c2ebf4f10d
The following change adds support for non-rectangular simd loops.
While working on that, I've noticed we actually don't vectorize collapsed
simd loops at all, because the code that I thought would be vectorizable
actually is not vectorized. While in theory for the constant lower/upper
bounds and constant step of all but the outermost loop we could in theory
vectorize by computing the seprate iterators using vectorized division
and modulo for each of them from the single iterator that increments
by 1 from 0 to total iteration count in the loop nest, I think that would
be fairly expensive and the chances of the loop body being vectorizable
would be low e.g. because of array indices unlikely to be linear and would
need scatters/gathers.
This patch changes the generated code to vectorize only the innermost
loop which has higher chance of being vectorized. Below is the list of
tests and function names in which the patch resulted in vectorizing something
that hasn't been vectorized before (ok, the first line is a new test).
I've also found that the vectorizer will not vectorize loops with non-constant
steps, I plan to do something about those incrementally on the omp-expand.c
side (basically, compute number of iterations before the loop and use a 0 to
number_of_iterations step 1 IV as the main one).
I have problem with the composite simd vectorization though.
The point is that each thread (or task etc.) is given only a range of
consecutive iterations, so somewhere earlier it computes total number of iterations
and splits the work between the workers and then the intent is to try to vectorize it.
So, each thread is then given a begin ... end-1 range that it would handle.
This means that from the single begin value I need to compute the individual iteration
vars I should start at and then goto into the loop nest to begin iterating there
(and actually compute how many iterations the innermost loop should do each time
so that it stops before end).
Very roughly the IL I emit is something like:
int t[100][100][100];
void
foo (int a, int b, int c, int d, int e, int f, int g, int h, int u, int v, int w, int x)
{
int i, j, k;
int cnt;
if (x)
{
i = u; j = v; k = w; goto doit;
}
for (i = a; i < b; i += c)
for (j = d; j < e; j += f)
{
k = g;
doit:
for (; k < h; k++)
t[i][j][k] += i + j + k;
}
}
Unfortunately, some pass then turns the innermost loop to have more than 2 basic blocks
and it isn't vectorized because of that.
Also, I have disabled (for now) SIMTization of collapsed simd loops, because for SIMT
it would be using a single thread anyway and I didn't want to bother with checking
SIMT on all places I've been changing. If SIMT support is added for some or all
collapsed loops, that omp-low.c change needs to be reverted.
Here is that list of what hasn't been vectorized before and is now:
gcc/testsuite/gcc.dg/vect/vect-simd-17.c doit
gcc/testsuite/gfortran.dg/gomp/openmp-simd-6.f90 bar
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-10.c f28_taskloop_simd_normal._omp_fn.0
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-10.c _Z24f28_taskloop_simd_normalv._omp_fn.0
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-11.c f25_t_simd_normal._omp_fn.0
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-11.c f26_t_simd_normal._omp_fn.0
