Hi, Richi. strided load/store has been posted for a while. Can this feature be available on GCC-14 ? Or postpone it to GCC-15 ? Thanks. juzhe.zhong@rivai.ai 发件人： juzhe.zhong@rivai.ai 发送时间： 2023-11-16 15:21 收件人： 钟居哲; gcc-patches 抄送： richard.sandiford; rguenther 主题： Re: [PATCH] DOC/IFN/OPTAB: Add mask_len_strided_load/mask_len_strided_store DOC/OPTAB/IFN Update just finished test CI. Tested on aarch64 QEMU no regression. juzhe.zhong@rivai.ai From: Juzhe-Zhong Date: 2023-11-14 11:39 To: gcc-patches CC: richard.sandiford; rguenther; Juzhe-Zhong Subject: [PATCH] DOC/IFN/OPTAB: Add mask_len_strided_load/mask_len_strided_store DOC/OPTAB/IFN This patch adds mask_len_strided_load/mask_len_strided_store. Document already has been reviewed. This patch adds OPTAB/IFN support as follows: 1. strided load GIMPLE level: v = MASK_LEN_STRIDED_LOAD (ptr, stride, mask, len, bias) be expand (by internal-fn.cc) into: v = mask_len_strided_load (ptr, stried, mask, len, bias) 2. strided store GIMPLE leve: MASK_LEN_STRIED_STORE (ptr, stride, v, mask, len, bias) be expand (by internal-fn.cc) into: mask_len_stried_store (ptr, stride, v, mask, len, bias) Bootstrap and regression on X86 no regression. Ok for trunk ? gcc/ChangeLog: * doc/md.texi: Add mask_len_strided_load/mask_len_strided_store. * internal-fn.cc (strided_load_direct): Ditto. (strided_store_direct): Ditto. (expand_strided_store_optab_fn): Ditto. (expand_strided_load_optab_fn): Ditto. (direct_strided_load_optab_supported_p): Ditto. (direct_strided_store_optab_supported_p): Ditto. (internal_fn_len_index): Ditto. (internal_fn_mask_index): Ditto. (internal_fn_stored_value_index): Ditto. * internal-fn.def (MASK_LEN_STRIDED_LOAD): Ditto. (MASK_LEN_STRIDED_STORE): Ditto. * optabs.def (OPTAB_D): Ditto. --- gcc/doc/md.texi | 27 +++++++++++++++++++ gcc/internal-fn.cc | 63 +++++++++++++++++++++++++++++++++++++++++++++ gcc/internal-fn.def | 6 +++++ gcc/optabs.def | 2 ++ 4 files changed, 98 insertions(+) diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi index 5d86152e5dd..5dc76a1183c 100644 --- a/gcc/doc/md.texi +++ b/gcc/doc/md.texi @@ -5094,6 +5094,20 @@ Bit @var{i} of the mask is set if element @var{i} of the result should be loaded from memory and clear if element @var{i} of the result should be undefined. Mask elements @var{i} with @var{i} > (operand 6 + operand 7) are ignored. +@cindex @code{mask_len_strided_load@var{m}} instruction pattern +@item @samp{mask_len_strided_load@var{m}} +Load several separate memory locations into a destination vector of mode @var{m}. +Operand 0 is a destination vector of mode @var{m}. +Operand 1 is a scalar base address and operand 2 is a scalar stride of Pmode. +operand 3 is mask operand, operand 4 is length operand and operand 5 is bias operand. +The instruction can be seen as a special case of @code{mask_len_gather_load@var{m}@var{n}} +with an offset vector that is a @code{vec_series} with operand 1 as base and operand 2 as step. +For each element index i load address is operand 1 + @var{i} * operand 2. +Similar to mask_len_load, the instruction loads at most (operand 4 + operand 5) elements from memory. +Element @var{i} of the mask (operand 3) is set if element @var{i} of the result should +be loaded from memory and clear if element @var{i} of the result should be zero. +Mask elements @var{i} with @var{i} > (operand 4 + operand 5) are ignored. + @cindex @code{scatter_store@var{m}@var{n}} instruction pattern @item @samp{scatter_store@var{m}@var{n}} Store a vector of mode @var{m} into several distinct memory locations. @@ -5131,6 +5145,19 @@ at most (operand 6 + operand 7) elements of (operand 4) to memory. Bit @var{i} of the mask is set if element @var{i} of (operand 4) should be stored. Mask elements @var{i} with @var{i} > (operand 6 + operand 7) are ignored. +@cindex @code{mask_len_strided_store@var{m}} instruction pattern +@item @samp{mask_len_strided_store@var{m}} +Store a vector of mode m into several distinct memory locations. +Operand 0 is a scalar base address and operand 1 is scalar stride of Pmode. +Operand 2 is the vector