Re: [PATCH GCC13 backport] Avoid compile time hog on vect_peel_nonlinear_iv_init for nonlinear induction vec_step_op_mul when iteration count is too big.
> Am 24.10.2023 um 13:22 schrieb liuhongt :
>
> This is the backport patch for releases/gcc-13 branch, the original patch
> for main trunk
> is at [1].
> The only difference between this backport patch and [1] is GCC13 doesn't
> support auto_mpz,
> So this patch manually use mpz_init/mpz_clear.
>
> [1] https://gcc.gnu.org/pipermail/gcc-patches/2023-October/633661.html
>
> Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}
> Ok for backport to releases/gcc-13?
Ok.
Richard
> There's loop in vect_peel_nonlinear_iv_init to get init_expr *
> pow (step_expr, skip_niters). When skipn_iters is too big, compile time
> hogs. To avoid that, optimize init_expr * pow (step_expr, skip_niters) to
> init_expr << (exact_log2 (step_expr) * skip_niters) when step_expr is
> pow of 2, otherwise give up vectorization when skip_niters >=
> TYPE_PRECISION (TREE_TYPE (init_expr)).
>
> Also give up vectorization when niters_skip is negative which will be
> used for fully masked loop.
>
> gcc/ChangeLog:
>
>PR tree-optimization/111820
>PR tree-optimization/111833
>* tree-vect-loop-manip.cc (vect_can_peel_nonlinear_iv_p): Give
>up vectorization for nonlinear iv vect_step_op_mul when
>step_expr is not exact_log2 and niters is greater than
>TYPE_PRECISION (TREE_TYPE (step_expr)). Also don't vectorize
>for nagative niters_skip which will be used by fully masked
>loop.
>(vect_can_advance_ivs_p): Pass whole phi_info to
>vect_can_peel_nonlinear_iv_p.
>* tree-vect-loop.cc (vect_peel_nonlinear_iv_init): Optimize
>init_expr * pow (step_expr, skipn) to init_expr
><< (log2 (step_expr) * skipn) when step_expr is exact_log2.
>
> gcc/testsuite/ChangeLog:
>
>* gcc.target/i386/pr111820-1.c: New test.
>* gcc.target/i386/pr111820-2.c: New test.
>* gcc.target/i386/pr111820-3.c: New test.
>* gcc.target/i386/pr103144-mul-1.c: Adjust testcase.
>* gcc.target/i386/pr103144-mul-2.c: Adjust testcase.
> ---
> .../gcc.target/i386/pr103144-mul-1.c | 8 +++---
> .../gcc.target/i386/pr103144-mul-2.c | 8 +++---
> gcc/testsuite/gcc.target/i386/pr111820-1.c| 16 +++
> gcc/testsuite/gcc.target/i386/pr111820-2.c| 16 +++
> gcc/testsuite/gcc.target/i386/pr111820-3.c| 16 +++
> gcc/tree-vect-loop-manip.cc | 28 +--
> gcc/tree-vect-loop.cc | 21 +++---
> 7 files changed, 98 insertions(+), 15 deletions(-)
> create mode 100644 gcc/testsuite/gcc.target/i386/pr111820-1.c
> create mode 100644 gcc/testsuite/gcc.target/i386/pr111820-2.c
> create mode 100644 gcc/testsuite/gcc.target/i386/pr111820-3.c
>
> diff --git a/gcc/testsuite/gcc.target/i386/pr103144-mul-1.c
> b/gcc/testsuite/gcc.target/i386/pr103144-mul-1.c
> index 640c34fd959..913d7737dcd 100644
> --- a/gcc/testsuite/gcc.target/i386/pr103144-mul-1.c
> +++ b/gcc/testsuite/gcc.target/i386/pr103144-mul-1.c
> @@ -11,7 +11,7 @@ foo_mul (int* a, int b)
> for (int i = 0; i != N; i++)
> {
> a[i] = b;
> - b *= 3;
> + b *= 4;
> }
> }
>
> @@ -23,7 +23,7 @@ foo_mul_const (int* a)
> for (int i = 0; i != N; i++)
> {
> a[i] = b;
> - b *= 3;
> + b *= 4;
> }
> }
>
> @@ -34,7 +34,7 @@ foo_mul_peel (int* a, int b)
> for (int i = 0; i != 39; i++)