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-11.c f27_t_simd_normal._omp_fn.0
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-11.c f28_tpf_simd_guided32._omp_fn.1
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-11.c f28_tpf_simd_runtime._omp_fn.1
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-11.c _Z17f25_t_simd_normaliiiiiii._omp_fn.0
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-11.c _Z17f26_t_simd_normaliiiixxi._omp_fn.0
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-11.c _Z17f27_t_simd_normalv._omp_fn.0
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-11.c _Z20f28_tpf_simd_runtimev._omp_fn.1
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-11.c _Z21f28_tpf_simd_guided32v._omp_fn.1
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-2.c f7_simd_normal
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-2.c f7_simd_normal
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-2.c f8_f_simd_guided32
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-2.c f8_f_simd_guided32
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-2.c f8_f_simd_runtime
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-2.c f8_f_simd_runtime
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-2.c f8_pf_simd_guided32._omp_fn.0
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-2.c f8_pf_simd_runtime._omp_fn.0
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-2.c _Z18f8_pf_simd_runtimev._omp_fn.0
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-2.c _Z19f8_pf_simd_guided32v._omp_fn.0
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-4.c f8_taskloop_simd_normal._omp_fn.0
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-4.c _Z23f8_taskloop_simd_normalv._omp_fn.0
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-5.c f7_t_simd_normal._omp_fn.0
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-5.c f8_tpf_simd_guided32._omp_fn.1
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-5.c f8_tpf_simd_runtime._omp_fn.1
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-5.c _Z16f7_t_simd_normalv._omp_fn.0
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-5.c _Z19f8_tpf_simd_runtimev._omp_fn.1
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-5.c _Z20f8_tpf_simd_guided32v._omp_fn.1
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-8.c f25_simd_normal
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-8.c f25_simd_normal
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-8.c f26_simd_normal
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-8.c f26_simd_normal
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-8.c f27_simd_normal
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-8.c f27_simd_normal
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-8.c f28_f_simd_guided32
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-8.c f28_f_simd_guided32
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-8.c f28_f_simd_runtime
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-8.c f28_f_simd_runtime
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-8.c f28_pf_simd_guided32._omp_fn.0
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/for-8.c f28_pf_simd_runtime._omp_fn.0
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-8.c _Z19f28_pf_simd_runtimev._omp_fn.0
