This patch adds the 'Zfa' extension for riscv, which is based on: https://github.com/riscv/riscv-isa-manual/commits/zfb
The binutils-gdb for 'Zfa' extension: https://sourceware.org/pipermail/binutils/2023-April/127060.html What needs special explanation is: 1, According to riscv-spec, "The FCVTMO D.W.D instruction was added principally to accelerate the processing of JavaScript Numbers.", so it seems that no implementation is required. 2, The instructions FMINM and FMAXM correspond to C23 library function fminimum and fmaximum. Therefore, this patch has simply implemented the pattern of fminm<hf\sf\df>3 and fmaxm<hf\sf\df>3 to prepare for later. gcc/ChangeLog: * common/config/riscv/riscv-common.cc: Add zfa extension version, which depends on the F extension. * config/riscv/constraints.md (zfli): Constrain the floating point number that the instructions FLI.H/S/D can load. * config/riscv/iterators.md (ceil): New. * config/riscv/riscv-opts.h (MASK_ZFA): New. (TARGET_ZFA): New. * config/riscv/riscv-protos.h (riscv_float_const_rtx_index_for_fli): New. * config/riscv/riscv.cc (riscv_float_const_rtx_index_for_fli): New. (riscv_cannot_force_const_mem): If instruction FLI.H/S/D can be used, memory is not applicable. (riscv_const_insns): Likewise. (riscv_legitimize_const_move): Likewise. (riscv_split_64bit_move_p): If instruction FLI.H/S/D can be used, no split is required. (riscv_split_doubleword_move): Likewise. (riscv_output_move): Output the mov instructions in zfa extension. (riscv_print_operand): Output the floating-point value of the FLI.H/S/D immediate in assembly. (riscv_secondary_memory_needed): Likewise. * config/riscv/riscv.md (fminm<mode>3): New. (fmaxm<mode>3): New. (movsidf2_low_rv32): New. (movsidf2_high_rv32): New. (movdfsisi3_rv32): New. (f<quiet_pattern>_quiet<ANYF:mode><X:mode>4_zfa): New. * config/riscv/riscv.opt: New. gcc/testsuite/ChangeLog: * gcc.target/riscv/zfa-fleq-fltq.c: New test. * gcc.target/riscv/zfa-fli-zfh.c: New test. * gcc.target/riscv/zfa-fli.c: New test. * gcc.target/riscv/zfa-fmovh-fmovp.c: New test. * gcc.target/riscv/zfa-fround.c: New test. --- gcc/common/config/riscv/riscv-common.cc | 7 + gcc/config/riscv/constraints.md | 21 +- gcc/config/riscv/iterators.md | 5 + gcc/config/riscv/riscv-opts.h | 3 + gcc/config/riscv/riscv-protos.h | 1 + gcc/config/riscv/riscv.cc | 205 +++++++++++++++++- gcc/config/riscv/riscv.md | 145 +++++++++++-- gcc/config/riscv/riscv.opt | 3 + .../gcc.target/riscv/zfa-fleq-fltq.c | 20 ++ gcc/testsuite/gcc.target/riscv/zfa-fli-zfh.c | 42 ++++ gcc/testsuite/gcc.target/riscv/zfa-fli.c | 80 +++++++ .../gcc.target/riscv/zfa-fmovh-fmovp.c | 10 + gcc/testsuite/gcc.target/riscv/zfa-fround.c | 43 ++++ 13 files changed, 549 insertions(+), 36 deletions(-) create mode 100644 gcc/testsuite/gcc.target/riscv/zfa-fleq-fltq.c create mode 100644 gcc/testsuite/gcc.target/riscv/zfa-fli-zfh.c create mode 100644 gcc/testsuite/gcc.target/riscv/zfa-fli.c create mode 100644 gcc/testsuite/gcc.target/riscv/zfa-fmovh-fmovp.c create mode 100644 gcc/testsuite/gcc.target/riscv/zfa-fround.c diff --git a/gcc/common/config/riscv/riscv-common.cc b/gcc/common/config/riscv/riscv-common.cc index 21f83f26371..c16986e1762 100644 --- a/gcc/common/config/riscv/riscv-common.cc +++ b/gcc/common/config/riscv/riscv-common.cc @@ -123,6 +123,9 @@ static const riscv_implied_info_t riscv_implied_info[] = {"zfh", "zfhmin"}, {"zfhmin", "f"}, + + {"zfa", "f"}, + {"zvfhmin", "zve32f"}, {"zvfh", "zve32f"}, {"zvfh", "zfhmin"}, @@ -262,6 +265,8 @@ static const struct riscv_ext_version riscv_ext_version_table[] = {"zvfhmin", ISA_SPEC_CLASS_NONE, 1, 0}, {"zvfh", ISA_SPEC_CLASS_NONE, 1, 0}, + {"zfa", ISA_SPEC_CLASS_NONE, 0, 