> {
> a[i] = b;
> - b *= 3;
> + b *= 4;
> }
> }
>
> @@ -46,6 +46,6 @@ foo_mul_peel_const (int* a)
> for (int i = 0; i != 39; i++)
> {
> a[i] = b;
> - b *= 3;
> + b *= 4;
> }
> }
> diff --git a/gcc/testsuite/gcc.target/i386/pr103144-mul-2.c
> b/gcc/testsuite/gcc.target/i386/pr103144-mul-2.c
> index 39fdea3a69d..b2ff186e335 100644
> --- a/gcc/testsuite/gcc.target/i386/pr103144-mul-2.c
> +++ b/gcc/testsuite/gcc.target/i386/pr103144-mul-2.c
> @@ -16,12 +16,12 @@ avx2_test (void)
>
> __builtin_memset (epi32_exp, 0, N * sizeof (int));
> int b = 8;
> - v8si init = __extension__(v8si) { b, b * 3, b * 9, b * 27, b * 81, b *
> 243, b * 729, b * 2187 };
> + v8si init = __extension__(v8si) { b, b * 4, b * 16, b * 64, b * 256, b *
> 1024, b * 4096, b * 16384 };
>
> for (int i = 0; i != N / 8; i++)
> {
> memcpy (epi32_exp + i * 8, , 32);
> - init *= 6561;
> + init *= 65536;
> }
>
> foo_mul (epi32_dst, b);
> @@ -32,11 +32,11 @@ avx2_test (void)
> if (__builtin_memcmp (epi32_dst, epi32_exp, 39 * 4) != 0)
> __builtin_abort ();
>
> - init = __extension__(v8si) { 1, 3, 9, 27, 81, 243, 729, 2187 };
> + init = __extension__(v8si) { 1, 4, 16, 64, 256, 1024, 4096, 16384 };
> for (int i = 0; i != N / 8; i++)
> {
> memcpy (epi32_exp + i * 8, , 32);
> - init *= 6561;
> + init *= 65536;
> }
>
> foo_mul_const (epi32_dst);
> diff --git a/gcc/testsuite/gcc.target/i386/pr111820-1.c
> b/gcc/testsuite/gcc.target/i386/pr111820-1.c
> new file mode 100644
> index 000..50e960c39d4
> --- /dev/null
> +++
[PATCH GCC13 backport] Avoid compile time hog on vect_peel_nonlinear_iv_init for nonlinear induction vec_step_op_mul when iteration count is too big.
This is the backport patch for releases/gcc-13 branch, the original patch for
main trunk
is at [1].
The only difference between this backport patch and [1] is GCC13 doesn't
support auto_mpz,
So this patch manually use mpz_init/mpz_clear.
[1] https://gcc.gnu.org/pipermail/gcc-patches/2023-October/633661.html
Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}
Ok for backport to releases/gcc-13?
There's loop in vect_peel_nonlinear_iv_init to get init_expr *
pow (step_expr, skip_niters). When skipn_iters is too big, compile time
hogs. To avoid that, optimize init_expr * pow (step_expr, skip_niters) to
init_expr << (exact_log2 (step_expr) * skip_niters) when step_expr is
pow of 2, otherwise give up vectorization when skip_niters >=
TYPE_PRECISION (TREE_TYPE (init_expr)).
Also give up vectorization when niters_skip is negative which will be
used for fully masked loop.
gcc/ChangeLog:
PR tree-optimization/111820
PR tree-optimization/111833
* tree-vect-loop-manip.cc (vect_can_peel_nonlinear_iv_p): Give
up vectorization for nonlinear iv vect_step_op_mul when
step_expr is not exact_log2 and niters is greater than
TYPE_PRECISION (TREE_TYPE (step_expr)). Also don't vectorize
for nagative niters_skip which will be used by fully masked
loop.
(vect_can_advance_ivs_p): Pass whole phi_info to
vect_can_peel_nonlinear_iv_p.
* tree-vect-loop.cc (vect_peel_nonlinear_iv_init): Optimize
init_expr * pow (step_expr, skipn) to init_expr
<< (log2 (step_expr) * skipn) when step_expr is exact_log2.
gcc/testsuite/ChangeLog:
* gcc.target/i386/pr111820-1.c: New test.