of values that should be stored, which is of mode @var{m}. +operand 3 is mask operand, operand 4 is length operand and operand 5 is bias operand. +The instruction can be seen as a special case of @code{mask_len_scatter_store@var{m}@var{n}} +with an offset vector that is a @code{vec_series} with operand 1 as base and operand 1 as step. +For each element index i store address is operand 0 + @var{i} * operand 1. +Similar to mask_len_store, the instruction stores at most (operand 4 + operand 5) elements of mask (operand 3) to memory. +Element @var{i} of the mask is set if element @var{i} of (operand 3) should be stored. +Mask elements @var{i} with @var{i} > (operand 4 + operand 5) are ignored. + @cindex @code{vec_set@var{m}} instruction pattern @item @samp{vec_set@var{m}} Set given field in the vector value. Operand 0 is the vector to modify, diff --git a/gcc/internal-fn.cc b/gcc/internal-fn.cc index 5a998e794ad..bfb307684a9 100644 --- a/gcc/internal-fn.cc +++ b/gcc/internal-fn.cc @@ -164,6 +164,7 @@ init_internal_fns () #define load_lanes_direct { -1, -1, false } #define mask_load_lanes_direct { -1, -1, false } #define gather_load_direct { 3, 1, false } +#define strided_load_direct { -1, -1, false } #define len_load_direct { -1, -1, false } #define mask_len_load_direct { -1, 4, false } #define mask_store_direct { 3, 2, false } @@ -173,6 +174,7 @@ init_internal_fns () #define vec_cond_mask_len_direct { 1, 1, false } #define vec_cond_direct { 2, 0, false } #define scatter_store_direct { 3, 1, false } +#define strided_store_direct { 1, 1, false } #define len_store_direct { 3, 3, false } #define mask_len_store_direct { 4, 5, false } #define vec_set_direct { 3, 3, false } @@ -3593,6 +3595,31 @@ expand_scatter_store_optab_fn (internal_fn, gcall *stmt, direct_optab optab) expand_insn (icode, i, ops); } +/* Expand MASK_LEN_STRIDED_STORE call CALL using optab OPTAB. */ + +static void +expand_strided_store_optab_fn (internal_fn, gcall *stmt, direct_optab optab) +{ + internal_fn ifn = gimple_call_internal_fn (stmt); + int rhs_index = internal_fn_stored_value_index (ifn); + tree base = gimple_call_arg (stmt, 0); + tree stride = gimple_call_arg (stmt, 1); + tree rhs = gimple_call_arg (stmt, rhs_index); + + rtx base_rtx = expand_normal (base); + rtx stride_rtx = expand_normal (stride); + rtx rhs_rtx = expand_normal (rhs); + + class expand_operand ops[6]; + int i = 0; + create_address_operand (&ops[i++], base_rtx); + create_address_operand (&ops[i++], stride_rtx); + create_input_operand (&ops[i++], rhs_rtx, TYPE_MODE (TREE_TYPE (rhs))); + i = add_mask_and_len_args (ops, i, stmt); + insn_code icode = direct_optab_handler (optab, TYPE_MODE (TREE_TYPE (rhs))); + expand_insn (icode, i, ops); +} + /* Expand {MASK_,}GATHER_LOAD call CALL using optab OPTAB. */ static void @@ -3623,6 +3650,31 @@ expand_gather_load_optab_fn (internal_fn, gcall *stmt, direct_optab optab) emit_move_insn (lhs_rtx, ops[0].value); } +/* Expand MASK_LEN_STRIDED_LOAD call CALL using optab OPTAB. */ + +static void +expand_strided_load_optab_fn (internal_fn, gcall *stmt, direct_optab optab) +{ + tree lhs = gimple_call_lhs (stmt); + tree base = gimple_call_arg (stmt, 0); + tree stride = gimple_call_arg (stmt, 1); + + rtx lhs_rtx = expand_expr (lhs, NULL_RTX, VOIDmode, EXPAND_WRITE); + rtx base_rtx = expand_normal (base); + rtx stride_rtx = expand_normal (stride); + + int i = 0; + class expand_operand ops[6]; + create_output_operand (&ops[i++], lhs_rtx, TYPE_MODE (TREE_TYPE (lhs))); + create_address_operand (&ops[i++], base_rtx); + create_address_operand (&ops[i++], stride_rtx); + i = add_mask_and_len_args (ops, i, stmt); + insn_code icode = direct_optab_handler (optab, TYPE_MODE (TREE_TYPE (lhs))); + expand_insn (icode, i, ops); + if (!rtx_equal_p (lhs_rtx, ops[0].value)) + emit_move_insn (lhs_rtx, ops[0].value); +} + /* Helper for expand_DIVMOD. Return true if the sequence starting with INSN contains any call insns or insns with {,U}{DIV,MOD} rtxes. */ @@ -4013,6 +4065,7 @@ multi_vector_optab_supported_p (convert_optab optab, tree_pair types, #define