Re: [PATCH V15] VECT: Add decrement IV iteration loop control by variable amount support

["juzhe.zhong@rivai.ai" <juzhe.zhong@rivai.ai>]

[-- Attachment #1: Type: text/plain, Size: 24849 bytes --]

Bootstrap && Regression on X86 passed.

Ok for trunk ?


juzhe.zhong@rivai.ai
 
From: juzhe.zhong
Date: 2023-05-25 10:58
To: gcc-patches
CC: richard.sandiford; rguenther; Ju-Zhe Zhong
Subject: [PATCH V15] VECT: Add decrement IV iteration loop control by variable amount support
From: Ju-Zhe Zhong <juzhe.zhong@rivai.ai>
 
This patch is supporting decrement IV by following the flow designed by Richard:
 
(1) In vect_set_loop_condition_partial_vectors, for the first iteration of:
    call vect_set_loop_controls_directly.
 
(2) vect_set_loop_controls_directly calculates "step" as in your patch.
If rgc has 1 control, this step is the SSA name created for that control.
Otherwise the step is a fresh SSA name, as in your patch.
 
(3) vect_set_loop_controls_directly stores this step somewhere for later
use, probably in LOOP_VINFO.  Let's use "S" to refer to this stored step.
 
(4) After the vect_set_loop_controls_directly call above, and outside
the "if" statement that now contains vect_set_loop_controls_directly,
check whether rgc->controls.length () > 1.  If so, use
vect_adjust_loop_lens_control to set the controls based on S.
 
Then the only caller of vect_adjust_loop_lens_control is
vect_set_loop_condition_partial_vectors.  And the starting
step for vect_adjust_loop_lens_control is always S.
 
This patch has well tested for single-rgroup and multiple-rgroup (SLP) and
passed all testcase in RISC-V port.
 
Also, pass tests for multiple-rgroup (non-SLP) tested on vec_pack_trunk.
 
Fix bugs of V14 patch:
FAIL: gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-3.c execution test
FAIL: gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-3.c execution test
FAIL: gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-3.c execution test
FAIL: gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-3.c execution test
FAIL: gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-3.c execution test
FAIL: gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-3.c execution test
FAIL: gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-3.c execution test
FAIL: gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-3.c execution test
 
This patch passed all testcases listed above.
 
gcc/ChangeLog:
 
        * tree-vect-loop-manip.cc (vect_set_loop_controls_directly): Add decrement IV support.
        (vect_adjust_loop_lens_control): Ditto.
        (vect_set_loop_condition_partial_vectors): Ditto.
        * tree-vect-loop.cc (_loop_vec_info::_loop_vec_info): New variables.
        * tree-vectorizer.h (LOOP_VINFO_USING_DECREMENTING_IV_P): New macro.
        (LOOP_VINFO_DECREMENTING_IV_STEP): Ditto.
 
gcc/testsuite/ChangeLog:
 
        * gcc.target/riscv/rvv/autovec/partial/multiple_rgroup-3.c: New test.
        * gcc.target/riscv/rvv/autovec/partial/multiple_rgroup-4.c: New test.
        * gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-3.c: New test.
        * gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-4.c: New test.
 
---
.../rvv/autovec/partial/multiple_rgroup-3.c   | 288 ++++++++++++++++++
.../rvv/autovec/partial/multiple_rgroup-4.c   |  75 +++++
.../autovec/partial/multiple_rgroup_run-3.c   |  36 +++
.../autovec/partial/multiple_rgroup_run-4.c   |  15 +
gcc/tree-vect-loop-manip.cc                   | 153 ++++++++++
gcc/tree-vect-loop.cc                         |  13 +
gcc/tree-vectorizer.h                         |  12 +
7 files changed, 592 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup-3.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup-4.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-3.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-4.c
 
