abi-1.c @@ -1,4 +1,4 @@ -/* { dg-do compile } */ +/* { dg-do compile { target { ! riscv_xtheadvector } } } */ /* { dg-skip-if "test rvv intrinsic" { *-*-* } { "*" } { "-march=rv*v*" } } */ void foo0 () {__rvv_bool64_t t;} diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pragma-1.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pragma-1.c index 3d81b179235e..ef329e30785f 100644 --- a/gcc/testsuite/gcc.target/riscv/rvv/base/pragma-1.c +++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pragma-1.c @@ -1,4 +1,4 @@ /* { dg-do compile } */ /* { dg-options "-O3 -march=rv32gc -mabi=ilp32d" } */ -#pragma riscv intrinsic "vector" /* { dg-error {#pragma riscv intrinsic' option 'vector' needs 'V' extension enabled} } */ +#pragma riscv intrinsic "vector" /* { dg-error {#pragma riscv intrinsic' option 'vector' needs 'V' or 'XTHEADVECTOR' extension enabled} } */ diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp index fac32fb3d0e2..73360cd3a0d5 100644 --- a/gcc/testsuite/lib/target-supports.exp +++ b/gcc/testsuite/lib/target-supports.exp @@ -1956,6 +1956,18 @@ proc check_effective_target_riscv_zbb { } { }] } +# Return 1 if the target arch supports the XTheadVector extension, 0 otherwise. +# Cache the result. + +proc check_effective_target_riscv_xtheadvector { } { + return [check_no_compiler_messages riscv_ext_xtheadvector assembly { + #ifndef __riscv_xtheadvector + #error "Not __riscv_xtheadvector" + #endif + }] +} + + # Return 1 if we can execute code when using dg-add-options riscv_v proc check_effective_target_riscv_v_ok { } {