From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 1923) id D8BA9384F6DF; Thu, 17 Nov 2022 22:26:29 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org D8BA9384F6DF DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1668723989; bh=5/5t8pvmhZcYJ43h0BffDuzRr8E4kWmLsgxJVtYUIMg=; h=From:To:Subject:Date:From; b=dRWkKxeeXEg0IK6GA7sjqweTUT2upp9HFLE40Cdc3R0xzAqso2amG5OAXywVgHM99 6iUSZp1AmrVJymBwg0adPUNG9azapm4oWlewy9T5hfu7r/flLwVQhgCsYDyX/hGHI7 Nh6JXgsFH9AmZf6zlqgRcvPRNUfNAfdrMwkijlKM= Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: Philipp Tomsich To: gcc-cvs@gcc.gnu.org Subject: [gcc(refs/vendors/vrull/heads/for-upstream)] RISC-V: Add instruction fusion (for ventana-vt1) X-Act-Checkin: gcc X-Git-Author: Philipp Tomsich X-Git-Refname: refs/vendors/vrull/heads/for-upstream X-Git-Oldrev: 84b7d1c6bf7e70f921ab10cd7c4e23b62aab0fe7 X-Git-Newrev: 1908015344c1c5cca5b05b81f78eb5fd5043a7be Message-Id: <20221117222629.D8BA9384F6DF@sourceware.org> Date: Thu, 17 Nov 2022 22:26:29 +0000 (GMT) List-Id: https://gcc.gnu.org/g:1908015344c1c5cca5b05b81f78eb5fd5043a7be commit 1908015344c1c5cca5b05b81f78eb5fd5043a7be Author: Philipp Tomsich Date: Sun Nov 14 22:56:19 2021 +0100 RISC-V: Add instruction fusion (for ventana-vt1) The Ventana VT1 core supports quad-issue and instruction fusion. This implemented TARGET_SCHED_MACRO_FUSION_P to keep fusible sequences together and adds idiom matcheing for the supported fusion cases. gcc/ChangeLog: * config/riscv/riscv.cc (enum riscv_fusion_pairs): Add symbolic constants to identify supported fusion patterns. (struct riscv_tune_param): Add fusible_op field. (riscv_macro_fusion_p): Implement. (riscv_fusion_enabled_p): Implement. (riscv_macro_fusion_pair_p): Implement and recognize fusible idioms for Ventana VT1. (TARGET_SCHED_MACRO_FUSION_P): Point to riscv_macro_fusion_p. (TARGET_SCHED_MACRO_FUSION_PAIR_P): Point to riscv_macro_fusion_pair_p. Diff: --- gcc/config/riscv/riscv.cc | 220 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 220 insertions(+) diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc index 5e6fb27e383..e4fb53c46f1 100644 --- a/gcc/config/riscv/riscv.cc +++ b/gcc/config/riscv/riscv.cc @@ -222,6 +222,19 @@ struct riscv_integer_op { The worst case is LUI, ADDI, SLLI, ADDI, SLLI, ADDI, SLLI, ADDI. */ #define RISCV_MAX_INTEGER_OPS 8 +enum riscv_fusion_pairs +{ + RISCV_FUSE_NOTHING = 0, + RISCV_FUSE_ZEXTW = (1 << 0), + RISCV_FUSE_ZEXTH = (1 << 1), + RISCV_FUSE_ZEXTWS = (1 << 2), + RISCV_FUSE_LDINDEXED = (1 << 3), + RISCV_FUSE_LUI_ADDI = (1 << 4), + RISCV_FUSE_AUIPC_ADDI = (1 << 5), + RISCV_FUSE_LUI_LD = (1 << 6), + RISCV_FUSE_AUIPC_LD = (1 << 7), +}; + /* Costs of various operations on the different architectures. */ struct riscv_tune_param @@ -236,6 +249,7 @@ struct riscv_tune_param unsigned short memory_cost; unsigned short fmv_cost; bool slow_unaligned_access; + unsigned int fusible_ops; }; /* Information about one micro-arch