Upstream ARC-V RMX-100

gcc/config/riscv/arcv-rmx100.md

@@ -0,0 +1,103 @@
+;; DFA scheduling description of the Synopsys RMX-100 cpu
+;; for GNU C compiler
+;; Copyright (C) 2023 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.
+
+;; You should have received a copy of the GNU General Public License
+;; along with GCC; see the file COPYING3.  If not see
+;; <http://www.gnu.org/licenses/>.
+
+(define_automaton "arcv_rmx100")
+
+(define_cpu_unit "arcv_rmx100_ALU"    "arcv_rmx100")
+;(define_cpu_unit "arcv_rmx100_CSR"    "arcv_rmx100")
+(define_cpu_unit "arcv_rmx100_FPU"    "arcv_rmx100")
+(define_cpu_unit "arcv_rmx100_MPY"    "arcv_rmx100")
+(define_cpu_unit "arcv_rmx100_DIV"    "arcv_rmx100")
+(define_cpu_unit "arcv_rmx100_DMP"    "arcv_rmx100")
+
+;; Instruction reservation for arithmetic instructions.
+(define_insn_reservation "arcv_rmx100_alu_arith" 1
+  (and (eq_attr "tune" "arcv_rmx100")
+       (eq_attr "type" "unknown, const, arith, shift, slt, multi, auipc, nop,
+			logical, move, atomic, mvpair, bitmanip, clz, ctz, cpop,
+			zicond, condmove, clmul, min, max, minu, maxu, rotate"))
+  "arcv_rmx100_ALU")
+
+(define_insn_reservation "arcv_rmx100_jmp_insn" 1
+  (and (eq_attr "tune" "arcv_rmx100")
+       (eq_attr "type" "branch, jump, call, jalr, ret, trap"))
+  "arcv_rmx100_ALU")
+
+; DIV insn: latency may be overridden by a define_bypass
+(define_insn_reservation "arcv_rmx100_div_insn" 35
+  (and (eq_attr "tune" "arcv_rmx100")
+       (eq_attr "type" "idiv"))
+  "arcv_rmx100_DIV*35")
+
+; MPY insn: latency may be overridden by a define_bypass
+(define_insn_reservation "arcv_rmx100_mpy32_insn" 9
+  (and (eq_attr "tune" "arcv_rmx100")
+       (eq_attr "type" "imul"))
+  "arcv_rmx100_MPY")
+
+(define_insn_reservation "arcv_rmx100_load_insn" 3
+  (and (eq_attr "tune" "arcv_rmx100")
+       (eq_attr "type" "load"))
+  "arcv_rmx100_DMP,nothing*2")
+
+(define_insn_reservation "arcv_rmx100_store_insn" 1
+  (and (eq_attr "tune" "arcv_rmx100")
+       (eq_attr "type" "store,fpstore"))
+  "arcv_rmx100_DMP")
+
+;; FPU scheduling. FIXME: This is based on the "fast" unit for now, the "slow"
+;; option remains to be implemented later (together with the -mfpu flag).
+
+(define_insn_reservation "arcv_rmx100_fpload_insn" 3
+  (and (eq_attr "tune" "arcv_rmx100")
+       (eq_attr "type" "fpload"))
+  "arcv_rmx100_DMP,nothing*2")
+
+(define_insn_reservation "arcv_rmx100_farith_insn" 2
+  (and (eq_attr "tune" "arcv_rmx100")
+       (eq_attr "type" "fadd,fcmp"))
+  "arcv_rmx100_FPU,nothing")
+
+(define_insn_reservation "arcv_rmx100_xfer" 1
+  (and (eq_attr "tune" "arcv_rmx100")
+       (eq_attr "type" "fmove,mtc,mfc,fcvt,fcvt_f2i,fcvt_i2f"))
+   "arcv_rmx100_FPU")
+
+(define_insn_reservation "arcv_rmx100_fmul_insn" 2
+  (and (eq_attr "tune" "arcv_rmx100")
+       (eq_attr "type" "fmul"))
+  "arcv_rmx100_FPU,nothing")
+
+(define_insn_reservation "arcv_rmx100_fmac_insn" 2
+  (and (eq_attr "tune" "arcv_rmx100")
+       (eq_attr "type" "fmadd"))
+  "arcv_rmx100_FPU,nothing")
+
+(define_insn_reservation "arcv_rmx100_fdiv_insn" 10
+  (and (eq_attr "tune" "arcv_rmx100")
+       (eq_attr "type" "fdiv,fsqrt"))
+  "arcv_rmx100_FPU")
+
+
+(define_bypass 1 "arcv_rmx100_mpy32_insn" "arcv_rmx100_*" "arcv_mpy_1c_bypass_p")
+(define_bypass 2 "arcv_rmx100_mpy32_insn" "arcv_rmx100_*" "arcv_mpy_2c_bypass_p")
+
+(define_bypass 9 "arcv_rmx100_div_insn" "arcv_rmx100_*" "arcv_mpy_1c_bypass_p")
+(define_bypass 9 "arcv_rmx100_div_insn" "arcv_rmx100_*" "arcv_mpy_2c_bypass_p")