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup-3.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup-3.c
new file mode 100644
index 00000000000..9579749c285
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup-3.c
@@ -0,0 +1,288 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param riscv-autovec-preference=fixed-vlmax" } */
+
+#include <stdint-gcc.h>
+
+void __attribute__ ((noinline, noclone))
+f0 (int8_t *__restrict x, int16_t *__restrict y, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 4, j += 8)
+    {
+      x[i + 0] += 1;
+      x[i + 1] += 2;
+      x[i + 2] += 3;
+      x[i + 3] += 4;
+      y[j + 0] += 1;
+      y[j + 1] += 2;
+      y[j + 2] += 3;
+      y[j + 3] += 4;
+      y[j + 4] += 5;
+      y[j + 5] += 6;
+      y[j + 6] += 7;
+      y[j + 7] += 8;
+    }
+}
+
+void __attribute__ ((optimize (0)))
+f0_init (int8_t *__restrict x, int8_t *__restrict x2, int16_t *__restrict y,
+ int16_t *__restrict y2, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 4, j += 8)
+    {
+      x[i + 0] = i % 120;
+      x[i + 1] = i % 78;
+      x[i + 2] = i % 55;
+      x[i + 3] = i % 27;
+      y[j + 0] = j % 33;
+      y[j + 1] = j % 44;
+      y[j + 2] = j % 66;
+      y[j + 3] = j % 88;
+      y[j + 4] = j % 99;
+      y[j + 5] = j % 39;
+      y[j + 6] = j % 49;
+      y[j + 7] = j % 101;
+
+      x2[i + 0] = i % 120;
+      x2[i + 1] = i % 78;
+      x2[i + 2] = i % 55;
+      x2[i + 3] = i % 27;
+      y2[j + 0] = j % 33;
+      y2[j + 1] = j % 44;
+      y2[j + 2] = j % 66;
+      y2[j + 3] = j % 88;
+      y2[j + 4] = j % 99;
+      y2[j + 5] = j % 39;
+      y2[j + 6] = j % 49;
+      y2[j + 7] = j % 101;
+    }
+}
+
+void __attribute__ ((optimize (0)))
+f0_golden (int8_t *__restrict x, int16_t *__restrict y, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 4, j += 8)
+    {
+      x[i + 0] += 1;
+      x[i + 1] += 2;
+      x[i + 2] += 3;
+      x[i + 3] += 4;
+      y[j + 0] += 1;
+      y[j + 1] += 2;
+      y[j + 2] += 3;
+      y[j + 3] += 4;
+      y[j + 4] += 5;
+      y[j + 5] += 6;
+      y[j + 6] += 7;
+      y[j + 7] += 8;
+    }
+}
+
+void __attribute__ ((optimize (0)))
+f0_check (int8_t *__restrict x, int8_t *__restrict x2, int16_t *__restrict y,
+   int16_t *__restrict y2, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 4, j += 8)
+    {
+      if (x[i + 0] != x2[i + 0])
+ __builtin_abort ();
+      if (x[i + 1] != x2[i + 1])
+ __builtin_abort ();
+      if (x[i + 2] != x2[i + 2])
+ __builtin_abort ();
+      if (x[i + 3] != x2[i + 3])
+ __builtin_abort ();
+      if (y[j + 0] != y2[j + 0])
+ __builtin_abort ();
+      if (y[j + 1] != y2[j + 1])
+ __builtin_abort ();
+      if (y[j + 2] != y2[j + 2])
+ __builtin_abort ();
+      if (y[j + 3] != y2[j + 3])
+ __builtin_abort ();
+      if (y[j + 4] != y2[j + 4])
+ __builtin_abort ();
+      if (y[j + 5] != y2[j + 5])
+ __builtin_abort ();
+      if (y[j + 6] != y2[j + 6])
+ __builtin_abort ();
+      if (y[j + 7] != y2[j + 7])
+ __builtin_abort ();
+    }
+}
+
+void __attribute__ ((noinline, noclone))
+f1 (int16_t *__restrict x, int32_t *__restrict y, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 2, j += 4)
+    {
+      x[i + 0] += 1;
