From: Ju-Zhe Zhong <juzhe.zh...@rivai.ai> This patch is adding SELECT_VL middle-end support allow target have target dependent optimization in case of length calculation.
This patch is inspired by RVV ISA and LLVM: https://reviews.llvm.org/D99750 The SELECT_VL is same behavior as LLVM "get_vector_length" with these following properties: 1. Only apply on single-rgroup. 2. non SLP. 3. adjust loop control IV. 4. adjust data reference IV. 5. allow non-vf elements processing in non-final iteration Code: # void vvaddint32(size_t n, const int*x, const int*y, int*z) # { for (size_t i=0; i<n; i++) { z[i]=x[i]+y[i]; } } Take RVV codegen for example: Before this patch: vvaddint32: ble a0,zero,.L6 csrr a4,vlenb srli a6,a4,2 .L4: mv a5,a0 bleu a0,a6,.L3 mv a5,a6 .L3: vsetvli zero,a5,e32,m1,ta,ma vle32.v v2,0(a1) vle32.v v1,0(a2) vsetvli a7,zero,e32,m1,ta,ma sub a0,a0,a5 vadd.vv v1,v1,v2 vsetvli zero,a5,e32,m1,ta,ma vse32.v v1,0(a3) add a2,a2,a4 add a3,a3,a4 add a1,a1,a4 bne a0,zero,.L4 .L6: ret After this patch: vvaddint32: vsetvli t0, a0, e32, ta, ma # Set vector length based on 32-bit vectors vle32.v v0, (a1) # Get first vector sub a0, a0, t0 # Decrement number done slli t0, t0, 2 # Multiply number done by 4 bytes add a1, a1, t0 # Bump pointer vle32.v v1, (a2) # Get second vector add a2, a2, t0 # Bump pointer vadd.vv v2, v0, v1 # Sum vectors vse32.v v2, (a3) # Store result add a3, a3, t0 # Bump pointer bnez a0, vvaddint32 # Loop back ret # Finished gcc/ChangeLog: * doc/md.texi: Add SELECT_VL support. * internal-fn.def (SELECT_VL): Ditto. * optabs.def (OPTAB_D): Ditto. * tree-vect-loop-manip.cc (vect_set_loop_controls_directly): Ditto. * tree-vect-loop.cc (_loop_vec_info::_loop_vec_info): Ditto. * tree-vect-stmts.cc (get_select_vl_data_ref_ptr): Ditto. (vectorizable_store): Ditto. (vectorizable_load): Ditto. * tree-vectorizer.h (LOOP_VINFO_USING_SELECT_VL_P): Ditto. --- gcc/doc/md.texi | 22 ++++++++++++ gcc/internal-fn.def | 1 + gcc/optabs.def | 1 + gcc/tree-vect-loop-manip.cc | 13 ++++--- gcc/tree-vect-loop.cc | 9 +++++ gcc/tree-vect-stmts.cc | 70 +++++++++++++++++++++++++++++++++++++ gcc/tree-vectorizer.h | 6 ++++ 7 files changed, 118 insertions(+), 4 deletions(-) diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi index 6a435eb4461..95f7fe1f802 100644 --- a/gcc/doc/md.texi +++ b/gcc/doc/md.texi @@ -4974,6 +4974,28 @@ for (i = 1; i < operand3; i++) operand0[i] = operand0[i - 1] && (operand1 + i < operand2); @end smallexample +@cindex @code{select_vl@var{m}} instruction pattern +@item @code{select_vl@var{m}} +Set operand 0 to the number of scalar iterations that should be handled +by one iteration of a vector loop. Operand 1 is the total number of +scalar iterations that the loop needs to process and operand 2 is a +maximum bound on the result (also known as the maximum ``vectorization +factor''). + +The maximum value of operand 0 is given by: +@smallexample +operand0 = MIN (operand1, operand2) +@end smallexample +However, targets might choose a lower value than this, based on +target-specific criteria. Each iteration of the vector loop might +therefore process a different number of scalar iterations, which in turn +means that induction variables will have a variable step. Because of +this, it is generally not useful to define this instruction if it will +always calculate the maximum value. + +This optab is only useful on targets that implement @samp{len_load_@var{m}} +and/or @samp{len_store_@var{m}}. + @cindex @code{check_raw_ptrs@var{m}} instruction pattern @item @samp{check_raw_ptrs@var{m}} Check whether, given two pointers @var{a} and @var{b} and a length @var{len}, diff --git a/gcc/internal-fn.def b/gcc/internal-fn.def index 7fe742c2ae7..6f6fa7d37f9 100644 --- a/gcc/internal-fn.def +++ b/gcc/internal-fn.def @@ -153,6 +153,7 @@ DEF_INTERNAL_OPTAB_FN (VEC_SET, 0, vec_set, vec_set) DEF_INTERNAL_OPTAB_FN (LEN_STORE, 