gcc/config/riscv/riscv-cores.def

@@ -50,6 +50,7 @@ RISCV_TUNE("xt-c920", generic, generic_ooo_tune_info)
 RISCV_TUNE("xt-c920v2", generic, generic_ooo_tune_info)
 RISCV_TUNE("xiangshan-nanhu", xiangshan, xiangshan_nanhu_tune_info)
 RISCV_TUNE("xiangshan-kunminghu", xiangshan, generic_ooo_tune_info)
+RISCV_TUNE("arc-v-rmx-100-series", arcv_rmx100, arcv_rmx100_tune_info)
 RISCV_TUNE("generic-ooo", generic_ooo, generic_ooo_tune_info)
 RISCV_TUNE("size", generic, optimize_size_tune_info)
 RISCV_TUNE("mips-p8700", mips_p8700, mips_p8700_tune_info)

gcc/config/riscv/riscv-opts.h

@@ -61,6 +61,7 @@ enum riscv_microarchitecture_type {
   generic_ooo,
   mips_p8700,
   tt_ascalon_d8,
+  arcv_rmx100,
 };
 extern enum riscv_microarchitecture_type riscv_microarchitecture;
 
@@ -85,6 +86,13 @@ enum rvv_max_lmul_enum {
   RVV_DYNAMIC = 9
 };
 
+/* ARC-V multiply option.  */
+enum arcv_mpy_option_enum {
+  ARCV_MPY_OPTION_1C = 1,
+  ARCV_MPY_OPTION_2C = 2,
+  ARCV_MPY_OPTION_10C = 8,
+};
+
 enum riscv_multilib_select_kind {
   /* Select multilib by builtin way.  */
   select_by_builtin,

gcc/config/riscv/riscv-protos.h

@@ -165,6 +165,9 @@ extern bool riscv_epilogue_uses (unsigned int);
 extern bool riscv_can_use_return_insn (void);
 extern rtx riscv_function_value (const_tree, const_tree, enum machine_mode);
 extern bool riscv_store_data_bypass_p (rtx_insn *, rtx_insn *);
+extern bool arcv_mpy_1c_bypass_p (rtx_insn *, rtx_insn *);
+extern bool arcv_mpy_2c_bypass_p (rtx_insn *, rtx_insn *);
+extern bool arcv_mpy_10c_bypass_p (rtx_insn *, rtx_insn *);
 extern rtx riscv_gen_gpr_save_insn (struct riscv_frame_info *);
 extern bool riscv_gpr_save_operation_p (rtx);
 extern void riscv_reinit (void);

gcc/config/riscv/riscv.cc

@@ -685,6 +685,30 @@ static const struct riscv_tune_param tt_ascalon_d8_tune_info = {
   true,						/* prefer-agnostic.  */
 };
 