direct_load_lanes_optab_supported_p multi_vector_optab_supported_p #define direct_mask_load_lanes_optab_supported_p multi_vector_optab_supported_p #define direct_gather_load_optab_supported_p convert_optab_supported_p +#define direct_strided_load_optab_supported_p direct_optab_supported_p #define direct_len_load_optab_supported_p direct_optab_supported_p #define direct_mask_len_load_optab_supported_p convert_optab_supported_p #define direct_mask_store_optab_supported_p convert_optab_supported_p @@ -4021,6 +4074,7 @@ multi_vector_optab_supported_p (convert_optab optab, tree_pair types, #define direct_vec_cond_mask_optab_supported_p convert_optab_supported_p #define direct_vec_cond_optab_supported_p convert_optab_supported_p #define direct_scatter_store_optab_supported_p convert_optab_supported_p +#define direct_strided_store_optab_supported_p direct_optab_supported_p #define direct_len_store_optab_supported_p direct_optab_supported_p #define direct_mask_len_store_optab_supported_p convert_optab_supported_p #define direct_while_optab_supported_p convert_optab_supported_p @@ -4684,6 +4738,8 @@ internal_fn_len_index (internal_fn fn) case IFN_COND_LEN_XOR: case IFN_COND_LEN_SHL: case IFN_COND_LEN_SHR: + case IFN_MASK_LEN_STRIDED_LOAD: + case IFN_MASK_LEN_STRIDED_STORE: return 4; case IFN_COND_LEN_NEG: @@ -4778,6 +4834,10 @@ internal_fn_mask_index (internal_fn fn) case IFN_MASK_LEN_STORE: return 2; + case IFN_MASK_LEN_STRIDED_LOAD: + case IFN_MASK_LEN_STRIDED_STORE: + return 3; + case IFN_MASK_GATHER_LOAD: case IFN_MASK_SCATTER_STORE: case IFN_MASK_LEN_GATHER_LOAD: @@ -4801,6 +4861,9 @@ internal_fn_stored_value_index (internal_fn fn) { switch (fn) { + case IFN_MASK_LEN_STRIDED_STORE: + return 2; + case IFN_MASK_STORE: case IFN_MASK_STORE_LANES: case IFN_SCATTER_STORE: diff --git a/gcc/internal-fn.def b/gcc/internal-fn.def index 319e0ab26cd..8a380df20f1 100644 --- a/gcc/internal-fn.def +++ b/gcc/internal-fn.def @@ -52,6 +52,7 @@ along with GCC; see the file COPYING3. If not see - mask_load_lanes: currently just vec_mask_load_lanes - mask_len_load_lanes: currently just vec_mask_len_load_lanes - gather_load: used for {mask_,mask_len_,}gather_load + - strided_load: currently just mask_len_strided_load - len_load: currently just len_load - mask_len_load: currently just mask_len_load @@ -60,6 +61,7 @@ along with GCC; see the file COPYING3. If not see - mask_store_lanes: currently just vec_mask_store_lanes - mask_len_store_lanes: currently just vec_mask_len_store_lanes - scatter_store: used for {mask_,mask_len_,}scatter_store + - strided_store: currently just mask_len_strided_store - len_store: currently just len_store - mask_len_store: currently just mask_len_store @@ -199,6 +201,8 @@ DEF_INTERNAL_OPTAB_FN (MASK_GATHER_LOAD, ECF_PURE, mask_gather_load, gather_load) DEF_INTERNAL_OPTAB_FN (MASK_LEN_GATHER_LOAD, ECF_PURE, mask_len_gather_load, gather_load) +DEF_INTERNAL_OPTAB_FN (MASK_LEN_STRIDED_LOAD, ECF_PURE, + mask_len_strided_load, strided_load) DEF_INTERNAL_OPTAB_FN (LEN_LOAD, ECF_PURE, len_load, len_load) DEF_INTERNAL_OPTAB_FN (MASK_LEN_LOAD, ECF_PURE, mask_len_load, mask_len_load) @@ -208,6 +212,8 @@ DEF_INTERNAL_OPTAB_FN (MASK_SCATTER_STORE, 0, mask_scatter_store, scatter_store) DEF_INTERNAL_OPTAB_FN (MASK_LEN_SCATTER_STORE, 0, mask_len_scatter_store, scatter_store) +DEF_INTERNAL_OPTAB_FN (MASK_LEN_STRIDED_STORE, 0, + mask_len_strided_store, strided_store) DEF_INTERNAL_OPTAB_FN (MASK_STORE, 0, maskstore, mask_store) DEF_INTERNAL_OPTAB_FN (STORE_LANES, ECF_CONST, vec_store_lanes, store_lanes) diff --git a/gcc/optabs.def b/gcc/optabs.def index 07c06ba8cbb..fa7a51b4906 100644 --- a/gcc/optabs.def +++ b/gcc/optabs.def @@ -539,4 +539,6 @@ OPTAB_DC (vec_series_optab, "vec_series$a", VEC_SERIES) OPTAB_D (vec_shl_insert_optab, "vec_shl_insert_$a") OPTAB_D (len_load_optab, "len_load_$a") OPTAB_D (len_store_optab, "len_store_$a") +OPTAB_D (mask_len_strided_load_optab, "mask_len_strided_load_$a") +OPTAB_D (mask_len_strided_store_optab, "mask_len_strided_store_$a") OPTAB_D (select_vl_optab, "select_vl$a") -- 2.36.3