This patch fixes following FAILs in zvl1024b of both RV32/RV64:

FAIL: gcc.c-torture/execute/990128-1.c   -O2  execution test
FAIL: gcc.c-torture/execute/990128-1.c   -O2 -flto -fno-use-linker-plugin 
-flto-partition=none  execution test
FAIL: gcc.c-torture/execute/990128-1.c   -O2 -flto -fuse-linker-plugin 
-fno-fat-lto-objects  execution test
FAIL: gcc.c-torture/execute/990128-1.c   -O3 -fomit-frame-pointer 
-funroll-loops -fpeel-loops -ftracer -finline-functions  execution test
FAIL: gcc.c-torture/execute/990128-1.c   -O3 -g  execution test
FAIL: gcc.dg/torture/pr58955-2.c   -O3 -fomit-frame-pointer -funroll-loops 
-fpeel-loops -ftracer -finline-functions  execution test

The root case can be simpliy described in this following small case:

https://godbolt.org/z/7GaxbEGzG

#include "riscv_vector.h"

typedef int64_t v1024b __attribute__ ((vector_size (128)));

void foo (void *out, void *in, int64_t a, int64_t b)
{
  v1024b v = {a,a,a,a,a,a,a,a,a,a,a,a,a,a,a,a};
  v1024b v2 = {b,b,b,b,b,b,b,b,b,b,b,b,b,b,b,b};
  v1024b index = *(v1024b*)in;
  v1024b v3 = __builtin_shuffle (v, v2, index);
  __riscv_vse64_v_i64m1 (out, (vint64m1_t)v3, 10);
}

Incorrect ASM:

foo:
        li      a5,31
        vsetivli        zero,10,e64,m1,ta,mu
        vmv.v.x v2,a5
        vl1re64.v       v1,0(a1)
        vmv.v.x v4,a2
        vand.vv v1,v1,v2
        vmv.v.x v3,a3
        vmsgeu.vi       v0,v1,16
        vrgather.vv     v2,v4,v1       --> AVL = VLMAX according to codes.
        vadd.vi v1,v1,-16
        vrgather.vv     v2,v3,v1,v0.t  --> AVL = VLMAX according to codes.
        vse64.v v2,0(a0)               --> AVL = 10 according to codes.
        ret

For vrgather dest, source, index instruction, when index may has the value > 
the following store AVL
that is index value > 10.  In this situation, the codes above will end up with:

The source vector of vrgather has undefined value on index >= AVL (which is 10 
in this case).

So disable AVL propagation for vrgather instruction.


        PR target/112599

gcc/ChangeLog:

        * config/riscv/riscv-avlprop.cc (alv_can_be_propagated_p): New function.
        (vlmax_ta_p): Disable vrgather AVL propagation.

gcc/testsuite/ChangeLog:

        * gcc.target/riscv/rvv/autovec/pr112599-1.c: New test.

---
 gcc/config/riscv/riscv-avlprop.cc               | 13 ++++++++++++-
 .../gcc.target/riscv/rvv/autovec/pr112599-1.c   | 17 +++++++++++++++++
 2 files changed, 29 insertions(+), 1 deletion(-)
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/pr112599-1.c

diff --git a/gcc/config/riscv/riscv-avlprop.cc 
b/gcc/config/riscv/riscv-avlprop.cc
index 1f6ba405342..68b9af07d99 100644
--- a/gcc/config/riscv/riscv-avlprop.cc
+++ b/gcc/config/riscv/riscv-avlprop.cc
@@ -104,10 +104,21 @@ avlprop_type_to_str (enum avlprop_type type)
     }
 }
 
+/* Return true if the AVL of the INSN can be propagated.  */
+static bool
+alv_can_be_propagated_p (rtx_insn *rinsn)
+{
+  /* The index of "vrgather dest, source, index" may pick up the
+     element which has index >= AVL, so we can't strip the elements
+     that has index >= AVL of source register.  */
+  return get_attr_type (rinsn) != TYPE_VGATHER;
+}
+
 static bool
 vlmax_ta_p (rtx_insn *rinsn)
 {
-  return vlmax_avl_type_p (rinsn) && tail_agnostic_p (rinsn);
+  return vlmax_avl_type_p (rinsn) && tail_agnostic_p (rinsn)
+        && alv_can_be_propagated_p (rinsn);
 }
 
 static machine_mode
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr112599-1.c 
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr112599-1.c
new file mode 100644
index 00000000000..911b6922b4a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr112599-1.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvfh_zfh_zvl1024b -mabi=lp64d -O3 
--param=riscv-autovec-preference=fixed-vlmax" } */
+
+#include "riscv_vector.h"
+
+typedef int64_t v1024b __attribute__ ((vector_size (128)));
+
+void foo (void *out, void *in, int64_t a, int64_t b)
+{
+  v1024b v = {a,a,a,a,a,a,a,a,a,a,a,a,a,a,a,a};
+  v1024b v2 = {b,b,b,b,b,b,b,b,b,b,b,b,b,b,b,b};
+  v1024b index = *(v1024b*)in;
+  v1024b v3 = __builtin_shuffle (v, v2, index);
+  __riscv_vse64_v_i64m1 (out, (vint64m1_t)v3, 10);
+}
+
+/* { dg-final { scan-assembler {vsetivli\s+zero,\s*16} } } */
-- 
2.36.3

Reply via email to