diff options
author | Ju-Zhe Zhong <juzhe.zhong@rivai.ai> | 2023-06-09 16:39:34 +0800 |
---|---|---|
committer | Pan Li <pan2.li@intel.com> | 2023-06-10 07:52:46 +0800 |
commit | 47203d89a0ff914406f635bf9cf34e61ed6f19c5 (patch) | |
tree | 25fc7145f2aeff3592cd1d3a16ef66931a9c8a86 /gcc/tree-vect-loop-manip.cc | |
parent | fe9771b59f576fb37e762013ef5d9b26162e3a88 (diff) | |
download | gcc-47203d89a0ff914406f635bf9cf34e61ed6f19c5.zip gcc-47203d89a0ff914406f635bf9cf34e61ed6f19c5.tar.gz gcc-47203d89a0ff914406f635bf9cf34e61ed6f19c5.tar.bz2 |
VECT: Add SELECT_VL support
This patch address comments from Richard && Richi and rebase to trunk.
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
Co-authored-by: Richard Sandiford<richard.sandiford@arm.com>
Co-authored-by: Richard Biener <rguenther@suse.de>
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.
Diffstat (limited to 'gcc/tree-vect-loop-manip.cc')
-rw-r--r-- | gcc/tree-vect-loop-manip.cc | 32 |
1 files changed, 23 insertions, 9 deletions
diff --git a/gcc/tree-vect-loop-manip.cc b/gcc/tree-vect-loop-manip.cc index 3f73594..1c8100c 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); ... @@ -549,15 +549,28 @@ vect_set_loop_controls_directly (class loop *loop, loop_vec_info loop_vinfo, tree step = rgc->controls.length () == 1 ? rgc->controls[0] : make_ssa_name (iv_type); /* Create decrement IV. */ - create_iv (nitems_total, MINUS_EXPR, nitems_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)); + if (LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo)) + { + create_iv (nitems_total, MINUS_EXPR, step, NULL_TREE, loop, &incr_gsi, + insert_after, &index_before_incr, &index_after_incr); + tree len = gimple_build (header_seq, IFN_SELECT_VL, iv_type, + index_before_incr, nitems_step); + gimple_seq_add_stmt (header_seq, gimple_build_assign (step, len)); + } + else + { + create_iv (nitems_total, MINUS_EXPR, nitems_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)); + } *iv_step = step; *compare_step = nitems_step; - return index_before_incr; + return LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo) ? index_after_incr + : index_before_incr; } /* Create increment IV. */ @@ -888,7 +901,8 @@ vect_set_loop_condition_partial_vectors (class loop *loop, /* Get a boolean result that tells us whether to iterate. */ edge exit_edge = single_exit (loop); gcond *cond_stmt; - if (LOOP_VINFO_USING_DECREMENTING_IV_P (loop_vinfo)) + if (LOOP_VINFO_USING_DECREMENTING_IV_P (loop_vinfo) + && !LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo)) { gcc_assert (compare_step); tree_code code = (exit_edge->flags & EDGE_TRUE_VALUE) ? LE_EXPR : GT_EXPR; |