1}, + {"zmmul", ISA_SPEC_CLASS_NONE, 1, 0}, {"svinval", ISA_SPEC_CLASS_NONE, 1, 0}, @@ -1405,6 +1410,8 @@ static const riscv_ext_flag_table_t riscv_ext_flag_table[] = {"zvfhmin", &gcc_options::x_riscv_zf_subext, MASK_ZVFHMIN}, {"zvfh", &gcc_options::x_riscv_zf_subext, MASK_ZVFH}, + {"zfa", &gcc_options::x_riscv_zfa_subext, MASK_ZFA}, + {"zmmul", &gcc_options::x_riscv_zm_subext, MASK_ZMMUL}, {"svinval", &gcc_options::x_riscv_sv_subext, MASK_SVINVAL}, diff --git a/gcc/config/riscv/constraints.md b/gcc/config/riscv/constraints.md index 44525b2da49..3f52bc76f67 100644 --- a/gcc/config/riscv/constraints.md +++ b/gcc/config/riscv/constraints.md @@ -118,6 +118,19 @@ (define_constraint "T" (and (match_operand 0 "move_operand") (match_test "CONSTANT_P (op)"))) +;; Zfa constraints. + +(define_constraint "zfli" + "A floating point number that can be loaded using instruction `fli` in zfa." + (and (match_code "const_double") + (match_test "TARGET_ZFA && (riscv_float_const_rtx_index_for_fli (op) != -1)"))) + +(define_register_constraint "zmvf" "(TARGET_ZFA || TARGET_XTHEADFMV) ? FP_REGS : NO_REGS" + "A floating-point register for ZFA or XTheadFmv.") + +(define_register_constraint "zmvr" "(TARGET_ZFA || TARGET_XTHEADFMV) ? GR_REGS : NO_REGS" + "An integer register for ZFA or XTheadFmv.") + ;; Vector constraints. (define_register_constraint "vr" "TARGET_VECTOR ? V_REGS : NO_REGS" @@ -180,11 +193,3 @@ (define_memory_constraint "Wdm" "Vector duplicate memory operand" (and (match_code "mem") (match_code "reg" "0"))) - -;; Vendor ISA extension constraints. - -(define_register_constraint "th_f_fmv" "TARGET_XTHEADFMV ? FP_REGS : NO_REGS" - "A floating-point register for XTheadFmv.") - -(define_register_constraint "th_r_fmv" "TARGET_XTHEADFMV ? GR_REGS : NO_REGS" - "An integer register for XTheadFmv.") diff --git a/gcc/config/riscv/iterators.md b/gcc/config/riscv/iterators.md index d374a10810c..27bfdea1dfb 100644 --- a/gcc/config/riscv/iterators.md +++ b/gcc/config/riscv/iterators.md @@ -300,3 +300,8 @@ (define_int_iterator QUIET_COMPARISON [UNSPEC_FLT_QUIET UNSPEC_FLE_QUIET]) (define_int_attr quiet_pattern [(UNSPEC_FLT_QUIET "lt") (UNSPEC_FLE_QUIET "le")]) (define_int_attr QUIET_PATTERN [(UNSPEC_FLT_QUIET "LT") (UNSPEC_FLE_QUIET "LE")]) +(define_int_iterator ROUND [UNSPEC_ROUND UNSPEC_FLOOR UNSPEC_CEIL UNSPEC_BTRUNC UNSPEC_ROUNDEVEN UNSPEC_NEARBYINT]) +(define_int_attr round_pattern [(UNSPEC_ROUND "round") (UNSPEC_FLOOR "floor") (UNSPEC_CEIL "ceil") + (UNSPEC_BTRUNC "btrunc") (UNSPEC_ROUNDEVEN "roundeven") (UNSPEC_NEARBYINT "nearbyint")]) +(define_int_attr round_rm [(UNSPEC_ROUND "rmm") (UNSPEC_FLOOR "rdn") (UNSPEC_CEIL "rup") + (UNSPEC_BTRUNC "rtz") (UNSPEC_ROUNDEVEN "rne") (UNSPEC_NEARBYINT "dyn")]) diff --git a/gcc/config/riscv/riscv-opts.h b/gcc/config/riscv/riscv-opts.h index aeea805b342..1c02d73f1b2 100644 --- a/gcc/config/riscv/riscv-opts.h +++ b/gcc/config/riscv/riscv-opts.h @@ -245,6 +245,9 @@ enum riscv_entity #define MASK_ZICOND (1 << 2) #define TARGET_ZICOND ((riscv_zi_subext & MASK_ZICOND) != 0) +#define MASK_ZFA (1 << 0) +#define TARGET_ZFA ((riscv_zfa_subext & MASK_ZFA) != 0) + #define MASK_ZFHMIN (1 << 0) #define MASK_ZFH (1 << 1) #define MASK_ZVFHMIN (1 << 2) diff --git a/gcc/config/riscv/riscv-protos.h b/gcc/config/riscv/riscv-protos.h index 2fbed04ff84..34b7ba3c163 100644 --- a/gcc/config/riscv/riscv-protos.h +++ b/gcc/config/riscv/riscv-protos.h @@ -83,6 +83,7 @@ struct riscv_address_info { /* Routines implemented in riscv.cc. */ extern enum riscv_symbol_type riscv_classify_symbolic_expression (rtx); extern bool riscv_symbolic_constant_p (rtx, enum riscv_symbol_type *); +extern int riscv_float_const_rtx_index_for_fli (rtx); extern int