On Wed, 9 Oct 2019 at 08:14, Prathamesh Kulkarni
<prathamesh.kulka...@linaro.org> wrote:
>
> On Tue, 8 Oct 2019 at 13:21, Richard Sandiford
> <richard.sandif...@arm.com> wrote:
> >
> > Leaving the main review to Richard, just some comments...
> >
> > Prathamesh Kulkarni <prathamesh.kulka...@linaro.org> writes:
> > > @@ -9774,6 +9777,10 @@ vect_is_simple_cond (tree cond, vec_info *vinfo,
> > >
> > > When STMT_INFO is vectorized as a nested cycle, for_reduction is true.
> > >
> > > + For COND_EXPR<C, T, E> if T comes from masked load, and is conditional
> > > + on C, we apply loop mask to result of vector comparison, if it's
> > > present.
> > > + Similarly for E, if it is conditional on !C.
> > > +
> > > Return true if STMT_INFO is vectorizable in this way. */
> > >
> > > bool
> >
> > I think this is a bit misleading. But IMO it'd be better not to have
> > a comment here and just rely on the one in the main function body.
> > This optimisation isn't really changing the vectorisation strategy,
> > and the comment could easily get forgotten if things change in future.
> >
> > > [...]
> > > @@ -9999,6 +10006,35 @@ vectorizable_condition (stmt_vec_info stmt_info,
> > > gimple_stmt_iterator *gsi,
> > > /* Handle cond expr. */
> > > for (j = 0; j < ncopies; j++)
> > > {
> > > + tree loop_mask = NULL_TREE;
> > > + bool swap_cond_operands = false;
> > > +
> > > + /* Look up if there is a loop mask associated with the
> > > + scalar cond, or it's inverse. */
> >
> > Maybe:
> >
> > See whether another part of the vectorized code applies a loop
> > mask to the condition, or to its inverse.
> >
> > > +
> > > + if (loop_vinfo && LOOP_VINFO_FULLY_MASKED_P (loop_vinfo))
> > > + {
> > > + scalar_cond_masked_key cond (cond_expr, ncopies);
> > > + if (loop_vinfo->scalar_cond_masked_set.contains (cond))
> > > + {
> > > + vec_loop_masks *masks = &LOOP_VINFO_MASKS (loop_vinfo);
> > > + loop_mask = vect_get_loop_mask (gsi, masks, ncopies, vectype,
> > > j);
> > > + }
> > > + else
> > > + {
> > > + bool honor_nans = HONOR_NANS (TREE_TYPE (cond.op0));
> > > + cond.code = invert_tree_comparison (cond.code, honor_nans);
> > > + if (loop_vinfo->scalar_cond_masked_set.contains (cond))
> > > + {
> > > + vec_loop_masks *masks = &LOOP_VINFO_MASKS (loop_vinfo);
> > > + loop_mask = vect_get_loop_mask (gsi, masks, ncopies,
> > > + vectype, j);
> > > + cond_code = cond.code;
> > > + swap_cond_operands = true;
> > > + }
> > > + }
> > > + }
> > > +
> > > stmt_vec_info new_stmt_info = NULL;
> > > if (j == 0)
> > > {
> > > @@ -10114,6 +10153,47 @@ vectorizable_condition (stmt_vec_info stmt_info,
> > > gimple_stmt_iterator *gsi,
> > > }
> > > }
> > > }
> > > +
> > > + /* If loop mask is present, then AND it with
> >
> > Maybe "If we decided to apply a loop mask, ..."
> >
> > > + result of vec comparison, so later passes (fre4)
> >
> > Probably better not to name the pass -- could easily change in future.
> >
> > > + will reuse the same condition used in masked load.
> >
> > Could be a masked store, or potentially other things too.
> > So maybe just "will reuse the masked condition"?