0, len_store, len_store) DEF_INTERNAL_OPTAB_FN (WHILE_ULT, ECF_CONST | ECF_NOTHROW, while_ult, while) +DEF_INTERNAL_OPTAB_FN (SELECT_VL, ECF_CONST | ECF_NOTHROW, select_vl, binary) DEF_INTERNAL_OPTAB_FN (CHECK_RAW_PTRS, ECF_CONST | ECF_NOTHROW, check_raw_ptrs, check_ptrs) DEF_INTERNAL_OPTAB_FN (CHECK_WAR_PTRS, ECF_CONST | ECF_NOTHROW, diff --git a/gcc/optabs.def b/gcc/optabs.def index 695f5911b30..b637471b76e 100644 --- a/gcc/optabs.def +++ b/gcc/optabs.def @@ -476,3 +476,4 @@ 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 (select_vl_optab, "select_vl$a") diff --git a/gcc/tree-vect-loop-manip.cc b/gcc/tree-vect-loop-manip.cc index acf3642ceb2..3ca61663684 100644 --- a/gcc/tree-vect-loop-manip.cc +++ b/gcc/tree-vect-loop-manip.cc @@ -534,7 +534,7 @@ vect_set_loop_controls_directly (class loop *loop, loop_vec_info loop_vinfo, _10 = (unsigned long) count_12(D); ... # ivtmp_9 = PHI <ivtmp_35(6), _10(5)> - _36 = MIN_EXPR <ivtmp_9, POLY_INT_CST [4, 4]>; + _36 = (MIN_EXPR | SELECT_VL) <ivtmp_9, POLY_INT_CST [4, 4]>; ... vect__4.8_28 = .LEN_LOAD (_17, 32B, _36, 0); ... @@ -551,9 +551,14 @@ vect_set_loop_controls_directly (class loop *loop, loop_vec_info loop_vinfo, /* Create decrement IV. */ create_iv (nitems_total, MINUS_EXPR, step, NULL_TREE, loop, &incr_gsi, insert_after, &index_before_incr, &index_after_incr); - gimple_seq_add_stmt (header_seq, gimple_build_assign (step, MIN_EXPR, - index_before_incr, - nitems_step)); + tree len = NULL_TREE; + if (LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo)) + len = gimple_build (header_seq, IFN_SELECT_VL, iv_type, + index_before_incr, nitems_step); + else + len = gimple_build (header_seq, MIN_EXPR, iv_type, index_before_incr, + nitems_step); + gimple_seq_add_stmt (header_seq, gimple_build_assign (step, len)); *iv_step = step; return index_after_incr; } diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc index 5b7a0da0034..f67340976c8 100644 --- a/gcc/tree-vect-loop.cc +++ b/gcc/tree-vect-loop.cc @@ -974,6 +974,7 @@ _loop_vec_info::_loop_vec_info (class loop *loop_in, vec_info_shared *shared) can_use_partial_vectors_p (param_vect_partial_vector_usage != 0), using_partial_vectors_p (false), using_decrementing_iv_p (false), + using_select_vl_p (false), epil_using_partial_vectors_p (false), partial_load_store_bias (0), peeling_for_gaps (false), @@ -2737,6 +2738,14 @@ start_over: LOOP_VINFO_VECT_FACTOR (loop_vinfo)))) LOOP_VINFO_USING_DECREMENTING_IV_P (loop_vinfo) = true; + /* If we're using decrement IV and SELECT_VL is supported by the target. + Use output of SELECT_VL to adjust IV of loop control and data reference. + Note: We only use SELECT_VL on single-rgroup control. */ + if (LOOP_VINFO_USING_DECREMENTING_IV_P (loop_vinfo) + && LOOP_VINFO_LENS (loop_vinfo).length () == 1 + && !slp) + LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo) = true; + /* If we're vectorizing an epilogue loop, the vectorized loop either needs to be able to handle fewer than VF scalars, or needs to have a lower VF than the main loop. */ diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc index 127b987cd62..8e8b0f71a4a 100644 --- a/gcc/tree-vect-stmts.cc +++ b/gcc/tree-vect-stmts.cc @@ -3147,6 +3147,61 @@ vect_get_data_ptr_increment (vec_info *vinfo, return iv_step; } +/* Prepare the pointer IVs which needs to be updated by a variable amount. + Such variable amount is the outcome of .SELECT_VL. In this case, we can + allow each iteration process the flexible number of elements as long as + the number <= vf elments. + + Return data reference according to SELECT_VL. + If new statements are needed, insert them before GSI. */ + +static tree +get_select_vl_data_ref_ptr (vec_info *vinfo, stmt_vec_info stmt_info, + tree aggr_type, class loop *at_loop, tree offset, + tree *dummy, gimple_stmt_iterator *gsi, + bool simd_lane_access_p, vec_loop_lens *loop_lens, + dr_vec_info *dr_info, + vect_memory_access_type memory_access_type) +{ + loop_vec_info loop_vinfo = dyn_cast<loop_vec_info> (vinfo); + tree step = vect_dr_behavior (vinfo, dr_info)->step; + + /* TODO: We don't support gather/scatter or load_lanes/store_lanes for pointer + IVs are updated by variable amount but we will support them in the future. + */ + gcc_assert (memory_access_type != VMAT_GATHER_SCATTER + && memory_access_type != VMAT_LOAD_STORE_LANES); + + /* When we support SELECT_VL pattern, we dynamic adjust + the memory address by .SELECT_VL result. + + The result of .SELECT_VL is the number of elements to + be processed of each iteration. So the memory address + adjustment operation should be: + + bytesize = GET_MODE_SIZE (element_mode (aggr_type)); + addr = addr + .SELECT_VL (ARG..) * bytesize; + */ + gimple *ptr_incr; + tree loop_len + = vect_get_loop_len (loop_vinfo, gsi, loop_lens, 1, aggr_type, 0, 0); + tree len_type = TREE_TYPE (loop_len); + poly_uint64 bytesize = GET_MODE_SIZE (element_mode (aggr_type)); + /* Since the outcome of .SELECT_VL is element size, we should adjust + it into bytesize so that it can be used in address pointer variable + amount IVs adjustment. */ + tree tmp = fold_build2 (MULT_EXPR, len_type, loop_len, + build_int_cst (len_type, bytesize)); + if (tree_int_cst_sgn (step) == -1) + tmp = fold_build1 (NEGATE_EXPR, len_type, tmp); + tree bump = make_temp_ssa_name (len_type, NULL, "ivtmp"); + gassign *assign = gimple_build_assign (bump, tmp); + gsi_insert_before (gsi, assign, GSI_SAME_STMT); + return vect_create_data_ref_ptr (vinfo, stmt_info, aggr_type, at_loop, offset, + dummy, gsi, &ptr_incr, simd_lane_access_p, + bump); +} + /* Check and perform vectorization of BUILT_IN_BSWAP{16,32,64,128}. */ static bool @@ -8558,6 +8613,14 @@ vectorizable_store (vec_info *vinfo, vect_get_gather_scatter_ops (loop_vinfo, loop, stmt_info, slp_node, &gs_info, &dataref_ptr, &vec_offsets); + else if (loop_lens && LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo) + && memory_access_type != VMAT_INVARIANT) + dataref_ptr + = get_select_vl_data_ref_ptr (vinfo, stmt_info, aggr_type, + simd_lane_access_p ? loop : NULL, + offset, &dummy, gsi, + simd_lane_access_p, loop_lens, + dr_info, memory_access_type); else dataref_ptr = vect_create_data_ref_ptr (vinfo, first_stmt_info, aggr_type, @@ -9949,6 +10012,13 @@ vectorizable_load (vec_info *vinfo, slp_node, &gs_info, &dataref_ptr, &vec_offsets); } + else if (loop_lens && LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo) + && memory_access_type != VMAT_INVARIANT) + dataref_ptr + = get_select_vl_data_ref_ptr (vinfo, stmt_info, aggr_type, + at_loop, offset, &dummy, gsi, + simd_lane_access_p, loop_lens, + dr_info, memory_access_type); else dataref_ptr = vect_create_data_ref_ptr (vinfo, first_stmt_info, aggr_type, diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h index fba09b9ffd3..97dd9ec06e8 100644 --- a/gcc/tree-vectorizer.h +++ b/gcc/tree-vectorizer.h @@ -825,6 +825,11 @@ public: (b) can iterate more than once. */ bool using_decrementing_iv_p; + /* True if we've decided to use output of select_vl to adjust IV of + both loop control and data reference pointer. This is only true + for single-rgroup control. */ + bool using_select_vl_p; + /* True if we've decided to use partially-populated vectors for the epilogue of loop. */ bool epil_using_partial_vectors_p; @@ -898,6 +903,7 @@ public: #define LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P(L) (L)->can_use_partial_vectors_p #define LOOP_VINFO_USING_PARTIAL_VECTORS_P(L) (L)->using_partial_vectors_p #define LOOP_VINFO_USING_DECREMENTING_IV_P(L) (L)->using_decrementing_iv_p +#define LOOP_VINFO_USING_SELECT_VL_P(L) (L)->using_select_vl_p #define LOOP_VINFO_EPIL_USING_PARTIAL_VECTORS_P(L) \ (L)->epil_using_partial_vectors_p #define LOOP_VINFO_PARTIAL_LOAD_STORE_BIAS(L) (L)->partial_load_store_bias -- 2.36.1