riscv_regno_mode_ok_for_base_p (int, machine_mode, bool); extern enum reg_class riscv_index_reg_class (); extern int riscv_regno_ok_for_index_p (int); diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc index f9b7a9ee749..85a014f81ff 100644 --- a/gcc/config/riscv/riscv.cc +++ b/gcc/config/riscv/riscv.cc @@ -804,6 +804,138 @@ static int riscv_symbol_insns (enum riscv_symbol_type type) } } +/* Immediate values loaded by the FLI.S instruction in Chapter 25 of the latest RISC-V ISA + Manual draft. For details, please see: + https://github.com/riscv/riscv-isa-manual/releases/tag/isa-449cd0c */ + +static unsigned HOST_WIDE_INT fli_value_hf[32] = +{ + 0xbcp8, 0x4p8, 0x1p8, 0x2p8, 0x1cp8, 0x20p8, 0x2cp8, 0x30p8, + 0x34p8, 0x35p8, 0x36p8, 0x37p8, 0x38p8, 0x39p8, 0x3ap8, 0x3bp8, + 0x3cp8, 0x3dp8, 0x3ep8, 0x3fp8, 0x40p8, 0x41p8, 0x42p8, 0x44p8, + 0x48p8, 0x4cp8, 0x58p8, 0x5cp8, 0x78p8, + /* Only used for filling, ensuring that 29 and 30 of HF are the same. */ + 0x78p8, + 0x7cp8, 0x7ep8 +}; + +static unsigned HOST_WIDE_INT fli_value_sf[32] = +{ + 0xbf8p20, 0x008p20, 0x378p20, 0x380p20, 0x3b8p20, 0x3c0p20, 0x3d8p20, 0x3e0p20, + 0x3e8p20, 0x3eap20, 0x3ecp20, 0x3eep20, 0x3f0p20, 0x3f2p20, 0x3f4p20, 0x3f6p20, + 0x3f8p20, 0x3fap20, 0x3fcp20, 0x3fep20, 0x400p20, 0x402p20, 0x404p20, 0x408p20, + 0x410p20, 0x418p20, 0x430p20, 0x438p20, 0x470p20, 0x478p20, 0x7f8p20, 0x7fcp20 +}; + +static unsigned HOST_WIDE_INT fli_value_df[32] = +{ + 0xbff0p48, 0x10p48, 0x3ef0p48, 0x3f00p48, + 0x3f70p48, 0x3f80p48, 0x3fb0p48, 0x3fc0p48, + 0x3fd0p48, 0x3fd4p48, 0x3fd8p48, 0x3fdcp48, + 0x3fe0p48, 0x3fe4p48, 0x3fe8p48, 0x3fecp48, + 0x3ff0p48, 0x3ff4p48, 0x3ff8p48, 0x3ffcp48, + 0x4000p48, 0x4004p48, 0x4008p48, 0x4010p48, + 0x4020p48, 0x4030p48, 0x4060p48, 0x4070p48, + 0x40e0p48, 0x40f0p48, 0x7ff0p48, 0x7ff8p48 +}; + +/* Display floating-point values at the assembly level, which is consistent + with the zfa extension of llvm: + https://reviews.llvm.org/D145645. */ + +const char *fli_value_print[32] = +{ + "-1.0", "min", "1.52587890625e-05", "3.0517578125e-05", "0.00390625", "0.0078125", "0.0625", "0.125", + "0.25", "0.3125", "0.375", "0.4375", "0.5", "0.625", "0.75", "0.875", + "1.0", "1.25", "1.5", "1.75", "2.0", "2.5", "3.0", "4.0", + "8.0", "16.0", "128.0", "256.0", "32768.0", "65536.0", "inf", "nan" +}; + +/* Return index of the FLI instruction table if rtx X is an immediate constant that can + be moved using a single FLI instruction in zfa extension. Return -1 if not found. */ + +int +riscv_float_const_rtx_index_for_fli (rtx x) +{ + unsigned HOST_WIDE_INT *fli_value_array; + + machine_mode mode = GET_MODE (x); + + if (!TARGET_ZFA + || !CONST_DOUBLE_P(x) + || mode == VOIDmode + || (mode == HFmode && !TARGET_ZFH) + || (mode == SFmode && !TARGET_HARD_FLOAT) + || (mode == DFmode && !TARGET_DOUBLE_FLOAT)) + return -1; + + if (!SCALAR_FLOAT_MODE_P (mode) + || GET_MODE_BITSIZE (mode).to_constant () > HOST_BITS_PER_WIDE_INT + /* Only support up to DF mode. */ + || GET_MODE_BITSIZE (mode).to_constant () > GET_MODE_BITSIZE (DFmode)) + return -1; + + unsigned HOST_WIDE_INT ival = 0; + + long res[2]; + real_to_target (res, + CONST_DOUBLE_REAL_VALUE (x), + REAL_MODE_FORMAT (mode)); + + if (mode == DFmode) + { + int order = BYTES_BIG_ENDIAN ? 