we know about. */ @@ -323,6 +337,7 @@ static const struct riscv_tune_param rocket_tune_info = { 5, /* memory_cost */ 8, /* fmv_cost */ true, /* slow_unaligned_access */ + RISCV_FUSE_NOTHING, /* fusible_ops */ }; /* Costs to use when optimizing for Sifive 7 Series. */ @@ -337,6 +352,7 @@ static const struct riscv_tune_param sifive_7_tune_info = { 3, /* memory_cost */ 8, /* fmv_cost */ true, /* slow_unaligned_access */ + RISCV_FUSE_NOTHING, /* fusible_ops */ }; /* Costs to use when optimizing for T-HEAD c906. */ @@ -351,6 +367,7 @@ static const struct riscv_tune_param thead_c906_tune_info = { 5, /* memory_cost */ 8, /* fmv_cost */ false, /* slow_unaligned_access */ + RISCV_FUSE_NOTHING, /* fusible_ops */ }; /* Costs to use when optimizing for size. */ @@ -365,6 +382,7 @@ static const struct riscv_tune_param optimize_size_tune_info = { 2, /* memory_cost */ 8, /* fmv_cost */ false, /* slow_unaligned_access */ + RISCV_FUSE_NOTHING, /* fusible_ops */ }; /* Costs to use when optimizing for Ventana Micro VT1. */ @@ -379,6 +397,10 @@ static const struct riscv_tune_param ventana_vt1_tune_info = { 5, /* memory_cost */ 8, /* fmv_cost */ false, /* slow_unaligned_access */ + ( RISCV_FUSE_ZEXTW | RISCV_FUSE_ZEXTH | /* fusible_ops */ + RISCV_FUSE_ZEXTWS | RISCV_FUSE_LDINDEXED | + RISCV_FUSE_LUI_ADDI | RISCV_FUSE_AUIPC_ADDI | + RISCV_FUSE_LUI_LD | RISCV_FUSE_AUIPC_LD ) }; static tree riscv_handle_fndecl_attribute (tree *, tree, tree, int, bool *); @@ -5796,6 +5818,200 @@ riscv_issue_rate (void) return tune_param->issue_rate; } +/* Implement TARGET_SCHED_MACRO_FUSION_P. Return true if target supports + instruction fusion of some sort. */ + +static bool +riscv_macro_fusion_p (void) +{ + return tune_param->fusible_ops != RISCV_FUSE_NOTHING; +} + +/* Return true iff the instruction fusion described by OP is enabled. */ + +static bool +riscv_fusion_enabled_p(enum riscv_fusion_pairs op) +{ + return tune_param->fusible_ops & op; +} + +/* Implement TARGET_SCHED_MACRO_FUSION_PAIR_P. Return true if PREV and CURR + should be kept together during scheduling. */ + +static bool +riscv_macro_fusion_pair_p (rtx_insn *prev, rtx_insn *curr) +{ + rtx prev_set = single_set (prev); + rtx curr_set = single_set (curr); + /* prev and curr are simple SET insns i.e. no flag setting or branching. */ + bool simple_sets_p = prev_set && curr_set && !any_condjump_p (curr); + + if (!riscv_macro_fusion_p ()) + return false; + + if (simple_sets_p + && (riscv_fusion_enabled_p (RISCV_FUSE_ZEXTW) + || riscv_fusion_enabled_p (RISCV_FUSE_ZEXTH))) + { + /* We are trying to match the following: + prev (slli) == (set (reg:DI rD) + (ashift:DI (reg:DI rS) (const_int 32))) + curr (slri) == (set (reg:DI rD) + (lshiftrt:DI (reg:DI rD) (const_int ))) + with being either 32 for FUSE_ZEXTW, or + less than 32 for FUSE_ZEXTWS. */ + + if (GET_CODE (SET_SRC (prev_set)) == ASHIFT + && GET_CODE (SET_SRC (curr_set)) == LSHIFTRT + && REG_P (SET_DEST (prev_set)) + && REG_P (SET_DEST (curr_set)) + && REGNO (SET_DEST (prev_set)) == REGNO (SET_DEST (curr_set)) + && REGNO (XEXP (SET_SRC (curr_set), 0)) == REGNO (SET_DEST (curr_set)) + && CONST_INT_P (XEXP (SET_SRC (prev_set), 1)) + && CONST_INT_P (XEXP (SET_SRC (curr_set), 1)) + && INTVAL (XEXP (SET_SRC (prev_set), 1)) == 32 + && ((INTVAL (XEXP (SET_SRC (curr_set), 1)) == 32 + && riscv_fusion_enabled_p (RISCV_FUSE_ZEXTW)) + || (INTVAL (XEXP (SET_SRC (curr_set), 1)) < 32 + && riscv_fusion_enabled_p (RISCV_FUSE_ZEXTWS)))) + return true; + } + + if (simple_sets_p && riscv_fusion_enabled_p (RISCV_FUSE_ZEXTH)) + { + /* We are trying to match the following: + prev (slli) == (set (reg:DI rD) + (ashift:DI (reg:DI rS) (const_int 48))) + curr (slri) == (set (reg:DI rD) + (lshiftrt:DI (reg:DI rD) (const_int 48))) */ + + if (GET_CODE (SET_SRC (prev_set)) == ASHIFT + && GET_CODE (SET_SRC (curr_set)) == LSHIFTRT + && REG_P (SET_DEST (prev_set)) + && REG_P (SET_DEST (curr_set)) + && REGNO (SET_DEST (prev_set)) == REGNO (SET_DEST (curr_set)) + && REGNO (XEXP (SET_SRC (curr_set), 0)) == REGNO (SET_DEST (curr_set)) + && CONST_INT_P (XEXP (SET_SRC (prev_set), 1)) + && CONST_INT_P (XEXP (SET_SRC (curr_set), 1)) + && INTVAL (XEXP (SET_SRC (prev_set), 1)) == 48 + && INTVAL (XEXP (SET_SRC (curr_set), 1)) == 48) + return true; + } + + if (simple_sets_p && riscv_fusion_enabled_p (RISCV_FUSE_LDINDEXED)) + { + /* We are trying to match the following: + prev (add) == (set (reg:DI rD) + (plus:DI (reg:DI rS1) (reg:DI rS2)) + curr (ld) == (set (reg:DI rD) + (mem:DI (reg:DI rD))) */ + + if (MEM_P (SET_SRC (curr_set)) + && REG_P (XEXP (SET_SRC (curr_set), 0)) + && REGNO (XEXP (SET_SRC (curr_set), 0)) == REGNO (SET_DEST (prev_set)) + && GET_CODE (SET_SRC (prev_set)) == PLUS + && REG_P (XEXP (SET_SRC (prev_set), 0)) + && REG_P (XEXP (SET_SRC (prev_set), 1))) + return true; + + /* We are trying to match the following: + prev (add) == (set (reg:DI rD) + (plus:DI (reg:DI rS1) (reg:DI rS2))) + curr (lw) == (set (any_extend:DI (mem:SUBX (reg:DI rD)))) */ + + if ((GET_CODE (SET_SRC (curr_set)) == SIGN_EXTEND + || (GET_CODE (SET_SRC (curr_set)) == ZERO_EXTEND)) + && MEM_P (XEXP (SET_SRC (curr_set), 0)) + && REG_P (XEXP (XEXP (SET_SRC (curr_set), 0), 0)) + && REGNO (XEXP (XEXP (SET_SRC (curr_set), 0), 0)) == REGNO (SET_DEST (prev_set)) + && GET_CODE (SET_SRC (prev_set)) == PLUS + && REG_P (XEXP (SET_SRC (prev_set), 0)) + && REG_P (XEXP (SET_SRC (prev_set), 1))) + return true; + } + + if (simple_sets_p && riscv_fusion_enabled_p (RISCV_FUSE_LUI_ADDI)) + { + /* We are trying to match the following: + prev (lui) == (set (reg:DI rD) (const_int UPPER_IMM_20)) + curr (addi) == (set (reg:DI rD) + (plus:DI (reg:DI rD) (const_int IMM12))) */ + + if ((GET_CODE (SET_SRC (curr_set)) == LO_SUM + || (GET_CODE (SET_SRC (curr_set)) == PLUS + && CONST_INT_P (XEXP (SET_SRC (curr_set), 1)) + && SMALL_OPERAND (INTVAL (XEXP (SET_SRC (curr_set), 