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/for-8.c _Z20f28_pf_simd_guided32v._omp_fn.0
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/master-combined-1.c main._omp_fn.9
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/master-combined-1.c main._omp_fn.9
libgomp/testsuite/libgomp.c++/../libgomp.c-c++-common/simd-1.c f2
libgomp/testsuite/libgomp.c/../libgomp.c-c++-common/simd-1.c f2
libgomp/testsuite/libgomp.c/pr70680-2.c f1._omp_fn.0
libgomp/testsuite/libgomp.c/pr70680-2.c f2._omp_fn.0
libgomp/testsuite/libgomp.c/pr70680-2.c f3._omp_fn.0
libgomp/testsuite/libgomp.c/pr70680-2.c f4._omp_fn.0
libgomp/testsuite/libgomp.c/simd-8.c foo
libgomp/testsuite/libgomp.c/simd-9.c bar
libgomp/testsuite/libgomp.c/simd-9.c foo
2020-09-25 Jakub Jelinek <jakub@redhat.com>
gcc/
* omp-low.c (scan_omp_1_stmt): Don't call scan_omp_simd for
collapse > 1 loops as simt doesn't support collapsed loops yet.
* omp-expand.c (expand_omp_for_init_counts, expand_omp_for_init_vars):
Small tweaks to function comment.
(expand_omp_simd): Rewritten collapse > 1 support to only attempt
to vectorize the innermost loop and emit set of outer loops around it.
For non-composite simd with collapse > 1 without broken loop don't
even try to compute number of iterations first. Add support for
non-rectangular simd loops.
(expand_omp_for): Don't sorry_at on non-rectangular simd loops.
gcc/testsuite/
* gcc.dg/vect/vect-simd-17.c: New test.
libgomp/
* testsuite/libgomp.c/loop-25.c: New test.
297 lines
7.8 KiB
C
297 lines
7.8 KiB
C
/* { dg-do run } */
|
|
/* { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" } */
|
|
/* { dg-additional-options "-mavx" { target avx_runtime } } */
|
|
|
|
int x, i, j;
|
|
volatile int a, b, c, d, e, f, g, h;
|
|
int k[11][101];
|
|
extern void abort (void);
|
|
|
|
int
|
|
main ()
|
|
{
|
|
int niters, err = 0;
|
|
for (i = 1; i <= 10; i++)
|
|
for (j = 1; j <= 10 * i; j++)
|
|
{
|
|
k[i][j] = 1;
|
|
asm volatile ("" : : : "memory");
|
|
}
|
|
a = 1; b = 11; c = 1; d = 0; e = 1; f = 10; g = 1; h = 1;
|
|
niters = 0; i = -100; j = -100; x = -100;
|
|
#pragma omp parallel for simd collapse(2) lastprivate (i, j, x) reduction(+:niters) reduction(|:err)
|
|
for (i = 1; i <= 10; i++)
|
|
for (j = 1; j <= 10 * i; j++)
|
|
{
|
|
err |= (i < 1);
|
|
err |= (i > 10);
|
|
err |= (j < 1);
|
|
err |= (j > 10 * i);
|
|
err |= (k[i][j] != 1);
|
|
k[i][j]++;
|
|
x = i * 1024 + (j & 1023);
|
|
niters++;
|
|
}
|
|
if (i != 11 || j != 101 || x != 10340 || niters != 550 || err)
|
|
abort ();
|
|
niters = 0; i = -100; j = -100; x = -100;
|
|
#pragma omp parallel for simd collapse(2) lastprivate (i, j, x) reduction(+:niters) reduction(|:err)
|
|
for (i = a; i < b; i += c)
|
|
for (j = d * i + e; j < g + i * f; j += h)
|
|
{
|
|
err |= (i < 1);
|
|
err |= (i > 10);
|
|
err |= (j < 1);
|
|
err |= (j > 10 * i);
|
|
err |= (k[i][j] != 2);
|
|
k[i][j]++;
|
|
x = i * 1024 + (j & 1023);
|
|
niters++;
|
|
}
|
|
if (i != 11 || j != 101 || x != 10340 || niters != 550 || err)
|
|
abort ();
|
|
for (i = 1; i <= 10; i++)
|
|
for (j = 1; j <= 10 * i; j++)
|
|
if (k[i][j] == 3)
|
|
k[i][j] = 0;
|
|
else
|
|
abort ();
|
|
for (i = 0; i < 11; i++)
|
|
for (j = 0; j < 101; j++)
|
|
if (k[i][j] != 0)
|
|
abort ();
|
|
for (i = 0; i < 10; i++)
|
|
for (j = 0; j < 10 * i; j++)
|
|
{
|
|
k[i][j] = 1;
|
|