> >
> > > +
> > > + For example:
> > > + for (int i = 0; i < 100; ++i)
> > > + x[i] = y[i] ? z[i] : 10;
> > > +
> > > + results in following optimized GIMPLE:
> > > +
> > > + mask__35.8_43 = vect__4.7_41 != { 0, ... };
> > > + vec_mask_and_46 = loop_mask_40 & mask__35.8_43;
> > > + _19 = &MEM[base: z_12(D), index: ivtmp_56, step: 4, offset:
> > > 0B];
> > > + vect_iftmp.11_47 = .MASK_LOAD (_19, 4B, vec_mask_and_46);
> > > + vect_iftmp.12_52 = VEC_COND_EXPR <vec_mask_and_46,
> > > + vect_iftmp.11_47, { 10, ...
> > > }>;
> > > +
> > > + instead of recomputing vec != { 0, ... } in vec_cond_expr */
> >
> > That's true, but gives the impression that avoiding the vec != { 0, ... }
> > is the main goal, whereas we could do that just by forcing a three-operand
> > COND_EXPR. It's really more about making sure that vec != { 0, ... }
> > and its masked form aren't both live at the same time. So maybe:
> >
> > instead of using a masked and unmasked forms of
> > vect__4.7_41 != { 0, ... } (masked in the MASK_LOAD,
> > unmasked in the VEC_COND_EXPR). */
> >
> Hi Richard,
> Thanks for the suggestions, I have updated comments in the attached patch.
Hi,
The attached patch is rebased on trunk, and after PR91532 fix, the
hunk for fmla_2.c is no
longer required.
Thanks,
Prathamesh
>
> Thanks,
> Prathamesh
> > Thanks,
> > Richard
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/cond_cnot_2.c b/gcc/testsuite/gcc.target/aarch64/sve/cond_cnot_2.c
index d689e21dc11..3df2431be38 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/cond_cnot_2.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/cond_cnot_2.c
@@ -32,4 +32,4 @@ TEST_ALL (DEF_LOOP)
/* { dg-final { scan-assembler-not {\tmov\tz} } } */
/* { dg-final { scan-assembler-not {\tmovprfx\t} } } */
/* Currently we canonicalize the ?: so that !b[i] is the "false" value. */
-/* { dg-final { scan-assembler-not {\tsel\t} { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-not {\tsel\t} } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/cond_convert_1.c b/gcc/testsuite/gcc.target/aarch64/sve/cond_convert_1.c
index dcc30768f88..86064ebfcba 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/cond_convert_1.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/cond_convert_1.c
@@ -11,7 +11,10 @@
INT_TYPE *__restrict pred, int n) \
{ \
for (int i = 0; i < n; ++i) \
- r[i] = pred[i] ? (FLOAT_TYPE) a[i] : b[i]; \
+ { \
+ FLOAT_TYPE bi = b[i]; \
+ r[i] = pred[i] ? (FLOAT_TYPE) a[i] : bi; \
+ } \
}
#define TEST_ALL(T) \
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/cond_convert_4.c b/gcc/testsuite/gcc.target/aarch64/sve/cond_convert_4.c
index 7e5f2a73ed9..e3a947b2698 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/cond_convert_4.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/cond_convert_4.c
@@ -11,7 +11,10 @@
INT_TYPE *__restrict pred, int n) \
{ \
for (int i = 0; i < n; ++i) \
- r[i] = pred[i] ? (INT_TYPE) a[i] : b[i]; \
+ { \
+ INT_TYPE bi = b[i]; \
+ r[i] = pred[i] ? (INT_TYPE) a[i] : bi; \
+ } \
}
#define TEST_ALL(T) \
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/cond_unary_2.c b/gcc/testsuite/gcc.target/aarch64/sve/cond_unary_2.c
index 991ccf016d1..97d1b8f5d45 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/cond_unary_2.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/cond_unary_2.c
@@ -13,7 +13,10 @@
TYPE *__restrict pred, int n) \
{ \
for (int i = 0; i < n; ++i) \
- r[i] = pred[i] ? OP (a[i]) : b[i]; \
+ { \
+ TYPE bi = b[i]; \
+ r[i] = pred[i] ? OP (a[i]) : bi; \
+ } \
}
#define TEST_INT_TYPE(T, TYPE) \
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/vcond_4.c b/gcc/testsuite/gcc.target/aarch64/sve/vcond_4.c
index 00d84760a19..b38f23e87ba 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/vcond_4.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/vcond_4.c
@@ -98,24 +98,24 @@ TEST_CMP (nugt)
/* { dg-final { scan-assembler-times {\tfcmne\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 30 { xfail *-*-* } } } */
/* 5 for lt, 5 for ult and 5 for nult. */
-/* { dg-final { scan-assembler-times {\tfcmlt\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0\n} 15 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmlt\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 30 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tfcmlt\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0\n} 15 } } */
+/* { dg-final { scan-assembler-times {\tfcmlt\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 30 } } */
/* 5 for le, 5 for ule and 5 for nule. */
