https://gcc.gnu.org/g:e5e9e50fc6816713d012f1d96ae308a0946d5a14

commit r15-6892-ge5e9e50fc6816713d012f1d96ae308a0946d5a14
Author: Robin Dapp <rd...@ventanamicro.com>
Date:   Thu Jan 9 20:45:10 2025 +0100

    RISC-V: Fix vsetvl compatibility predicate [PR118154].
    
    In PR118154 we emit strided stores but the first of those does not
    always have the proper VTYPE.  That's because we erroneously delete
    a necessary vsetvl.
    
    In order to determine whether to elide
    
    (1)
          Expr[7]: VALID (insn 116, bb 17)
            Demand fields: demand_ratio_and_ge_sew demand_avl
            SEW=8, VLMUL=mf2, RATIO=16, MAX_SEW=64
            TAIL_POLICY=agnostic, MASK_POLICY=agnostic
            AVL=(reg:DI 0 zero)
    
    when e.g.
    
    (2)
          Expr[3]: VALID (insn 360, bb 15)
            Demand fields: demand_sew_lmul demand_avl
            SEW=64, VLMUL=m1, RATIO=64, MAX_SEW=64
            TAIL_POLICY=agnostic, MASK_POLICY=agnostic
            AVL=(reg:DI 0 zero)
            VL=(reg:DI 13 a3 [345])
    
    is already available, we use
    sew_ge_and_prev_sew_le_next_max_sew_and_next_ratio_valid_for_prev_sew_p.
    
    (1) requires RATIO = SEW/LMUL = 16 and an SEW >= 8.  (2) has ratio = 64,
    though, so we cannot directly elide (1).
    
    This patch uses ratio_eq_p instead of next_ratio_valid_for_prev_sew_p.
    
            PR target/118154
    
    gcc/ChangeLog:
    
            * config/riscv/riscv-vsetvl.cc (MAX_LMUL): New define.
            (pre_vsetvl::earliest_fuse_vsetvl_info): Use.
            (pre_vsetvl::pre_global_vsetvl_info): New predicate with equal
            ratio.
            * config/riscv/riscv-vsetvl.def: Use.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.target/riscv/rvv/autovec/pr118154-1.c: New test.
            * gcc.target/riscv/rvv/autovec/pr118154-2.c: New test.

Diff:
---
 gcc/config/riscv/riscv-vsetvl.cc                   | 14 +++++++---
 gcc/config/riscv/riscv-vsetvl.def                  |  4 +--
 .../gcc.target/riscv/rvv/autovec/pr118154-1.c      | 23 ++++++++++++++++
 .../gcc.target/riscv/rvv/autovec/pr118154-2.c      | 31 ++++++++++++++++++++++
 4 files changed, 67 insertions(+), 5 deletions(-)

diff --git a/gcc/config/riscv/riscv-vsetvl.cc b/gcc/config/riscv/riscv-vsetvl.cc
index e9de21787dda..a4016beebc0c 100644
--- a/gcc/config/riscv/riscv-vsetvl.cc
+++ b/gcc/config/riscv/riscv-vsetvl.cc
@@ -223,6 +223,8 @@ enum emit_type
   EMIT_AFTER,
 };
 