1 : 0; + ival = zext_hwi (res[order], 32); + ival |= (zext_hwi (res[1 - order], 32) << 32); + + /* When the lower 32 bits are not all 0, it is impossible to be in the table. */ + if (ival & (unsigned HOST_WIDE_INT)0xffffffff) + return -1; + } + else + ival = zext_hwi (res[0], 32); + + switch (mode) + { + case E_HFmode: + fli_value_array = fli_value_hf; + break; + case E_SFmode: + fli_value_array = fli_value_sf; + break; + case E_DFmode: + fli_value_array = fli_value_df; + break; + default: + return -1; + } + + if (fli_value_array[0] == ival) + return 0; + + if (fli_value_array[1] == ival) + return 1; + + /* Perform a binary search to find target index. */ + unsigned l, r, m; + + l = 2; + r = 31; + + while (l <= r) + { + m = (l + r) / 2; + if (fli_value_array[m] == ival) + return m; + else if (fli_value_array[m] < ival) + l = m+1; + else + r = m-1; + } + + return -1; +} + /* Implement TARGET_LEGITIMATE_CONSTANT_P. */ static bool @@ -831,6 +963,9 @@ riscv_cannot_force_const_mem (machine_mode mode ATTRIBUTE_UNUSED, rtx x) if (GET_CODE (x) == HIGH) return true; + if (satisfies_constraint_zfli (x)) + return true; + split_const (x, &base, &offset); if (riscv_symbolic_constant_p (base, &type)) { @@ -1322,6 +1457,10 @@ riscv_const_insns (rtx x) } case CONST_DOUBLE: + /* See if we can use FMV directly. */ + if (satisfies_constraint_zfli (x)) + return 1; + /* We can use x0 to load floating-point zero. */ return x == CONST0_RTX (GET_MODE (x)) ? 1 : 0; case CONST_VECTOR: @@ -1944,6 +2083,12 @@ riscv_legitimize_const_move (machine_mode mode, rtx dest, rtx src) return; } + if (satisfies_constraint_zfli (src)) + { + riscv_emit_set (dest, src); + return; + } + /* Split moves of symbolic constants into high/low pairs. */ if (riscv_split_symbol (dest, src, MAX_MACHINE_MODE, &src)) { @@ -2991,6 +3136,10 @@ riscv_split_64bit_move_p (rtx dest, rtx src) if (TARGET_64BIT) return false; + /* There is no need to split if the FLI instruction in the `Zfa` extension can be used. */ + if (satisfies_constraint_zfli (src)) + return false; + /* Allow FPR <-> FPR and FPR <-> MEM moves, and permit the special case of zeroing an FPR with FCVT.D.W. */ if (TARGET_DOUBLE_FLOAT @@ -3010,22 +3159,36 @@ riscv_split_64bit_move_p (rtx dest, rtx src) void riscv_split_doubleword_move (rtx dest, rtx src) { - /* XTheadFmv has instructions for accessing the upper bits of a double. */ - if (!TARGET_64BIT && TARGET_XTHEADFMV) + /* ZFA or XTheadFmv has instructions for accessing the upper bits of a double. */ + if (!TARGET_64BIT && (TARGET_ZFA || TARGET_XTHEADFMV)) { if (FP_REG_RTX_P (dest)) { rtx low_src = riscv_subword (src, false); rtx high_src = riscv_subword (src, true); - emit_insn (gen_th_fmv_hw_w_x (dest, high_src, low_src)); + + if (TARGET_ZFA) + emit_insn (gen_movdfsisi3_rv32 (dest, high_src, low_src)); + else + emit_insn (gen_th_fmv_hw_w_x (dest, high_src, low_src)); return; } if (FP_REG_RTX_P (src)) { rtx low_dest = riscv_subword (dest, false); rtx high_dest = riscv_subword (dest, true); - emit_insn (gen_th_fmv_x_w (low_dest, src)); - emit_insn (gen_th_fmv_x_hw (high_dest, src)); + + if (TARGET_ZFA) + { + emit_insn (gen_movsidf2_low_rv32 (low_dest, src)); + emit_insn (gen_movsidf2_high_rv32 (high_dest, src)); + return; + } + else + { + emit_insn (gen_th_fmv_x_w (low_dest, src)); + emit_insn (gen_th_fmv_x_hw (high_dest, src)); + } return; } } @@ -3189,6 +3352,17 @@ riscv_output_move (rtx dest, rtx src) case 8: return "fld\t%0,%1"; } + + if (src_code == CONST_DOUBLE && satisfies_constraint_zfli (src)) + switch (width) + { + case 2: + return "fli.h\t%0,%1"; + case 4: + return "fli.s\t%0,%1"; + case 8: + return "fli.d\t%0,%1"; + } } if (dest_code == REG && GP_REG_P (REGNO (dest)) && src_code == CONST_POLY_INT) { @@ -5117,6 +5291,24 @@ riscv_print_operand (FILE *file, rtx op, int letter) output_address (mode, XEXP (op, 0)); break; + case CONST_DOUBLE: + { + if (letter == 'z' && op == CONST0_RTX (GET_MODE (op))) + { + fputs (reg_names[GP_REG_FIRST], file); + break; + } + + int fli_index = riscv_float_const_rtx_index_for_fli (op); + if (fli_index == -1 || fli_index > 31) + { + output_operand_lossage ("invalid use of '%%%c'", letter); + break; + } + asm_fprintf (file, "%s", fli_value_print[fli_index]); + break; + } + default: if (letter == 'z' && op == CONST0_RTX (GET_MODE (op))) fputs (reg_names[GP_REG_FIRST], file); @@ -6525,7 +6717,8 @@ riscv_secondary_memory_needed (machine_mode mode, reg_class_t class1, return (!riscv_v_ext_mode_p (mode) && GET_MODE_SIZE (mode).to_constant () > UNITS_PER_WORD && (class1 == FP_REGS) != (class2 == FP_REGS) - && !TARGET_XTHEADFMV); + && !TARGET_XTHEADFMV + && !TARGET_ZFA); } /* Implement TARGET_REGISTER_MOVE_COST. */ diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md index b456fa6abb3..47d14d99903 100644 --- a/gcc/config/riscv/riscv.md +++ b/gcc/config/riscv/riscv.md @@ -55,10 +55,19 @@ (define_c_enum "unspec" [ UNSPEC_FLT_QUIET UNSPEC_FLE_QUIET UNSPEC_COPYSIGN + UNSPEC_RINT + UNSPEC_ROUND + UNSPEC_FLOOR + UNSPEC_CEIL + UNSPEC_BTRUNC + UNSPEC_ROUNDEVEN + UNSPEC_NEARBYINT UNSPEC_LRINT UNSPEC_LROUND UNSPEC_FMIN UNSPEC_FMAX + UNSPEC_FMINM + UNSPEC_FMAXM ;; Stack tie UNSPEC_TIE @@ -1434,6 +1443,26 @@ (define_insn "neg<mode>2" ;; ;; .................... +(define_insn "fminm<mode>3" + [(set (match_operand:ANYF 0 "register_operand" "=f") + (unspec:ANYF [(use (match_operand:ANYF 1 "register_operand" " f")) + (use (match_operand:ANYF 2 "register_operand" " f"))] + UNSPEC_FMINM))] + "TARGET_HARD_FLOAT && TARGET_ZFA" + "fminm.<fmt>\t%0,%1,%2" + [(set_attr "type" "fmove") + (set_attr "mode" "<UNITMODE>")]) + +(define_insn "fmaxm<mode>3" + [(set (match_operand:ANYF 0 "register_operand" "=f") + (unspec:ANYF [(use (match_operand:ANYF 1 "register_operand" " f")) + (use (match_operand:ANYF 2 "register_operand" " f"))] + UNSPEC_FMAXM))] + "TARGET_HARD_FLOAT && TARGET_ZFA" + "fmaxm.<fmt>\t%0,%1,%2" + [(set_attr "type" "fmove") + (set_attr "mode" "<UNITMODE>")]) + (define_insn "fmin<mode>3" [(set (match_operand:ANYF 0 "register_operand" "=f") (unspec:ANYF [(use (match_operand:ANYF 1 "register_operand" " f")) @@ -1744,13 +1773,13 @@ (define_expand "movhf" }) (define_insn "*movhf_hardfloat" - [(set (match_operand:HF 0 "nonimmediate_operand" "=f,f,f,m,m,*f,*r, *r,*r,*m") - (match_operand:HF 1 "move_operand" " f,G,m,f,G,*r,*f,*G*r,*m,*r"))] + [(set (match_operand:HF 0 "nonimmediate_operand" "=f, f,f,f,m,m,*f,*r, *r,*r,*m") + (match_operand:HF 1 "move_operand" " f,zfli,G,m,f,G,*r,*f,*G*r,*m,*r"))] "TARGET_ZFHMIN && (register_operand (operands[0], HFmode) || reg_or_0_operand (operands[1], HFmode))" { return riscv_output_move (operands[0], operands[1]); } - [(set_attr "move_type" "fmove,mtc,fpload,fpstore,store,mtc,mfc,move,load,store") + [(set_attr "move_type" "fmove,fmove,mtc,fpload,fpstore,store,mtc,mfc,move,load,store") (set_attr "mode" "HF")]) (define_insn "*movhf_softfloat" @@ -1816,6 +1845,26 @@ (define_insn "l<rint_pattern><ANYF:mode><GPR:mode>2" [(set_attr "type" "fcvt") (set_attr "mode" "<ANYF:MODE>")]) +(define_insn "<round_pattern><ANYF:mode>2" + [(set (match_operand:ANYF 0 "register_operand" "=f") + (unspec:ANYF + [(match_operand:ANYF 1 "register_operand" " f")] + ROUND))] + "TARGET_HARD_FLOAT && TARGET_ZFA" + "fround.<ANYF:fmt>\t%0,%1,<round_rm>" + [(set_attr "type" "fcvt") + (set_attr "mode" "<ANYF:MODE>")]) + +(define_insn "rint<ANYF:mode>2" + [(set (match_operand:ANYF 0 "register_operand" "=f") + (unspec:ANYF + [(match_operand:ANYF 1 "register_operand" " f")] + UNSPEC_RINT))] + "TARGET_HARD_FLOAT && TARGET_ZFA" + "froundnx.