+      x[i + 1] += 2;
+      y[j + 0] += 1;
+      y[j + 1] += 2;
+      y[j + 2] += 3;
+      y[j + 3] += 4;
+    }
+}
+
+void __attribute__ ((optimize (0)))
+f1_init (int16_t *__restrict x, int16_t *__restrict x2, int32_t *__restrict y,
+ int32_t *__restrict y2, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 2, j += 4)
+    {
+      x[i + 0] = i % 67;
+      x[i + 1] = i % 76;
+      y[j + 0] = j % 111;
+      y[j + 1] = j % 63;
+      y[j + 2] = j % 39;
+      y[j + 3] = j % 8;
+
+      x2[i + 0] = i % 67;
+      x2[i + 1] = i % 76;
+      y2[j + 0] = j % 111;
+      y2[j + 1] = j % 63;
+      y2[j + 2] = j % 39;
+      y2[j + 3] = j % 8;
+    }
+}
+
+void __attribute__ ((optimize (0)))
+f1_golden (int16_t *__restrict x, int32_t *__restrict y, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 2, j += 4)
+    {
+      x[i + 0] += 1;
+      x[i + 1] += 2;
+      y[j + 0] += 1;
+      y[j + 1] += 2;
+      y[j + 2] += 3;
+      y[j + 3] += 4;
+    }
+}
+
+void __attribute__ ((optimize (0)))
+f1_check (int16_t *__restrict x, int16_t *__restrict x2, int32_t *__restrict y,
+   int32_t *__restrict y2, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 2, j += 4)
+    {
+      if (x[i + 0] != x2[i + 0])
+ __builtin_abort ();
+      if (x[i + 1] != x2[i + 1])
+ __builtin_abort ();
+      if (y[j + 0] != y2[j + 0])
+ __builtin_abort ();
+      if (y[j + 1] != y2[j + 1])
+ __builtin_abort ();
+      if (y[j + 2] != y2[j + 2])
+ __builtin_abort ();
+      if (y[j + 3] != y2[j + 3])
+ __builtin_abort ();
+    }
+}
+
+void __attribute__ ((noinline, noclone))
+f2 (int32_t *__restrict x, int64_t *__restrict y, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 1, j += 2)
+    {
+      x[i + 0] += 1;
+      y[j + 0] += 1;
+      y[j + 1] += 2;
+    }
+}
+
+void __attribute__ ((optimize (0)))
+f2_init (int32_t *__restrict x, int32_t *__restrict x2, int64_t *__restrict y,
+ int64_t *__restrict y2, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 1, j += 2)
+    {
+      x[i + 0] = i % 79;
+      y[j + 0] = j % 83;
+      y[j + 1] = j % 100;
+
+      x2[i + 0] = i % 79;
+      y2[j + 0] = j % 83;
+      y2[j + 1] = j % 100;
+    }
+}
+
+void __attribute__ ((optimize (0)))
+f2_golden (int32_t *__restrict x, int64_t *__restrict y, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 1, j += 2)
+    {
+      x[i + 0] += 1;
+      y[j + 0] += 1;
+      y[j + 1] += 2;
+    }
+}
+
+void __attribute__ ((noinline, noclone))
+f2_check (int32_t *__restrict x, int32_t *__restrict x2, int64_t *__restrict y,
+   int64_t *__restrict y2, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 1, j += 2)
+    {
+      if (x[i + 0] != x2[i + 0])
+ __builtin_abort ();
+      if (y[j + 0] != y2[j + 0])
+ __builtin_abort ();
+      if (y[j + 1] != y2[j + 1])
+ __builtin_abort ();
+    }
+}
+
+void __attribute__ ((noinline, noclone))
+f3 (int8_t *__restrict x, int64_t *__restrict y, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 1, j += 2)
+    {
+      x[i + 0] += 1;
+      y[j + 0] += 1;
+      y[j + 1] += 2;
+    }
+}
+
+void __attribute__ ((noinline, noclone))
+f3_init (int8_t *__restrict x, int8_t *__restrict x2, int64_t *__restrict y,