asm volatile ("" : : : "memory");
|
|
}
|
|
a = 0; b = 10; c = 1; d = 0; e = 0; f = 10; g = 0; h = 1;
|
|
niters = 0; i = -100; j = -100; x = -100;
|
|
#pragma omp parallel for simd collapse(2) lastprivate (i, j, x) reduction(+:niters) reduction(|:err)
|
|
for (i = 0; i < 10; i++)
|
|
for (j = 0; j < 10 * i; j++)
|
|
{
|
|
err |= (i < 0);
|
|
err |= (i >= 10);
|
|
err |= (j < 0);
|
|
err |= (j >= 10 * i);
|
|
err |= (k[i][j] != 1);
|
|
k[i][j]++;
|
|
x = i * 1024 + (j & 1023);
|
|
niters++;
|
|
}
|
|
if (i != 10 || j != 90 || x != 9305 || niters != 450 || err)
|
|
abort ();
|
|
niters = 0; i = -100; j = -100; x = -100;
|
|
#pragma omp parallel for simd collapse(2) lastprivate (i, j, x) reduction(+:niters) reduction(|:err)
|
|
for (i = a; i < b; i += c)
|
|
for (j = d * i + e; j < g + i * f; j += h)
|
|
{
|
|
err |= (i < 0);
|
|
err |= (i >= 10);
|
|
err |= (j < 0);
|
|
err |= (j >= 10 * i);
|
|
err |= (k[i][j] != 2);
|
|
k[i][j]++;
|
|
x = i * 1024 + (j & 1023);
|
|
niters++;
|
|
}
|
|
if (i != 10 || j != 90 || x != 9305 || niters != 450 || err)
|
|
abort ();
|
|
for (i = 0; i < 10; i++)
|
|
for (j = 0; j < 10 * i; j++)
|
|
if (k[i][j] == 3)
|
|
k[i][j] = 0;
|
|
else
|
|
abort ();
|
|
for (i = 0; i < 11; i++)
|
|
for (j = 0; j < 101; j++)
|
|
if (k[i][j] != 0)
|
|
abort ();
|
|
for (i = 4; i < 10; i++)
|
|
for (j = -9 + 2 * i; j < i; j++)
|
|
{
|
|
k[i][j + 1] = 1;
|
|
asm volatile ("" : : : "memory");
|
|
}
|
|
a = 4; b = 10; c = 1; d = 2; e = -9; f = 1; g = 0; h = 1;
|
|
niters = 0; i = -100; j = -100; x = -100;
|
|
#pragma omp parallel for simd collapse(2) lastprivate (i, j, x) reduction(+:niters) reduction(|:err)
|
|
for (i = 4; i < 10; i++)
|
|
for (j = -9 + 2 * i; j < i; j++)
|
|
{
|
|
err |= (i < 4);
|
|
err |= (i >= 10);
|
|
err |= (j < -9 + 2 * i);
|
|
err |= (j >= i);
|
|
err |= (k[i][j + 1] != 1);
|
|
k[i][j + 1]++;
|
|
x = i * 1024 + (j & 1023);
|
|
niters++;
|
|
}
|
|
if (/*i != 10 || j != 9 || */x != 8199 || niters != 15 || err)
|
|
abort ();
|
|
niters = 0; i = -100; j = -100; x = -100;
|
|
#pragma omp parallel for simd collapse(2) lastprivate (i, j, x) reduction(+:niters) reduction(|:err)
|
|
for (i = a; i < b; i += c)
|
|
for (j = d * i + e; j < g + i * f; j += h)
|
|
{
|
|
err |= (i < 4);
|
|
err |= (i >= 10);
|
|
err |= (j < -9 + 2 * i);
|
|
err |= (j >= i);
|
|
err |= (k[i][j + 1] != 2);
|
|
k[i][j + 1]++;
|
|
x = i * 1024 + (j & 1023);
|
|
niters++;
|
|
}
|
|
if (/*i != 10 || j != 9 || */x != 8199 || niters != 15 || err)
|
|
abort ();
|
|
for (i = 4; i < 10; i++)
|
|
for (j = -9 + 2 * i; j < i; j++)
|
|
if (k[i][j + 1] == 3)
|
|
k[i][j + 1] = 0;
|
|
else
|
|
abort ();
|
|
for (i = 0; i < 11; i++)
|
|
for (j = 0; j < 101; j++)
|
|
if (k[i][j] != 0)
|
|
abort ();
|
|
for (i = 1; i < 10; i += 2)
|
|
for (j = 1; j < i + 1; j++)
|
|
{
|
|
k[i][j] = 1;
|
|
asm volatile ("" : : : "memory");
|
|
}
|
|
a = 1; b = 10; c = 2; d = 0; e = 1; f = 1; g = 1; h = 1;
|
|
niters = 0; i = -100; j = -100; x = -100;
|
|
#pragma omp parallel for simd collapse(2) lastprivate (i, j, x) reduction(+:niters) reduction(|:err)
|
|
for (i = 1; i < 10; i += 2)
|
|
for (j = 1; j < i + 1; j++)
|
|
{
|
|
err |= (i < 1);
|
|
err |= (i >= 10);
|
|
err |= (j < 1);
|
|
err |= (j >= i + 1);
|
|
err |= (k[i][j] != 1);
|
|
k[i][j]++;
|
|
x = i * 1024 + (j & 1023);
|
|
niters++;
|