<ANYF:fmt>\t%0,%1" + [(set_attr "type" "fcvt") + (set_attr "mode" "<ANYF:MODE>")]) + ;; ;; .................... ;; @@ -2075,13 +2124,13 @@ (define_expand "movsf" }) (define_insn "*movsf_hardfloat" - [(set (match_operand:SF 0 "nonimmediate_operand" "=f,f,f,m,m,*f,*r, *r,*r,*m") - (match_operand:SF 1 "move_operand" " f,G,m,f,G,*r,*f,*G*r,*m,*r"))] + [(set (match_operand:SF 0 "nonimmediate_operand" "=f, f,f,f,m,m,*f,*r, *r,*r,*m") + (match_operand:SF 1 "move_operand" " f,zfli,G,m,f,G,*r,*f,*G*r,*m,*r"))] "TARGET_HARD_FLOAT && (register_operand (operands[0], SFmode) || reg_or_0_operand (operands[1], SFmode))" { return riscv_output_move (operands[0], operands[1]); } - [(set_attr "move_type" "fmove,mtc,fpload,fpstore,store,mtc,mfc,move,load,store") + [(set_attr "move_type" "fmove,fmove,mtc,fpload,fpstore,store,mtc,mfc,move,load,store") (set_attr "mode" "SF")]) (define_insn "*movsf_softfloat" @@ -2109,23 +2158,23 @@ (define_expand "movdf" ;; In RV32, we lack fmv.x.d and fmv.d.x. Go through memory instead. ;; (However, we can still use fcvt.d.w to zero a floating-point register.) (define_insn "*movdf_hardfloat_rv32" - [(set (match_operand:DF 0 "nonimmediate_operand" "=f,f,f,m,m,*th_f_fmv,*th_r_fmv, *r,*r,*m") - (match_operand:DF 1 "move_operand" " f,G,m,f,G,*th_r_fmv,*th_f_fmv,*r*G,*m,*r"))] + [(set (match_operand:DF 0 "nonimmediate_operand" "=f, f,f,f,m,m,*zmvf,*zmvr, *r,*r,*m") + (match_operand:DF 1 "move_operand" " f,zfli,G,m,f,G,*zmvr,*zmvf,*r*G,*m,*r"))] "!TARGET_64BIT && TARGET_DOUBLE_FLOAT && (register_operand (operands[0], DFmode) || reg_or_0_operand (operands[1], DFmode))" { return riscv_output_move (operands[0], operands[1]); } - [(set_attr "move_type" "fmove,mtc,fpload,fpstore,store,mtc,mfc,move,load,store") + [(set_attr "move_type" "fmove,fmove,mtc,fpload,fpstore,store,mtc,mfc,move,load,store") (set_attr "mode" "DF")]) (define_insn "*movdf_hardfloat_rv64" - [(set (match_operand:DF 0 "nonimmediate_operand" "=f,f,f,m,m,*f,*r, *r,*r,*m") - (match_operand:DF 1 "move_operand" " f,G,m,f,G,*r,*f,*r*G,*m,*r"))] + [(set (match_operand:DF 0 "nonimmediate_operand" "=f, f,f,f,m,m,*f,*r, *r,*r,*m") + (match_operand:DF 1 "move_operand" " f,zfli,G,m,f,G,*r,*f,*r*G,*m,*r"))] "TARGET_64BIT && TARGET_DOUBLE_FLOAT && (register_operand (operands[0], DFmode) || reg_or_0_operand (operands[1], DFmode))" { return riscv_output_move (operands[0], operands[1]); } - [(set_attr "move_type" "fmove,mtc,fpload,fpstore,store,mtc,mfc,move,load,store") + [(set_attr "move_type" "fmove,fmove,mtc,fpload,fpstore,store,mtc,mfc,move,load,store") (set_attr "mode" "DF")]) (define_insn "*movdf_softfloat" @@ -2138,6 +2187,39 @@ (define_insn "*movdf_softfloat" [(set_attr "move_type" "move,load,store") (set_attr "mode" "DF")]) +(define_insn "movsidf2_low_rv32" + [(set (match_operand:SI 0 "register_operand" "= r") + (truncate:SI + (match_operand:DF 1 "register_operand" "zmvf")))] + "TARGET_HARD_FLOAT && !TARGET_64BIT && TARGET_ZFA" + "fmv.x.w\t%0,%1" + [(set_attr "move_type" "fmove") + (set_attr "mode" "DF")]) + + +(define_insn "movsidf2_high_rv32" + [(set (match_operand:SI 0 "register_operand" "= r") + (truncate:SI + (lshiftrt:DF + (match_operand:DF 1 "register_operand" "zmvf") + (const_int 32))))] + "TARGET_HARD_FLOAT && !TARGET_64BIT && TARGET_ZFA" + "fmvh.x.d\t%0,%1" + [(set_attr "move_type" "fmove") + (set_attr "mode" "DF")]) + +(define_insn "movdfsisi3_rv32" + [(set (match_operand:DF 0 "register_operand" "= f") + (plus:DF + (match_operand:SI 2 "register_operand" "zmvr") + (ashift:SI + (match_operand:SI 1 "register_operand" "zmvr") + (const_int 32))))] + "TARGET_HARD_FLOAT && !TARGET_64BIT && TARGET_ZFA" + "fmvp.d.x\t%0,%2,%1" + [(set_attr "move_type" "fmove") + (set_attr "mode" "DF")]) + (define_split [(set (match_operand:MOVE64 0 "nonimmediate_operand") (match_operand:MOVE64 1 "move_operand"))] @@ -2663,16 +2745,23 @@ (define_expand "f<quiet_pattern>_quiet<ANYF:mode><X:mode>4" rtx op0 = operands[0]; rtx op1 = operands[1]; rtx op2 = operands[2]; - rtx