From: Pan Li <pan2.li@intel.com>
This patch fixes the following FAIL:
Running target
riscv-sim/-march=rv64gcv/-mabi=lp64d/-mcmodel=medlow/--param=riscv-autovec-lmul=m8
FAIL: gcc.dg/vect/fast-math-vect-complex-3.c execution test
The root cause is we generate incorrect codegen for (const_poly_int:DI
[549755813888, 549755813888])
Before this patch:
li a7,0
vmv.v.x v0,a7
After this patch:
csrr a2,vlenb
slli a2,a2,33
vmv.v.x v0,a2
gcc/ChangeLog:
* config/riscv/riscv.cc (riscv_expand_mult_with_const_int):
Change int into HOST_WIDE_INT.
(riscv_legitimize_poly_move): Ditto.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/autovec/bug-3.c: New test.
Signed-off-by: Pan Li <pan2.li@intel.com>
---
gcc/config/riscv/riscv.cc | 10 +++--
.../gcc.target/riscv/rvv/autovec/bug-3.c | 39 +++++++++++++++++++
2 files changed, 45 insertions(+), 4 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/bug-3.c
@@ -2371,7 +2371,7 @@ riscv_expand_op (enum rtx_code code, machine_mode mode, rtx op0, rtx op1,
static void
riscv_expand_mult_with_const_int (machine_mode mode, rtx dest, rtx multiplicand,
- int multiplier)
+ HOST_WIDE_INT multiplier)
{
if (multiplier == 0)
{
@@ -2380,7 +2380,7 @@ riscv_expand_mult_with_const_int (machine_mode mode, rtx dest, rtx multiplicand,
}
bool neg_p = multiplier < 0;
- int multiplier_abs = abs (multiplier);
+ unsigned HOST_WIDE_INT multiplier_abs = abs (multiplier);
if (multiplier_abs == 1)
{
@@ -2475,8 +2475,10 @@ void
riscv_legitimize_poly_move (machine_mode mode, rtx dest, rtx tmp, rtx src)
{
poly_int64 value = rtx_to_poly_int64 (src);
- int offset = value.coeffs[0];
- int factor = value.coeffs[1];
+ /* It use HOST_WIDE_INT intead of int since 32bit type is not enough
+ for e.g. (const_poly_int:DI [549755813888, 549755813888]). */
+ HOST_WIDE_INT offset = value.coeffs[0];
+ HOST_WIDE_INT factor = value.coeffs[1];
int vlenb = BYTES_PER_RISCV_VECTOR.coeffs[1];
int div_factor = 0;
/* Calculate (const_poly_int:MODE [m, n]) using scalar instructions.
new file mode 100644
@@ -0,0 +1,39 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl512b -mabi=lp64d --param=riscv-autovec-lmul=m8 --param=riscv-autovec-preference=scalable -fno-vect-cost-model -O2 -ffast-math" } */
+
+#define N 16
+
+_Complex float a[N] =
+ { 10.0F + 20.0iF, 11.0F + 21.0iF, 12.0F + 22.0iF, 13.0F + 23.0iF,
+ 14.0F + 24.0iF, 15.0F + 25.0iF, 16.0F + 26.0iF, 17.0F + 27.0iF,
+ 18.0F + 28.0iF, 19.0F + 29.0iF, 20.0F + 30.0iF, 21.0F + 31.0iF,
+ 22.0F + 32.0iF, 23.0F + 33.0iF, 24.0F + 34.0iF, 25.0F + 35.0iF };
+_Complex float b[N] =
+ { 30.0F + 40.0iF, 31.0F + 41.0iF, 32.0F + 42.0iF, 33.0F + 43.0iF,
+ 34.0F + 44.0iF, 35.0F + 45.0iF, 36.0F + 46.0iF, 37.0F + 47.0iF,
+ 38.0F + 48.0iF, 39.0F + 49.0iF, 40.0F + 50.0iF, 41.0F + 51.0iF,
+ 42.0F + 52.0iF, 43.0F + 53.0iF, 44.0F + 54.0iF, 45.0F + 55.0iF };
+
+_Complex float c[N];
+_Complex float res[N] =
+ { -500.0F + 1000.0iF, -520.0F + 1102.0iF,
+ -540.0F + 1208.0iF, -560.0F + 1318.0iF,
+ -580.0F + 1432.0iF, -600.0F + 1550.0iF,
+ -620.0F + 1672.0iF, -640.0F + 1798.0iF,
+ -660.0F + 1928.0iF, -680.0F + 2062.0iF,
+ -700.0F + 2200.0iF, -720.0F + 2342.0iF,
+ -740.0F + 2488.0iF, -760.0F + 2638.0iF,
+ -780.0F + 2792.0iF, -800.0F + 2950.0iF };
+
+
+void
+foo (void)
+{
+ int i;
+
+ for (i = 0; i < N; i++)
+ c[i] = a[i] * b[i];
+}
+
+/* { dg-final { scan-assembler-not {li\s+[a-x0-9]+,\s*0} } } */
+/* { dg-final { scan-assembler-times {slli\s+[a-x0-9]+,\s*[a-x0-9]+,\s*33} 1 } } */