+    int64_t *__restrict y2, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 1, j += 2)
+    {
+      x[i + 0] = i % 22;
+      y[j + 0] = i % 12;
+      y[j + 1] = i % 21;
+
+      x2[i + 0] = i % 22;
+      y2[j + 0] = i % 12;
+      y2[j + 1] = i % 21;
+    }
+}
+
+void __attribute__ ((optimize (0)))
+f3_golden (int8_t *__restrict x, int64_t *__restrict y, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 1, j += 2)
+    {
+      x[i + 0] += 1;
+      y[j + 0] += 1;
+      y[j + 1] += 2;
+    }
+}
+
+void __attribute__ ((noinline, noclone))
+f3_check (int8_t *__restrict x, int8_t *__restrict x2, int64_t *__restrict y,
+   int64_t *__restrict y2, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 1, j += 2)
+    {
+      if (x[i + 0] != x2[i + 0])
+ __builtin_abort ();
+      if (y[j + 0] != y2[j + 0])
+ __builtin_abort ();
+      if (y[j + 1] != y2[j + 1])
+ __builtin_abort ();
+    }
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup-4.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup-4.c
new file mode 100644
index 00000000000..e87961e49ac
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup-4.c
@@ -0,0 +1,75 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=rv32gcv -mabi=ilp32d --param riscv-autovec-preference=fixed-vlmax" } */
+
+#include <stdint-gcc.h>
+
+void __attribute__ ((noinline, noclone))
+f (uint64_t *__restrict x, uint16_t *__restrict y, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 2, j += 4)
+    {
+      x[i + 0] += 1;
+      x[i + 1] += 2;
+      y[j + 0] += 1;
+      y[j + 1] += 2;
+      y[j + 2] += 3;
+      y[j + 3] += 4;
+    }
+}
+
+void __attribute__ ((optimize (0)))
+f_init (uint64_t *__restrict x, uint64_t *__restrict x2, uint16_t *__restrict y,
+ uint16_t *__restrict y2, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 2, j += 4)
+    {
+      x[i + 0] = i * 897 + 189;
+      x[i + 1] = i * 79 + 55963;
+      y[j + 0] = j * 18 + 78642;
+      y[j + 1] = j * 9 + 8634;
+      y[j + 2] = j * 78 + 2588;
+      y[j + 3] = j * 38 + 8932;
+  
+      x2[i + 0] = i * 897 + 189;
+      x2[i + 1] = i * 79 + 55963;
+      y2[j + 0] = j * 18 + 78642;
+      y2[j + 1] = j * 9 + 8634;
+      y2[j + 2] = j * 78 + 2588;
+      y2[j + 3] = j * 38 + 8932;
+    }
+}
+
+void __attribute__ ((optimize (0)))
+f_golden (uint64_t *__restrict x, uint16_t *__restrict y, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 2, j += 4)
+    {
+      x[i + 0] += 1;
+      x[i + 1] += 2;
+      y[j + 0] += 1;
+      y[j + 1] += 2;
+      y[j + 2] += 3;
+      y[j + 3] += 4;
+    }
+}
+
+void __attribute__ ((optimize (0)))
+f_check (uint64_t *__restrict x, uint64_t *__restrict x2,
+ uint16_t *__restrict y, uint16_t *__restrict y2, int n)
+{
+  for (int i = 0, j = 0; i < n; i += 2, j += 4)
+    {
+      if (x[i + 0] != x2[i + 0])
+ __builtin_abort ();
+      if (x[i + 1] != x2[i + 1])
+ __builtin_abort ();
+      if (y[j + 0] != y2[j + 0])
+ __builtin_abort ();
+      if (y[j + 1] != y2[j + 1])
+ __builtin_abort ();
+      if (y[j + 2] != y2[j + 2])
+ __builtin_abort ();
+      if (y[j + 3] != y2[j + 3])
+ __builtin_abort ();
+    }
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-3.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-3.c
new file mode 100644
