From 47203d89a0ff914406f635bf9cf34e61ed6f19c5 Mon Sep 17 00:00:00 2001
From: Ju-Zhe Zhong <juzhe.zhong@rivai.ai>
Date: Fri, 9 Jun 2023 16:39:34 +0800
Subject: 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.
---
 gcc/tree-vectorizer.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'gcc/tree-vectorizer.h')

diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index 1e44f85..af25d20 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
-- 
cgit v1.1