+static const int MAX_LMUL = 8;
+
 /* dump helper functions */
 static const char *
 vlmul_to_str (vlmul_type vlmul)
@@ -1445,14 +1447,13 @@ private:
   inline bool prev_ratio_valid_for_next_sew_p (const vsetvl_info &prev,
                                               const vsetvl_info &next)
   {
-    return prev.get_ratio () >= (next.get_sew () / 8);
+    return prev.get_ratio () >= (next.get_sew () / MAX_LMUL);
   }
   inline bool next_ratio_valid_for_prev_sew_p (const vsetvl_info &prev,
                                               const vsetvl_info &next)
   {
-    return next.get_ratio () >= (prev.get_sew () / 8);
+    return next.get_ratio () >= (prev.get_sew () / MAX_LMUL);
   }
-
   inline bool sew_ge_and_ratio_eq_p (const vsetvl_info &prev,
                                     const vsetvl_info &next)
   {
@@ -1470,6 +1471,13 @@ private:
     return sew_ge_p (prev, next) && prev_sew_le_next_max_sew_p (prev, next)
           && next_ratio_valid_for_prev_sew_p (prev, next);
   }
+  inline bool
+  sew_ge_and_prev_sew_le_next_max_sew_and_ratio_eq_p (
+    const vsetvl_info &prev, const vsetvl_info &next)
+  {
+    return sew_ge_p (prev, next) && prev_sew_le_next_max_sew_p (prev, next)
+          && ratio_eq_p (prev, next);
+  }
   inline bool sew_le_and_next_sew_le_prev_max_sew_p (const vsetvl_info &prev,
                                                     const vsetvl_info &next)
   {
diff --git a/gcc/config/riscv/riscv-vsetvl.def 
b/gcc/config/riscv/riscv-vsetvl.def
index 2dfff71d987f..d7a5ada772d0 100644
--- a/gcc/config/riscv/riscv-vsetvl.def
+++ b/gcc/config/riscv/riscv-vsetvl.def
@@ -53,8 +53,8 @@ DEF_SEW_LMUL_RULE (sew_lmul, ge_sew, sew_lmul,
                   sew_ge_and_prev_sew_le_next_max_sew_p, nop)
 DEF_SEW_LMUL_RULE (
   sew_lmul, ratio_and_ge_sew, sew_lmul,
-  sew_ge_and_prev_sew_le_next_max_sew_and_next_ratio_valid_for_prev_sew_p,
-  sew_ge_and_prev_sew_le_next_max_sew_and_next_ratio_valid_for_prev_sew_p, nop)
+  sew_ge_and_prev_sew_le_next_max_sew_and_ratio_eq_p,
+  sew_ge_and_prev_sew_le_next_max_sew_and_ratio_eq_p, nop)
 
 DEF_SEW_LMUL_RULE (ratio_only, sew_lmul, sew_lmul, ratio_eq_p, always_false,
                   use_next_sew_lmul)
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr118154-1.c 
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr118154-1.c
new file mode 100644
index 000000000000..55386568a5f7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr118154-1.c
@@ -0,0 +1,23 @@
+/* { dg-do run } */
+/* { dg-require-effective-target riscv_v_ok } */
+/* { dg-add-options riscv_v } */
+/* { dg-additional-options "-std=gnu99 -Wno-pedantic" } */
+
+long a;
+char b;
+char c[22][484];
+int main() {
+  for (int e = 4; e < 33; e++) {
+    for (int f = 0; f < 3; f++)
+      for (int g = 0; g < 18; g++) {
+        c[f][g * 22] = 1;
+        a = ({ a > 1 ? a : 1; });
+      }
+    for (int i = 0; i < 33; i++)
+      for (int h = 0; h < 6; h++)
+        for (int j = 0; j < 17; j++)
+          b = ({ b > 17 ? b : 17; });
+  }
+  if (c[1][44] != 1)
+    __builtin_abort ();
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr118154-2.c 
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr118154-2.c
new file mode 100644
index 000000000000..4172f2929948
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr118154-2.c
@@ -0,0 +1,31 @@
+/* { dg-do run } */
+/* { dg-require-effective-target riscv_v_ok } */
+/* { dg-add-options riscv_v } */
+/* { dg-additional-options "-std=gnu99 -Wno-pedantic" } */
+
+long a;
+signed char b;
+long long d;
+signed char c[22][22][484];
+void m(long long *l, int n) { *l ^= n + (*l >> 2); }
+int main() {
+  signed char l = 35;
+  for (signed char f = 4; f; f++) {
+    for (signed g = 0; g < 022; g += 4)
+      for (signed char h = 0; h < 022; h++) {
+        c[9][g][h * 22 + h] = l;
+        a = ({ a > 4095 ? a : 4095; });
+      }
+    for (int i = 0; i < 22; i += 3)
+      for (signed char j = 1; j; j++)
+        for (signed char k = 0; k < 022; k++)
+          b = ({ b > 19 ? b : 19; });
+  }
+  for (long f = 0; f < 22; ++f)
+    for (long g = 0; g < 22; ++g)
+      for (long h = 0; h < 22; ++h)
+        for (long i = 0; i < 22; ++i)
+          m(&d, c[f][g][h * 2 + i]);
+  if (d != 38)
+    __builtin_abort ();
+}

Reply via email to