index 00000000000..b786738ce99
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-3.c
@@ -0,0 +1,36 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param riscv-autovec-preference=fixed-vlmax" } */
+
+#include "multiple_rgroup-3.c"
+
+int __attribute__ ((optimize (0))) main (void)
+{
+  int8_t f0_x[3108], f0_x2[3108];
+  int16_t f0_y[6216], f0_y2[6216];
+  f0_init (f0_x, f0_x2, f0_y, f0_y2, 3108);
+  f0 (f0_x, f0_y, 3108);
+  f0_golden (f0_x2, f0_y2, 3108);
+  f0_check (f0_x, f0_x2, f0_y, f0_y2, 3108);
+
+  int16_t f1_x[1998], f1_x2[1998];
+  int32_t f1_y[3996], f1_y2[3996];
+  f1_init (f1_x, f1_x2, f1_y, f1_y2, 1998);
+  f1 (f1_x, f1_y, 1998);
+  f1_golden (f1_x2, f1_y2, 1998);
+  f1_check (f1_x, f1_x2, f1_y, f1_y2, 1998);
+
+  int32_t f2_x[2023], f2_x2[2023];
+  int64_t f2_y[4046], f2_y2[4046];
+  f2_init (f2_x, f2_x2, f2_y, f2_y2, 2023);
+  f2 (f2_x, f2_y, 2023);
+  f2_golden (f2_x2, f2_y2, 2023);
+  f2_check (f2_x, f2_x2, f2_y, f2_y2, 2023);
+
+  int8_t f3_x[3203], f3_x2[3203];
+  int64_t f3_y[6406], f3_y2[6406];
+  f3_init (f3_x, f3_x2, f3_y, f3_y2, 3203);
+  f3 (f3_x, f3_y, 3203);
+  f3_golden (f3_x2, f3_y2, 3203);
+  f3_check (f3_x, f3_x2, f3_y, f3_y2, 3203);
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-4.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-4.c
new file mode 100644
index 00000000000..7751384183e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/multiple_rgroup_run-4.c
@@ -0,0 +1,15 @@
+/* { dg-do run { target { riscv_vector } } } */
+/* { dg-additional-options "--param riscv-autovec-preference=fixed-vlmax" } */
+
+#include "multiple_rgroup-4.c"
+
+int __attribute__ ((optimize (0))) main (void)
+{
+  uint64_t f_x[3108], f_x2[3108];
+  uint16_t f_y[6216], f_y2[6216];
+  f_init (f_x, f_x2, f_y, f_y2, 3108);
+  f (f_x, f_y, 3108);
+  f_golden (f_x2, f_y2, 3108);
+  f_check (f_x, f_x2, f_y, f_y2, 3108);
+  return 0;
+}
diff --git a/gcc/tree-vect-loop-manip.cc b/gcc/tree-vect-loop-manip.cc
index ff6159e08d5..f9d92ced982 100644
--- a/gcc/tree-vect-loop-manip.cc
+++ b/gcc/tree-vect-loop-manip.cc
@@ -468,6 +468,38 @@ vect_set_loop_controls_directly (class loop *loop, loop_vec_info loop_vinfo,
   gimple_stmt_iterator incr_gsi;
   bool insert_after;
   standard_iv_increment_position (loop, &incr_gsi, &insert_after);
+  if (LOOP_VINFO_USING_DECREMENTING_IV_P (loop_vinfo))
+    {
+      /* single rgroup:
+ ...
+ _10 = (unsigned long) count_12(D);
+ ...
+ # ivtmp_9 = PHI <ivtmp_35(6), _10(5)>
+ _36 = MIN_EXPR <ivtmp_9, POLY_INT_CST [4, 4]>;
+ ...
+ vect__4.8_28 = .LEN_LOAD (_17, 32B, _36, 0);
+ ...
+ ivtmp_35 = ivtmp_9 - _36;
+ ...
+ if (ivtmp_35 != 0)
+    goto <bb 4>; [83.33%]
+ else
+    goto <bb 5>; [16.67%]
+      */
+      nitems_total = gimple_convert (preheader_seq, iv_type, nitems_total);
+      tree step = rgc->controls.length () == 1 ? rgc->controls[0]
+        : make_ssa_name (iv_type);
+      /* 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));
+      LOOP_VINFO_DECREMENTING_IV_STEP (loop_vinfo) = step;
+      return index_after_incr;
+    }
+
+  /* Create increment IV.  */
   create_iv (build_int_cst (iv_type, 0), PLUS_EXPR, nitems_step, NULL_TREE,
     loop, &incr_gsi, insert_after, &index_before_incr,