|
}
|
|
if (i != 11 || j != 10 || x != 9225 || niters != 25 || err)
|
|
abort ();
|
|
niters = 0; i = -100; j = -100; x = -100;
|
|
#pragma omp parallel for simd collapse(2) lastprivate (i, j, x) reduction(+:niters) reduction(|:err)
|
|
for (i = a; i < b; i += c)
|
|
for (j = d * i + e; j < g + i * f; j += h)
|
|
{
|
|
err |= (i < 1);
|
|
err |= (i >= 10);
|
|
err |= (j < 1);
|
|
err |= (j >= i + 1);
|
|
err |= (k[i][j] != 2);
|
|
k[i][j]++;
|
|
x = i * 1024 + (j & 1023);
|
|
niters++;
|
|
}
|
|
if (i != 11 || j != 10 || x != 9225 || niters != 25 || err)
|
|
abort ();
|
|
for (i = 1; i < 10; i += 2)
|
|
for (j = 1; j < i + 1; j++)
|
|
if (k[i][j] == 3)
|
|
k[i][j] = 0;
|
|
else
|
|
abort ();
|
|
for (i = 0; i < 11; i++)
|
|
for (j = 0; j < 101; j++)
|
|
if (k[i][j] != 0)
|
|
abort ();
|
|
for (j = -11; j >= -41; j -= 15)
|
|
{
|
|
k[0][-j] = 1;
|
|
asm volatile ("" : : : "memory");
|
|
}
|
|
a = 4; b = 8; c = 12; d = -8; e = -9; f = -3; g = 6; h = 15;
|
|
niters = 0; i = -100; j = -100; x = -100;
|
|
#pragma omp parallel for simd collapse(2) lastprivate (i, j, x) reduction(+:niters) reduction(|:err)
|
|
for (i = 4; i < 8; i += 12)
|
|
for (j = -8 * i - 9; j < i * -3 + 6; j += 15)
|
|
{
|
|
err |= (i != 4);
|
|
err |= (j < -41);
|
|
err |= (j > -11);
|
|
err |= (k[0][-j] != 1);
|
|
k[0][-j]++;
|
|
x = i * 1024 + (j & 1023);
|
|
niters++;
|
|
}
|
|
if (i != 16 || j != 4 || x != 5109 || niters != 3 || err)
|
|
abort ();
|
|
niters = 0; i = -100; j = -100; x = -100;
|
|
#pragma omp parallel for simd collapse(2) lastprivate (i, j, x) reduction(+:niters) reduction(|:err)
|
|
for (i = a; i < b; i += c)
|
|
for (j = d * i + e; j < g + i * f; j += h)
|
|
{
|
|
err |= (i != 4);
|
|
err |= (j < -41);
|
|
err |= (j > -11);
|
|
err |= (k[0][-j] != 2);
|
|
k[0][-j]++;
|
|
x = i * 1024 + (j & 1023);
|
|
niters++;
|
|
}
|
|
if (i != 16 || j != 4 || x != 5109 || niters != 3 || err)
|
|
abort ();
|
|
for (j = -11; j >= -41; j -= 15)
|
|
if (k[0][-j] == 3)
|
|
k[0][-j] = 0;
|
|
else
|
|
abort ();
|
|
for (j = -11; j >= -41; j--)
|
|
if (k[0][-j] != 0)
|
|
abort ();
|
|
for (j = -34; j <= -7; j++)
|
|
{
|
|
k[0][-j] = 1;
|
|
asm volatile ("" : : : "memory");
|
|
}
|
|
a = -13; b = 7; c = 12; d = 3; e = 5; f = 0; g = -6; h = 1;
|
|
niters = 0; i = -100; j = -100; x = -100;
|
|
#pragma omp parallel for simd collapse(2) lastprivate (i, j, x) reduction(+:niters) reduction(|:err)
|
|
for (i = -13; i < 7; i += 12)
|
|
for (j = 3 * i + 5; j < -6; j++)
|
|
{
|
|
err |= (i != -13);
|
|
err |= (j < -34);
|
|
err |= (j > -7);
|
|
err |= (k[0][-j] != 1);
|
|
k[0][-j]++;
|
|
x = i * 1024 + (j & 1023);
|
|
niters++;
|
|
}
|
|
if (/*i != 11 || j != 2 || */x != -12295 || niters != 28 || err)
|
|
abort ();
|
|
niters = 0; i = -100; j = -100; x = -100;
|
|
#pragma omp parallel for simd collapse(2) lastprivate (i, j, x) reduction(+:niters) reduction(|:err)
|
|
for (i = a; i < b; i += c)
|
|
for (j = d * i + e; j < g + i * f; j += h)
|
|
{
|
|
err |= (i != -13);
|
|
err |= (j < -34);
|
|
err |= (j > -7);
|
|
err |= (k[0][-j] != 2);
|
|
k[0][-j]++;
|
|
x = i * 1024 + (j & 1023);
|
|
niters++;
|
|
}
|
|
if (/*i != 11 || j != 2 || */x != -12295 || niters != 28 || err)
|
|
abort ();
|
|
for (j = -34; j <= -7; j++)
|
|
if (k[0][-j] == 3)
|
|
k[0][-j] = 0;
|
|
else
|
|
abort ();
|
|
return 0;
|
|
}
|