In PR115703 we fuse two vsetvls:
Fuse curr info since prev info compatible with it:
prev_info: VALID (insn 438, bb 2)
Demand fields: demand_ge_sew demand_non_zero_avl
SEW=32, VLMUL=m1, RATIO=32, MAX_SEW=64
TAIL_POLICY=agnostic, MASK_POLICY=agnostic
AVL=(reg:DI 0 zero)
VL=(reg:DI 9 s1 [312])
curr_info: VALID (insn 92, bb 20)
Demand fields: demand_ratio_and_ge_sew demand_avl
SEW=64, VLMUL=m1, RATIO=64, MAX_SEW=64
TAIL_POLICY=agnostic, MASK_POLICY=agnostic
AVL=(const_int 4 [0x4])
VL=(nil)
prev_info after fused: VALID (insn 438, bb 2)
Demand fields: demand_ratio_and_ge_sew demand_avl
SEW=64, VLMUL=mf2, RATIO=64, MAX_SEW=64
TAIL_POLICY=agnostic, MASK_POLICY=agnostic
AVL=(const_int 4 [0x4])
VL=(nil).
The result is vsetvl zero, zero, e64, mf2, ta, ma. The previous vsetvl
set vl = 4 but here we wrongly set it to vl = 2. As all the following
vsetvls only ever change the ratio we never recover.
The issue is quite difficult to trigger because we can often
deduce the value of d at runtime. Then very check for the value of
d will be optimized away.
The last known bad commit is
r15-3458-g5326306e7d9d36. With that commit
the output is wrong but -fno-schedule-insns makes it correct. From the
next commit on the issue is latent. I still added the PR's test as scan
and run check even if they don't trigger right now. Not sure if the
run test will ever fail but well. I verified that the
patch fixes the issue when applied on top of
r15-3458-g5326306e7d9d36.
PR target/115703
gcc/ChangeLog:
* config/riscv/riscv-vsetvl.cc: Use max_sew for calculating the
new LMUL.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/autovec/pr115703-run.c: New test.
* gcc.target/riscv/rvv/autovec/pr115703.c: New test.
inline void use_max_sew_and_lmul_with_next_ratio (vsetvl_info &prev,
const vsetvl_info &next)
{
- prev.set_vlmul (calculate_vlmul (prev.get_sew (), next.get_ratio ()));
+ int max_sew = MAX (prev.get_sew (), next.get_sew ());
+ prev.set_vlmul (calculate_vlmul (max_sew, next.get_ratio ()));
use_max_sew (prev, next);
prev.set_ratio (next.get_ratio ());
}
--- /dev/null
+/* { dg-do run } */
+/* { dg-require-effective-target rvv_zvl256b_ok } */
+/* { dg-options "-O3 -march=rv64gcv_zvl256b -mabi=lp64d -fwhole-program -fwrapv" } */
+
+int a, i;
+unsigned long b;
+unsigned c, f;
+long long d = 1;
+short e, m;
+long g, h;
+
+__attribute__ ((noipa))
+void check (unsigned long long x)
+{
+ if (x != 13667643351234938049ull)
+ __builtin_abort ();
+}
+
+int main() {
+ for (int q = 0; q < 2; q += 1) {
+ for (short r = 0; r < 2; r += 1)
+ for (char s = 0; s < 6; s++)
+ for (short t = 0; t < 011; t += 12081 - 12080)
+ for (short u = 0; u < 11; u++) {
+ a = ({ a > 1 ? a : 1; });
+ b = ({ b > 5 ? b : 5; });
+ for (short j = 0; j < 2; j = 2080)
+ c = ({ c > 030 ? c : 030; });
+ for (short k = 0; k < 2; k += 2080)
+ d *= 7;
+ e *= 10807;
+ f = ({ f > 3 ? f : 3; });
+ }
+ for (int l = 0; l < 21; l += 1)
+ for (int n = 0; n < 16; n++) {
+ g = ({ m ? g : m; });
+ for (char o = 0; o < 7; o += 1)
+ h *= 3;
+ i = ({ i < 0 ? i : 0; });
+ }
+ }
+
+ check (d);
+}
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=rv64gcv_zvl256b -mabi=lp64d -fwhole-program -fwrapv" } */
+
+int a, i;
+unsigned long b;
+unsigned c, f;
+long long d = 1;
+short e, m;
+long g, h;
+
+int main() {
+ for (int q = 0; q < 2; q += 1) {
+ for (short r = 0; r < 2; r += 1)
+ for (char s = 0; s < 6; s++)
+ for (short t = 0; t < 011; t += 12081 - 12080)
+ for (short u = 0; u < 11; u++) {
+ a = ({ a > 1 ? a : 1; });
+ b = ({ b > 5 ? b : 5; });
+ for (short j = 0; j < 2; j = 2080)
+ c = ({ c > 030 ? c : 030; });
+ for (short k = 0; k < 2; k += 2080)
+ d *= 7;
+ e *= 10807;
+ f = ({ f > 3 ? f : 3; });
+ }
+ for (int l = 0; l < 21; l += 1)
+ for (int n = 0; n < 16; n++) {
+ g = ({ m ? g : m; });
+ for (char o = 0; o < 7; o += 1)
+ h *= 3;
+ i = ({ i < 0 ? i : 0; });
+ }
+ }
+
+ __builtin_printf ("%llu\n", d);
+}
+
+/* { dg-final { scan-assembler-not "vset.*e64,mf2" } } */