1))))) + && (GET_CODE (SET_SRC (prev_set)) == HIGH + || (CONST_INT_P (SET_SRC (prev_set)) + && LUI_OPERAND (INTVAL (SET_SRC (prev_set)))))) + return true; + } + + if (simple_sets_p && riscv_fusion_enabled_p (RISCV_FUSE_AUIPC_ADDI)) + { + /* We are trying to match the following: + prev (auipc) == (set (reg:DI rD) (unspec:DI [...] UNSPEC_AUIPC)) + curr (addi) == (set (reg:DI rD) + (plus:DI (reg:DI rD) (const_int IMM12))) + and + prev (auipc) == (set (reg:DI rD) (unspec:DI [...] UNSPEC_AUIPC)) + curr (addi) == (set (reg:DI rD) + (lo_sum:DI (reg:DI rD) (const_int IMM12))) */ + + if (GET_CODE (SET_SRC (prev_set)) == UNSPEC + && XINT (prev_set, 1) == UNSPEC_AUIPC + && (GET_CODE (SET_SRC (curr_set)) == LO_SUM + || (GET_CODE (SET_SRC (curr_set)) == PLUS + && SMALL_OPERAND (INTVAL (XEXP (SET_SRC (curr_set), 1)))))) + + return true; + } + + if (simple_sets_p && riscv_fusion_enabled_p (RISCV_FUSE_LUI_LD)) + { + /* We are trying to match the following: + prev (lui) == (set (reg:DI rD) (const_int UPPER_IMM_20)) + curr (ld) == (set (reg:DI rD) + (mem:DI (plus:DI (reg:DI rD) (const_int IMM12)))) */ + + if (CONST_INT_P (SET_SRC (prev_set)) + && LUI_OPERAND (INTVAL (SET_SRC (prev_set))) + && MEM_P (SET_SRC (curr_set)) + && GET_CODE (XEXP (SET_SRC (curr_set), 0)) == PLUS) + return true; + + if (GET_CODE (SET_SRC (prev_set)) == HIGH + && MEM_P (SET_SRC (curr_set)) + && GET_CODE (XEXP (SET_SRC (curr_set), 0)) == LO_SUM + && REGNO (SET_DEST (prev_set)) == REGNO (XEXP (XEXP (SET_SRC (curr_set), 0), 0))) + return true; + + if (GET_CODE (SET_SRC (prev_set)) == HIGH + && (GET_CODE (SET_SRC (curr_set)) == SIGN_EXTEND + || GET_CODE (SET_SRC (curr_set)) == ZERO_EXTEND) + && MEM_P (XEXP (SET_SRC (curr_set), 0)) + && (GET_CODE (XEXP (XEXP (SET_SRC (curr_set), 0), 0)) == LO_SUM + && REGNO (SET_DEST (prev_set)) == REGNO (XEXP (XEXP (XEXP (SET_SRC (curr_set), 0), 0), 0)))) + return true; + } + + if (simple_sets_p && riscv_fusion_enabled_p (RISCV_FUSE_AUIPC_LD)) + { + /* We are trying to match the following: + prev (auipc) == (set (reg:DI rD) (unspec:DI [...] UNSPEC_AUIPC)) + curr (ld) == (set (reg:DI rD) + (mem:DI (plus:DI (reg:DI rD) (const_int IMM12)))) */ + + if (GET_CODE (SET_SRC (prev_set)) == UNSPEC + && XINT (prev_set, 1) == UNSPEC_AUIPC + && MEM_P (SET_SRC (curr_set)) + && GET_CODE (XEXP (SET_SRC (curr_set), 0)) == PLUS) + return true; + } + + return false; +} + /* Auxiliary function to emit RISC-V ELF attribute. */ static void riscv_emit_attribute () @@ -6826,6 +7042,10 @@ riscv_shamt_matches_mask_p (int shamt, HOST_WIDE_INT mask) #undef TARGET_SCHED_ISSUE_RATE #define TARGET_SCHED_ISSUE_RATE riscv_issue_rate +#undef TARGET_SCHED_MACRO_FUSION_P +#define TARGET_SCHED_MACRO_FUSION_P riscv_macro_fusion_p +#undef TARGET_SCHED_MACRO_FUSION_PAIR_P +#define TARGET_SCHED_MACRO_FUSION_PAIR_P riscv_macro_fusion_pair_p #undef TARGET_FUNCTION_OK_FOR_SIBCALL #define TARGET_FUNCTION_OK_FOR_SIBCALL riscv_function_ok_for_sibcall