     &index_after_incr);
@@ -683,6 +715,63 @@ vect_set_loop_controls_directly (class loop *loop, loop_vec_info loop_vinfo,
   return next_ctrl;
}
+/* Try to use adjust loop lens for multiple-rgroups.
+
+     _36 = MIN_EXPR <ivtmp_34, VF>;
+
+     First length (MIN (X, VF/N)):
+       loop_len_15 = MIN_EXPR <_36, VF/N>;
+
+     Second length:
+       tmp = _36 - loop_len_15;
+       loop_len_16 = MIN (tmp, VF/N);
+
+     Third length:
+       tmp2 = tmp - loop_len_16;
+       loop_len_17 = MIN (tmp2, VF/N);
+
+     Last length:
+       loop_len_18 = tmp2 - loop_len_17;
+*/
+
+static void
+vect_adjust_loop_lens_control (tree iv_type, gimple_seq *seq,
+        rgroup_controls *dest_rgm, tree step)
+{
+  tree ctrl_type = dest_rgm->type;
+  poly_uint64 nitems_per_ctrl
+    = TYPE_VECTOR_SUBPARTS (ctrl_type) * dest_rgm->factor;
+  tree length_limit = build_int_cst (iv_type, nitems_per_ctrl);
+
+  for (unsigned int i = 0; i < dest_rgm->controls.length (); ++i)
+    {
+      tree ctrl = dest_rgm->controls[i];
+      if (i == 0)
+ {
+   /* First iteration: MIN (X, VF/N) capped to the range [0, VF/N].  */
+   gassign *assign
+     = gimple_build_assign (ctrl, MIN_EXPR, step, length_limit);
+   gimple_seq_add_stmt (seq, assign);
+ }
+      else if (i == dest_rgm->controls.length () - 1)
+ {
+   /* Last iteration: Remain capped to the range [0, VF/N].  */
+   gassign *assign = gimple_build_assign (ctrl, MINUS_EXPR, step,
+ dest_rgm->controls[i - 1]);
+   gimple_seq_add_stmt (seq, assign);
+ }
+      else
+ {
+   /* (MIN (remain, VF*I/N)) capped to the range [0, VF/N].  */
+   step = gimple_build (seq, MINUS_EXPR, iv_type, step,
+        dest_rgm->controls[i - 1]);
+   gassign *assign
+     = gimple_build_assign (ctrl, MIN_EXPR, step, length_limit);
+   gimple_seq_add_stmt (seq, assign);
+ }
+    }
+}
+
/* Set up the iteration condition and rgroup controls for LOOP, given
    that LOOP_VINFO_USING_PARTIAL_VECTORS_P is true for the vectorized
    loop.  LOOP_VINFO describes the vectorization of LOOP.  NITERS is
@@ -764,6 +853,70 @@ vect_set_loop_condition_partial_vectors (class loop *loop,
     loop_cond_gsi, rgc,
     niters, niters_skip,
     might_wrap_p);
+
+ /* Decrement IV only run vect_set_loop_controls_directly once.  */
+ if (LOOP_VINFO_USING_DECREMENTING_IV_P (loop_vinfo)
+     && rgc->controls.length () > 1)
+   {
+     /*
+        - Multiple rgroup (SLP):
+ ...
+ _38 = (unsigned long) bnd.7_29;
+ _39 = _38 * 2;
+ ...
+ # ivtmp_41 = PHI <ivtmp_42(6), _39(5)>
+ ...
+ _43 = MIN_EXPR <ivtmp_41, 32>;
+ loop_len_26 = MIN_EXPR <_43, 16>;
+ loop_len_25 = _43 - loop_len_26;
+ ...
+ .LEN_STORE (_6, 8B, loop_len_26, ...);
+ ...
+ .LEN_STORE (_25, 8B, loop_len_25, ...);
+ _33 = loop_len_26 / 2;
+ ...
+ .LEN_STORE (_8, 16B, _33, ...);
+ _36 = loop_len_25 / 2;
+ ...
+ .LEN_STORE (_15, 16B, _36, ...);
+ ivtmp_42 = ivtmp_41 - _43;
+ ...
+
+        - Multiple rgroup (non-SLP):
+ ...
+ _38 = (unsigned long) n_12(D);
+ ...
+ # ivtmp_38 = PHI <ivtmp_39(3), 100(2)>
+ ...
+ loop_len_38 = MIN_EXPR <ivtmp_41, POLY_INT_CST [8, 8]>;
+ _43 = MIN_EXPR <ivtmp_44, POLY_INT_CST [8, 8]>;
+ loop_len_24 = MIN_EXPR <_43, POLY_INT_CST [2, 2]>;
+ _46 = _43 - loop_len_24;
