Message ID | 20151123191459.GH5675@tucnak.redhat.com |
---|---|
State | New |
Headers | show |
On November 23, 2015 8:14:59 PM GMT+01:00, Jakub Jelinek <jakub@redhat.com> wrote: >Hi! > >The patches that removed VEC_RSHIFT_EXPR regressed the first of these >testcases on i?86/-msse2, because can_vec_perm_p returns false for >that, >and indeed as can_vec_perm_p is given only the mode and mask indices, >there is nothing it can do about it. The former VEC_RSHIFT_EXPR >is a special VEC_PERM_EXPR with zero (bitwise, so not -0.0) as second >argument and we can use vec_shr in that case. The expander knows that, >but >veclower hasn't been taught about that, which is what this patch does. > >The patch also fixes up the shift_amt_for_vec_perm_mask function, >if the first index is >= nelt, then it certainly is not a vector shift, >but >all zeros result (we should have folded it), plus when first is < nelt, >then it doesn't make sense to mask the result, even for first == nelt - >1 >first + nelt - 1 is <= 2 * nelt - 1. > >Bootstrapped/regtested on x86_64-linux and i686-linux, ok for >trunk/5.3? OK. I wonder if we want a more "powerful" can_vec_perm that gets the actual arguments for example to decide if the result of folding a perm is still valid To include that shift case. Richard. >2015-11-23 Jakub Jelinek <jakub@redhat.com> > > PR target/68483 > * tree-vect-generic.c (lower_vec_perm): If VEC_PERM_EXPR > is valid vec_shr pattern, don't lower it even if can_vec_perm_p > returns false. > * optabs.c (shift_amt_for_vec_perm_mask): Return NULL_RTX > whenever first is nelt or above. Don't mask expected with > 2 * nelt - 1. > > * gcc.target/i386/pr68483-1.c: New test. > * gcc.target/i386/pr68483-2.c: New test. > >--- gcc/tree-vect-generic.c.jj 2015-11-23 13:29:41.959236201 +0100 >+++ gcc/tree-vect-generic.c 2015-11-23 14:13:10.378094173 +0100 >@@ -1272,6 +1272,30 @@ lower_vec_perm (gimple_stmt_iterator *gs > update_stmt (stmt); > return; > } >+ /* Also detect vec_shr pattern - VEC_PERM_EXPR with zero >+ vector as VEC1 and a right element shift MASK. */ >+ if (optab_handler (vec_shr_optab, TYPE_MODE (vect_type)) >+ != CODE_FOR_nothing >+ && TREE_CODE (vec1) == VECTOR_CST >+ && initializer_zerop (vec1) >+ && sel_int[0] >+ && sel_int[0] < elements) >+ { >+ for (i = 1; i < elements; ++i) >+ { >+ unsigned int expected = i + sel_int[0]; >+ /* Indices into the second vector are all equivalent. */ >+ if (MIN (elements, (unsigned) sel_int[i]) >+ != MIN (elements, expected)) >+ break; >+ } >+ if (i == elements) >+ { >+ gimple_assign_set_rhs3 (stmt, mask); >+ update_stmt (stmt); >+ return; >+ } >+ } > } > else if (can_vec_perm_p (TYPE_MODE (vect_type), true, NULL)) > return; >--- gcc/optabs.c.jj 2015-11-23 13:29:41.706239800 +0100 >+++ gcc/optabs.c 2015-11-23 13:33:14.857205132 +0100 >@@ -5232,12 +5232,12 @@ shift_amt_for_vec_perm_mask (rtx sel) > return NULL_RTX; > > first = INTVAL (CONST_VECTOR_ELT (sel, 0)); >- if (first >= 2*nelt) >+ if (first >= nelt) > return NULL_RTX; > for (i = 1; i < nelt; i++) > { > int idx = INTVAL (CONST_VECTOR_ELT (sel, i)); >- unsigned int expected = (i + first) & (2 * nelt - 1); >+ unsigned int expected = i + first; > /* Indices into the second vector are all equivalent. */ > if (idx < 0 || (MIN (nelt, (unsigned) idx) != MIN (nelt, expected))) > return NULL_RTX; >--- gcc/testsuite/gcc.target/i386/pr68483-1.c.jj 2015-11-23 >14:27:54.213534756 +0100 >+++ gcc/testsuite/gcc.target/i386/pr68483-1.c 2015-11-23 >14:33:57.810362424 +0100 >@@ -0,0 +1,22 @@ >+/* PR target/68483 */ >+/* { dg-do compile } */ >+/* { dg-options "-O2 -ftree-vectorize -msse2 -mno-sse3" } */ >+ >+void >+test (int *input, int *out, unsigned x1, unsigned x2) >+{ >+ unsigned i, j; >+ unsigned end = x1; >+ >+ for (i = j = 0; i < 1000; i++) >+ { >+ int sum = 0; >+ end += x2; >+ for (; j < end; j++) >+ sum += input[j]; >+ out[i] = sum; >+ } >+} >+ >+/* { dg-final { scan-assembler "psrldq\[^\n\r]*(8,|, 8)" { target ia32 >} } } */ >+/* { dg-final { scan-assembler "psrldq\[^\n\r]*(4,|, 4)" { target ia32 >} } } */ >--- gcc/testsuite/gcc.target/i386/pr68483-2.c.jj 2015-11-23 >14:33:22.436865628 +0100 >+++ gcc/testsuite/gcc.target/i386/pr68483-2.c 2015-11-23 >14:34:33.716851638 +0100 >@@ -0,0 +1,15 @@ >+/* PR target/68483 */ >+/* { dg-do compile } */ >+/* { dg-options "-O2 -msse2 -mno-sse3" } */ >+ >+typedef int V __attribute__((vector_size (16))); >+ >+void >+foo (V *a, V *b) >+{ >+ V c = { 0, 0, 0, 0 }; >+ V d = { 1, 2, 3, 4 }; >+ *a = __builtin_shuffle (*b, c, d); >+} >+ >+/* { dg-final { scan-assembler "psrldq\[^\n\r]*(4,|, 4)" } } */ > > Jakub
--- gcc/tree-vect-generic.c.jj 2015-11-23 13:29:41.959236201 +0100 +++ gcc/tree-vect-generic.c 2015-11-23 14:13:10.378094173 +0100 @@ -1272,6 +1272,30 @@ lower_vec_perm (gimple_stmt_iterator *gs update_stmt (stmt); return; } + /* Also detect vec_shr pattern - VEC_PERM_EXPR with zero + vector as VEC1 and a right element shift MASK. */ + if (optab_handler (vec_shr_optab, TYPE_MODE (vect_type)) + != CODE_FOR_nothing + && TREE_CODE (vec1) == VECTOR_CST + && initializer_zerop (vec1) + && sel_int[0] + && sel_int[0] < elements) + { + for (i = 1; i < elements; ++i) + { + unsigned int expected = i + sel_int[0]; + /* Indices into the second vector are all equivalent. */ + if (MIN (elements, (unsigned) sel_int[i]) + != MIN (elements, expected)) + break; + } + if (i == elements) + { + gimple_assign_set_rhs3 (stmt, mask); + update_stmt (stmt); + return; + } + } } else if (can_vec_perm_p (TYPE_MODE (vect_type), true, NULL)) return; --- gcc/optabs.c.jj 2015-11-23 13:29:41.706239800 +0100 +++ gcc/optabs.c 2015-11-23 13:33:14.857205132 +0100 @@ -5232,12 +5232,12 @@ shift_amt_for_vec_perm_mask (rtx sel) return NULL_RTX; first = INTVAL (CONST_VECTOR_ELT (sel, 0)); - if (first >= 2*nelt) + if (first >= nelt) return NULL_RTX; for (i = 1; i < nelt; i++) { int idx = INTVAL (CONST_VECTOR_ELT (sel, i)); - unsigned int expected = (i + first) & (2 * nelt - 1); + unsigned int expected = i + first; /* Indices into the second vector are all equivalent. */ if (idx < 0 || (MIN (nelt, (unsigned) idx) != MIN (nelt, expected))) return NULL_RTX; --- gcc/testsuite/gcc.target/i386/pr68483-1.c.jj 2015-11-23 14:27:54.213534756 +0100 +++ gcc/testsuite/gcc.target/i386/pr68483-1.c 2015-11-23 14:33:57.810362424 +0100 @@ -0,0 +1,22 @@ +/* PR target/68483 */ +/* { dg-do compile } */ +/* { dg-options "-O2 -ftree-vectorize -msse2 -mno-sse3" } */ + +void +test (int *input, int *out, unsigned x1, unsigned x2) +{ + unsigned i, j; + unsigned end = x1; + + for (i = j = 0; i < 1000; i++) + { + int sum = 0; + end += x2; + for (; j < end; j++) + sum += input[j]; + out[i] = sum; + } +} + +/* { dg-final { scan-assembler "psrldq\[^\n\r]*(8,|, 8)" { target ia32 } } } */ +/* { dg-final { scan-assembler "psrldq\[^\n\r]*(4,|, 4)" { target ia32 } } } */ --- gcc/testsuite/gcc.target/i386/pr68483-2.c.jj 2015-11-23 14:33:22.436865628 +0100 +++ gcc/testsuite/gcc.target/i386/pr68483-2.c 2015-11-23 14:34:33.716851638 +0100 @@ -0,0 +1,15 @@ +/* PR target/68483 */ +/* { dg-do compile } */ +/* { dg-options "-O2 -msse2 -mno-sse3" } */ + +typedef int V __attribute__((vector_size (16))); + +void +foo (V *a, V *b) +{ + V c = { 0, 0, 0, 0 }; + V d = { 1, 2, 3, 4 }; + *a = __builtin_shuffle (*b, c, d); +} + +/* { dg-final { scan-assembler "psrldq\[^\n\r]*(4,|, 4)" } } */