+/* Costs to use when optimizing for Synopsys RMX-100.  */
+static const struct riscv_tune_param arcv_rmx100_tune_info = {
+  {COSTS_N_INSNS (2), COSTS_N_INSNS (2)},	/* fp_add */
+  {COSTS_N_INSNS (2), COSTS_N_INSNS (2)},	/* fp_mul */
+  {COSTS_N_INSNS (17), COSTS_N_INSNS (17)},	/* fp_div */
+  {COSTS_N_INSNS (2), COSTS_N_INSNS (2)},	/* int_mul */
+  {COSTS_N_INSNS (17), COSTS_N_INSNS (17)},	/* int_div */
+  1,						/* issue_rate */
+  4,						/* branch_cost */
+  2,						/* memory_cost */
+  4,						/* fmv_cost */
+  false,					/* slow_unaligned_access */
+  false,					/* vector_unaligned_access */
+  false,					/* use_divmod_expansion */
+  false,					/* overlap_op_by_pieces */
+  true,						/* use_zero_stride_load */
+  false,					/* speculative_sched_vsetvl */
+  RISCV_FUSE_NOTHING,				/* fusible_ops */
+  NULL,						/* vector cost */
+  NULL,						/* function_align */
+  NULL,						/* jump_align */
+  NULL,						/* loop_align */
+};
+
 /* Costs to use when optimizing for size.  */
 static const struct riscv_tune_param optimize_size_tune_info = {
   {COSTS_N_INSNS (1), COSTS_N_INSNS (1)},	/* fp_add */
@@ -10466,6 +10490,30 @@ riscv_store_data_bypass_p (rtx_insn *out_insn, rtx_insn *in_insn)
   return store_data_bypass_p (out_insn, in_insn);
 }
 
+/* Implement one boolean function for each of the values of the
+   arcv_mpy_option enum, for the needs of rhx100.md.  */
+
+bool
+arcv_mpy_1c_bypass_p (rtx_insn *out_insn ATTRIBUTE_UNUSED,
+		       rtx_insn *in_insn ATTRIBUTE_UNUSED)
+{
+  return arcv_mpy_option == ARCV_MPY_OPTION_1C;
+}
+
+bool
+arcv_mpy_2c_bypass_p (rtx_insn *out_insn ATTRIBUTE_UNUSED,
+		       rtx_insn *in_insn ATTRIBUTE_UNUSED)
+{
+  return arcv_mpy_option == ARCV_MPY_OPTION_2C;
+}
+
+bool
+arcv_mpy_10c_bypass_p (rtx_insn *out_insn ATTRIBUTE_UNUSED,
+			rtx_insn *in_insn ATTRIBUTE_UNUSED)
+{
+  return arcv_mpy_option == ARCV_MPY_OPTION_10C;
+}
+
 /* Implement TARGET_SECONDARY_MEMORY_NEEDED.
 
    When floating-point registers are wider than integer ones, moves between

gcc/config/riscv/riscv.md

@@ -672,7 +672,7 @@
 ;; Microarchitectures we know how to tune for.
 ;; Keep this in sync with enum riscv_microarchitecture.
 (define_attr "tune"
-  "generic,sifive_7,sifive_p400,sifive_p600,xiangshan,generic_ooo,mips_p8700,tt_ascalon_d8"
+  "generic,sifive_7,sifive_p400,sifive_p600,xiangshan,generic_ooo,mips_p8700,tt_ascalon_d8,arcv_rmx100"
   (const (symbol_ref "((enum attr_tune) riscv_microarchitecture)")))
 
 ;; Describe a user's asm statement.
@@ -4966,3 +4966,4 @@
 (include "generic-vector-ooo.md")
 (include "generic-ooo.md")
 (include "tt-ascalon-d8.md")
+(include "arcv-rmx100.md")

gcc/config/riscv/riscv.opt

@@ -396,3 +396,20 @@ Specifies whether the fence.tso instruction should be used.
 mautovec-segment
 Target Integer Var(riscv_mautovec_segment) Init(1)
 Enable (default) or disable generation of vector segment load/store instructions.
+
+Enum
+Name(arcv_mpy_option) Type(enum arcv_mpy_option_enum)
+Valid arguments to -param=arcv_mpy_option=:
+
+EnumValue
+Enum(arcv_mpy_option) String(1c) Value(ARCV_MPY_OPTION_1C)
+
+EnumValue
+Enum(arcv_mpy_option) String(2c) Value(ARCV_MPY_OPTION_2C)
+
+EnumValue
+Enum(arcv_mpy_option) String(10c) Value(ARCV_MPY_OPTION_10C)
+
+-param=arcv-mpy-option=
+Target RejectNegative Joined Enum(arcv_mpy_option) Var(arcv_mpy_option) Init(ARCV_MPY_OPTION_2C)
+The type of MPY unit used by the RMX-100 core (to be used in combination with -mtune=rmx100) (default: 2c).

gcc/doc/riscv-mtune.texi

@@ -50,6 +50,8 @@ particular CPU name.  Permissible values for this option are:
 
 @samp{xiangshan-kunminghu},
 
+@samp{arc-v-rmx-100-series},
+
 @samp{generic-ooo},
 
 @samp{size},