* gcc.target/i386/pr111820-2.c: New test.
* gcc.target/i386/pr111820-3.c: New test.
* gcc.target/i386/pr103144-mul-1.c: Adjust testcase.
* gcc.target/i386/pr103144-mul-2.c: Adjust testcase.
---
.../gcc.target/i386/pr103144-mul-1.c | 8 +++---
.../gcc.target/i386/pr103144-mul-2.c | 8 +++---
gcc/testsuite/gcc.target/i386/pr111820-1.c| 16 +++
gcc/testsuite/gcc.target/i386/pr111820-2.c| 16 +++
gcc/testsuite/gcc.target/i386/pr111820-3.c| 16 +++
gcc/tree-vect-loop-manip.cc | 28 +--
gcc/tree-vect-loop.cc | 21 +++---
7 files changed, 98 insertions(+), 15 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/i386/pr111820-1.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr111820-2.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr111820-3.c
diff --git a/gcc/testsuite/gcc.target/i386/pr103144-mul-1.c
b/gcc/testsuite/gcc.target/i386/pr103144-mul-1.c
index 640c34fd959..913d7737dcd 100644
--- a/gcc/testsuite/gcc.target/i386/pr103144-mul-1.c
+++ b/gcc/testsuite/gcc.target/i386/pr103144-mul-1.c
@@ -11,7 +11,7 @@ foo_mul (int* a, int b)
for (int i = 0; i != N; i++)
{
a[i] = b;
- b *= 3;
+ b *= 4;
}
}
@@ -23,7 +23,7 @@ foo_mul_const (int* a)
for (int i = 0; i != N; i++)
{
a[i] = b;
- b *= 3;
+ b *= 4;
}
}
@@ -34,7 +34,7 @@ foo_mul_peel (int* a, int b)
for (int i = 0; i != 39; i++)
{
a[i] = b;
- b *= 3;
+ b *= 4;
}
}
@@ -46,6 +46,6 @@ foo_mul_peel_const (int* a)
for (int i = 0; i != 39; i++)
{
a[i] = b;
- b *= 3;
+ b *= 4;
}
}
diff --git a/gcc/testsuite/gcc.target/i386/pr103144-mul-2.c
b/gcc/testsuite/gcc.target/i386/pr103144-mul-2.c
index 39fdea3a69d..b2ff186e335 100644
--- a/gcc/testsuite/gcc.target/i386/pr103144-mul-2.c
+++ b/gcc/testsuite/gcc.target/i386/pr103144-mul-2.c
@@ -16,12 +16,12 @@ avx2_test (void)
__builtin_memset (epi32_exp, 0, N * sizeof (int));
int b = 8;
- v8si init = __extension__(v8si) { b, b * 3, b * 9, b * 27, b * 81, b * 243,
b * 729, b * 2187 };
+ v8si init = __extension__(v8si) { b, b * 4, b * 16, b * 64, b * 256, b *
1024, b * 4096, b * 16384 };
for (int i = 0; i != N / 8; i++)
{
memcpy (epi32_exp + i * 8, , 32);
- init *= 6561;
+ init *= 65536;
}
foo_mul (epi32_dst, b);
@@ -32,11 +32,11 @@ avx2_test (void)
if (__builtin_memcmp (epi32_dst, epi32_exp, 39 * 4) != 0)
__builtin_abort ();
- init = __extension__(v8si) { 1, 3, 9, 27, 81, 243, 729, 2187 };
+ init = __extension__(v8si) { 1, 4, 16, 64, 256, 1024, 4096, 16384 };
for (int i = 0; i != N / 8; i++)
{
memcpy (epi32_exp + i * 8, , 32);
- init *= 6561;
+ init *= 65536;
}
foo_mul_const (epi32_dst);
diff --git a/gcc/testsuite/gcc.target/i386/pr111820-1.c
b/gcc/testsuite/gcc.target/i386/pr111820-1.c
new file mode 100644
index 000..50e960c39d4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr111820-1.c
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -mavx2 -fno-tree-vrp -Wno-aggressive-loop-optimizations
-fdump-tree-vect-details" } */
+/* { dg-final { scan-tree-dump "Avoid