-/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0\n} 15 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 30 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0\n} 15 } } */
+/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 30 } } */
/* 5 for gt, 5 for ugt and 5 for nugt. */
-/* { dg-final { scan-assembler-times {\tfcmgt\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0\n} 15 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmgt\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 30 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tfcmgt\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0\n} 15 } } */
+/* { dg-final { scan-assembler-times {\tfcmgt\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 30 } } */
/* 5 for ge, 5 for uge and 5 for nuge. */
-/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0\n} 15 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 30 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0\n} 15 } } */
+/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 30 } } */
/* { dg-final { scan-assembler-not {\tfcmuo\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0\n} } } */
/* 3 loops * 5 invocations for all 12 unordered comparisons. */
-/* { dg-final { scan-assembler-times {\tfcmuo\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 180 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tfcmuo\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s\n} 180 } } */
/* { dg-final { scan-assembler-times {\tfcmeq\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0\n} 7 { xfail *-*-* } } } */
/* { dg-final { scan-assembler-times {\tfcmeq\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 14 { xfail *-*-* } } } */
@@ -123,19 +123,19 @@ TEST_CMP (nugt)
/* { dg-final { scan-assembler-times {\tfcmne\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0\n} 21 { xfail *-*-* } } } */
/* { dg-final { scan-assembler-times {\tfcmne\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 42 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmlt\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0\n} 21 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmlt\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 42 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tfcmlt\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0\n} 21 } } */
+/* { dg-final { scan-assembler-times {\tfcmlt\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 42 } } */
-/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0\n} 21 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 42 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0\n} 21 } } */
+/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 42 } } */
-/* { dg-final { scan-assembler-times {\tfcmgt\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0\n} 21 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmgt\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 42 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tfcmgt\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0\n} 21 } } */
+/* { dg-final { scan-assembler-times {\tfcmgt\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 42 } } */
-/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0\n} 21 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 42 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0\n} 21 } } */
+/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 42 } } */
/* { dg-final { scan-assembler-not {\tfcmuo\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0\n} } } */
/* 3 loops * 5 invocations, with 2 invocations having ncopies == 2,
for all 12 unordered comparisons. */
-/* { dg-final { scan-assembler-times {\tfcmuo\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 252 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tfcmuo\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d\n} 252 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/vcond_5.c b/gcc/testsuite/gcc.target/aarch64/sve/vcond_5.c
index 23bfb7b2649..2f16fbff522 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/vcond_5.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/vcond_5.c
@@ -19,16 +19,16 @@
/* { dg-final { scan-assembler-times {\tfcmlt\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s} 40 { xfail *-*-* } } } */
/* 5 for le, 5 for ule and 5 for nule. */
-/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0} 15 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s} 30 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0} 15 } } */
+/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s} 30 } } */
/* 5 for gt, 5 for ugt, 5 for nueq and 5 for nugt. */