tmp = gen_reg_rtx (SImode); - rtx cmp = gen_rtx_<QUIET_PATTERN> (<X:MODE>mode, op1, op2); - rtx frflags = gen_rtx_UNSPEC_VOLATILE (SImode, gen_rtvec (1, const0_rtx), - UNSPECV_FRFLAGS); - rtx fsflags = gen_rtx_UNSPEC_VOLATILE (SImode, gen_rtvec (1, tmp), - UNSPECV_FSFLAGS); - - emit_insn (gen_rtx_SET (tmp, frflags)); - emit_insn (gen_rtx_SET (op0, cmp)); - emit_insn (fsflags); + + if (TARGET_ZFA) + emit_insn (gen_f<quiet_pattern>_quiet<ANYF:mode><X:mode>4_zfa(op0, op1, op2)); + else + { + rtx tmp = gen_reg_rtx (SImode); + rtx cmp = gen_rtx_<QUIET_PATTERN> (<X:MODE>mode, op1, op2); + rtx frflags = gen_rtx_UNSPEC_VOLATILE (SImode, gen_rtvec (1, const0_rtx), + UNSPECV_FRFLAGS); + rtx fsflags = gen_rtx_UNSPEC_VOLATILE (SImode, gen_rtvec (1, tmp), + UNSPECV_FSFLAGS); + + emit_insn (gen_rtx_SET (tmp, frflags)); + emit_insn (gen_rtx_SET (op0, cmp)); + emit_insn (fsflags); + } + if (HONOR_SNANS (<ANYF:MODE>mode)) emit_insn (gen_rtx_UNSPEC_VOLATILE (<ANYF:MODE>mode, gen_rtvec (2, op1, op2), @@ -2680,6 +2769,18 @@ (define_expand "f<quiet_pattern>_quiet<ANYF:mode><X:mode>4" DONE; }) +(define_insn "f<quiet_pattern>_quiet<ANYF:mode><X:mode>4_zfa" + [(set (match_operand:X 0 "register_operand" "=r") + (unspec:X + [(match_operand:ANYF 1 "register_operand" " f") + (match_operand:ANYF 2 "register_operand" " f")] + QUIET_COMPARISON))] + "TARGET_HARD_FLOAT && TARGET_ZFA" + "f<quiet_pattern>q.<fmt>\t%0,%1,%2" + [(set_attr "type" "fcmp") + (set_attr "mode" "<UNITMODE>") + (set (attr "length") (const_int 16))]) + (define_insn "*seq_zero_<X:mode><GPR:mode>" [(set (match_operand:GPR 0 "register_operand" "=r") (eq:GPR (match_operand:X 1 "register_operand" " r") diff --git a/gcc/config/riscv/riscv.opt b/gcc/config/riscv/riscv.opt index 717b51b5305..9d564d58619 100644 --- a/gcc/config/riscv/riscv.opt +++ b/gcc/config/riscv/riscv.opt @@ -239,6 +239,9 @@ int riscv_zicmo_subext TargetVariable int riscv_zf_subext +TargetVariable +int riscv_zfa_subext + TargetVariable int riscv_zm_subext diff --git a/gcc/testsuite/gcc.target/riscv/zfa-fleq-fltq.c b/gcc/testsuite/gcc.target/riscv/zfa-fleq-fltq.c new file mode 100644 index 00000000000..7c28b0bcccc --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zfa-fleq-fltq.c @@ -0,0 +1,20 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32imafdc_zfa -mabi=ilp32d" { target { rv32 } } } */ +/* { dg-options "-march=rv64imafdc_zfa -mabi=lp64d" { target { rv64 } } } */ + +extern void abort(void); +extern float a, b; +extern double c, d; + +void +foo() +{ + if ((__builtin_isless(a, b) || __builtin_islessequal(c, d)) + && (__builtin_islessequal(a, b)|| __builtin_isless(c, d))) + abort(); +} + +/* { dg-final { scan-assembler-times "fleq.s" 1 } } */ +/* { dg-final { scan-assembler-times "fltq.s" 1 } } */ +/* { dg-final { scan-assembler-times "fleq.d" 1 } } */ +/* { dg-final { scan-assembler-times "fltq.d" 1 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zfa-fli-zfh.c b/gcc/testsuite/gcc.target/riscv/zfa-fli-zfh.c new file mode 100644 index 00000000000..05e2dcbe45e --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zfa-fli-zfh.c @@ -0,0 +1,42 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32imafdc_zfa_zfh -mabi=ilp32d -O0" { target { rv32 } } } */ +/* { dg-options "-march=rv64imafdc_zfa_zfh -mabi=lp64d -O0" { target { rv64 } } } */ + +void foo_float16 () +{ + volatile _Float16 a; + a = -1.0; + a = 6.104e-5; + a = 1.0/(1 << 16); + a = 1.0/(1 << 15); + a = 1.0/(1 << 8); + a = 1.0/(1 << 7); + a = 1.0/(1 << 4); + a = 1.0/(1 << 3); + a = 1.0/(1 << 2); + a = 0.3125; + a = 0.375; + a = 0.4375; + a = 0.5; + a = 0.625; + a = 0.75; + a = 0.875; + a = 1.0; + a = 1.25; + a = 1.5; + a = 1.75; + a = 2.0; + a = 2.5; + a = 3.0; + a = 1.0*(1 << 2); + a = 1.0*(1 << 3); + a = 1.0*(1 << 4); + a = 1.0*(1 << 7); + a = 1.0*(1 << 8); + a = 1.0*(1 << 15); + a = 1.0*(1 << 16); + a = __builtin_inff16 (); + a = __builtin_nanf16 (""); +} + +/* { dg-final { scan-assembler-times "fli.h" 32 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zfa-fli.c b/gcc/testsuite/gcc.target/riscv/zfa-fli.c new file mode 100644 index 00000000000..e5c1e591c8c --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zfa-fli.c @@ -0,0 +1,80 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32imafdc_zfa -mabi=ilp32d" { target { rv32 } } } */ +/* { dg-options "-march=rv64imafdc_zfa -mabi=lp64d" { target { rv64 } } } */ + +void foo_float32 () +{ + volatile float a; + a = -1.0; + a = 1.1754944e-38; + a = 1.0/(1 << 16); + a = 1.0/(1 << 15); + a = 1.0/(1 << 8); + a = 1.0/(1 << 7); + a = 1.0/(1 << 4); + a = 1.0/(1 << 3); + a = 1.0/(1 << 2); + a = 0.3125; + a = 0.375; + a = 0.4375; + a = 0.5; + a = 0.625; + a = 0.75; + a = 0.875; + a = 1.0; + a = 1.25; + a = 1.5; + a = 1.75; + a = 2.0; + a = 2.5; + a = 3.0; + a = 1.0*(1 << 2); + a = 1.0*(1 << 3); + a = 1.0*(1 << 4); + a = 1.0*(1 << 7); + a = 1.0*(1 << 8); + a = 1.0*(1 << 15); + a = 1.0*(1 << 16); + a = __builtin_inff (); + a = __builtin_nanf (""); +} + +void foo_double64 () +{ + volatile double a; + a = -1.0; + a = 2.2250738585072014e-308; + a = 1.0/(1 << 16); + a = 1.0/(1 << 15); + a = 1.0/(1 << 8); + a = 1.0/(1 << 7); + a = 1.0/(1 << 4); + a = 1.0/(1 << 3); + a = 1.0/(1 << 2); + a = 0.3125; + a = 0.375; + a = 0.4375; + a = 0.5; + a = 0.625; + a = 0.75; + a = 0.875; + a = 1.0; + a = 1.25; + a = 1.5; + a = 1.75; + a = 2.0; + a = 2.5; + a = 3.0; + a = 1.0*(1 << 2); + a = 1.0*(1 << 3); + a = 1.0*(1 << 4); + a = 1.0*(1 << 7); + a = 1.0*(1 << 8); + a = 1.0*(1 << 15); + a = 1.0*(1 << 16); + a = __builtin_inf (); + a = __builtin_nan (""); +} + +/* { dg-final { scan-assembler-times "fli.s" 32 } } */ +/* { dg-final { scan-assembler-times "fli.d" 32 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zfa-fmovh-fmovp.c b/gcc/testsuite/gcc.target/riscv/zfa-fmovh-fmovp.c new file mode 100644 index 00000000000..5a52adce36a --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zfa-fmovh-fmovp.c @@ -0,0 +1,10 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32g_zfa -mabi=ilp32 -O0" } */ + +double foo(long long a) +{ + return (double)(a + 3); +} + +/* { dg-final { scan-assembler-times "fmvp.d.x" 1 } } */ +/* { dg-final { scan-assembler-times "fmvh.x.d" 1 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zfa-fround.c b/gcc/testsuite/gcc.target/riscv/zfa-fround.c new file mode 100644 index 00000000000..0765334b7ff --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zfa-fround.c @@ -0,0 +1,43 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32imafdc_zfa -mabi=ilp32d" { target { rv32 } } } */ +/* { dg-options "-march=rv64imafdc_zfa -mabi=lp64d" { target { rv64 } } } */ + +extern float a; +extern double b; + +void foo (float *x, double *y) +{ + { + *x = __builtin_roundf (a); + *y = __builtin_round (b); + } + { + *x = __builtin_floorf (a); + *y = __builtin_floor (b); + } + { + *x = __builtin_ceilf (a); + *y = __builtin_ceil (b); + } + { + *x = __builtin_truncf (a); + *y = __builtin_trunc (b); + } + { + *x = __builtin_roundevenf (a); + *y = __builtin_roundeven (b); + } + { + *x = __builtin_nearbyintf (a); + *y = __builtin_nearbyint (b); + } + { + *x = __builtin_rintf (a); + *y = __builtin_rint (b); + } +} + +/* { dg-final { scan-assembler-times "fround.s" 6 } } */ +/* { dg-final { scan-assembler-times "fround.d" 6 } } */ +/* { dg-final { scan-assembler-times "froundnx.s" 1 } } */ +/* { dg-final { scan-assembler-times "froundnx.d" 1 } } */ -- 2.17.1