+ loop_len_23 = MIN_EXPR <_46, POLY_INT_CST [2, 2]>;
+ _47 = _46 - loop_len_23;
+ loop_len_22 = MIN_EXPR <_47, POLY_INT_CST [2, 2]>;
+ loop_len_21 = _47 - loop_len_22;
+ ...
+ vect__4.8_17 = .LEN_LOAD (_6, 64B, loop_len_24, 0);
+ ...
+ vect__4.9_9 = .LEN_LOAD (_49, 64B, loop_len_23, 0);
+ ...
+ vect__4.10_30 = .LEN_LOAD (_52, 64B, loop_len_22, 0);
+ ...
+ vect__4.11_32 = .LEN_LOAD (_55, 64B, loop_len_21, 0);
+ vect__7.13_31 = VEC_PACK_TRUNC_EXPR <...>,
+ vect__7.13_32 = VEC_PACK_TRUNC_EXPR <...>;
+ vect__7.12_33 = VEC_PACK_TRUNC_EXPR <...>;
+ ...
+ .LEN_STORE (_14, 16B, _40, vect__7.12_33, 0);
+ ivtmp_39 = ivtmp_38 - _40;
+ ...
+     */
+     tree iv_type = LOOP_VINFO_RGROUP_IV_TYPE (loop_vinfo);
+     tree step = LOOP_VINFO_DECREMENTING_IV_STEP (loop_vinfo);
+     gcc_assert (step);
+     vect_adjust_loop_lens_control (iv_type, &header_seq, rgc, step);
+   }
       }
   /* Emit all accumulated statements.  */
diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
index cf10132b0bf..456f50fa7cc 100644
--- a/gcc/tree-vect-loop.cc
+++ b/gcc/tree-vect-loop.cc
@@ -973,6 +973,8 @@ _loop_vec_info::_loop_vec_info (class loop *loop_in, vec_info_shared *shared)
     vectorizable (false),
     can_use_partial_vectors_p (param_vect_partial_vector_usage != 0),
     using_partial_vectors_p (false),
+    using_decrementing_iv_p (false),
+    decrementing_iv_step (NULL_TREE),
     epil_using_partial_vectors_p (false),
     partial_load_store_bias (0),
     peeling_for_gaps (false),
@@ -2725,6 +2727,17 @@ start_over:
       && !vect_verify_loop_lens (loop_vinfo))
     LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P (loop_vinfo) = false;
+  /* If we're vectorizing an loop that uses length "controls" and
+     can iterate more than once, we apply decrementing IV approach
+     in loop control.  */
+  if (LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P (loop_vinfo)
+      && !LOOP_VINFO_LENS (loop_vinfo).is_empty ()
+      && LOOP_VINFO_PARTIAL_LOAD_STORE_BIAS (loop_vinfo) == 0
+      && !(LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
+    && known_le (LOOP_VINFO_INT_NITERS (loop_vinfo),
+ LOOP_VINFO_VECT_FACTOR (loop_vinfo))))
+    LOOP_VINFO_USING_DECREMENTING_IV_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-vectorizer.h b/gcc/tree-vectorizer.h
index 02d2ad6fba1..7ed079f543a 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -818,6 +818,16 @@ public:
      the vector loop can handle fewer than VF scalars.  */
   bool using_partial_vectors_p;
+  /* True if we've decided to use a decrementing loop control IV that counts
+     scalars. This can be done for any loop that:
+
+ (a) uses length "controls"; and
+ (b) can iterate more than once.  */
+  bool using_decrementing_iv_p;
+
+  /* The variable amount step for decrement IV.  */
+  tree decrementing_iv_step;
+
   /* True if we've decided to use partially-populated vectors for the
      epilogue of loop.  */
   bool epil_using_partial_vectors_p;
@@ -890,6 +900,8 @@ public:
#define LOOP_VINFO_VECTORIZABLE_P(L)       (L)->vectorizable
#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_DECREMENTING_IV_STEP(L) (L)->decrementing_iv_step
#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
-- 
2.36.3