/* { dg-final { scan-assembler-times {\tfcmgt\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0} 20 { xfail *-*-* } } } */
/* { dg-final { scan-assembler-times {\tfcmgt\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s} 40 { xfail *-*-* } } } */
/* 5 for ge, 5 for uge and 5 for nuge. */
-/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0} 15 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s} 30 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0} 15 } } */
+/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, z[0-9]+\.s} 30 } } */
/* { dg-final { scan-assembler-not {\tfcmuo\tp[0-9]+\.s, p[0-7]/z, z[0-9]+\.s, #0\.0} } } */
/* 3 loops * 5 invocations for ordered, unordered amd ueq. */
@@ -43,14 +43,14 @@
/* { dg-final { scan-assembler-times {\tfcmlt\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0} 28 { xfail *-*-* } } } */
/* { dg-final { scan-assembler-times {\tfcmlt\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d} 56 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0} 21 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d} 42 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0} 21 } } */
+/* { dg-final { scan-assembler-times {\tfcmle\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d} 42 } } */
/* { dg-final { scan-assembler-times {\tfcmgt\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0} 28 { xfail *-*-* } } } */
/* { dg-final { scan-assembler-times {\tfcmgt\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d} 56 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0} 21 { xfail *-*-* } } } */
-/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d} 42 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0} 21 } } */
+/* { dg-final { scan-assembler-times {\tfcmge\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, z[0-9]+\.d} 42 } } */
/* { dg-final { scan-assembler-not {\tfcmuo\tp[0-9]+\.d, p[0-7]/z, z[0-9]+\.d, #0\.0} } } */
/* 3 loops * 5 invocations, with 2 invocations having ncopies == 2,
diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
index de018acefad..e0ea1769d7f 100644
--- a/gcc/tree-vect-loop.c
+++ b/gcc/tree-vect-loop.c
@@ -6525,7 +6525,7 @@ vectorizable_reduction (stmt_vec_info stmt_info, slp_tree slp_node,
}
else
vect_record_loop_mask (loop_vinfo, masks, ncopies * vec_num,
- vectype_in);
+ vectype_in, NULL);
}
if (dump_enabled_p ()
&& reduction_type == FOLD_LEFT_REDUCTION)
@@ -7756,7 +7756,7 @@ vectorizable_live_operation (stmt_vec_info stmt_info,
gcc_assert (ncopies == 1 && !slp_node);
vect_record_loop_mask (loop_vinfo,
&LOOP_VINFO_MASKS (loop_vinfo),
- 1, vectype);
+ 1, vectype, NULL);
}
}
return true;
@@ -7955,11 +7955,12 @@ vect_double_mask_nunits (tree type)
/* Record that a fully-masked version of LOOP_VINFO would need MASKS to
contain a sequence of NVECTORS masks that each control a vector of type
- VECTYPE. */
+ VECTYPE. If SCALAR_MASK is nonnull, the fully-masked loop would AND
+ these vector masks with the vector version of SCALAR_MASK. */
void
vect_record_loop_mask (loop_vec_info loop_vinfo, vec_loop_masks *masks,
- unsigned int nvectors, tree vectype)
+ unsigned int nvectors, tree vectype, tree scalar_mask)
{
gcc_assert (nvectors != 0);
if (masks->length () < nvectors)
@@ -7970,6 +7971,13 @@ vect_record_loop_mask (loop_vec_info loop_vinfo, vec_loop_masks *masks,
unsigned int nscalars_per_iter
= exact_div (nvectors * TYPE_VECTOR_SUBPARTS (vectype),
LOOP_VINFO_VECT_FACTOR (loop_vinfo)).to_constant ();
+
+ if (scalar_mask)
+ {
+ scalar_cond_masked_key cond (scalar_mask, nvectors);
+ loop_vinfo->scalar_cond_masked_set.add (cond);
+ }
+
if (rgm->max_nscalars_per_iter < nscalars_per_iter)
{
rgm->max_nscalars_per_iter = nscalars_per_iter;
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index e606945d536..046af80fa99 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -1879,7 +1879,8 @@ static tree permute_vec_elements (tree, tree, tree, stmt_vec_info,
says how the load or store is going to be implemented and GROUP_SIZE
is the number of load or store statements in the containing group.
If the access is a gather load or scatter store, GS_INFO describes
- its arguments.
+ its arguments. If the load or store is conditional, SCALAR_MASK is the
+ condition under which it occurs.
Clear LOOP_VINFO_CAN_FULLY_MASK_P if a fully-masked loop is not
supported, otherwise record the required mask types. */
@@ -1888,7 +1889,7 @@ static void
check_load_store_masking (loop_vec_info loop_vinfo, tree vectype,
vec_load_store_type vls_type, int group_size,
vect_memory_access_type memory_access_type,
- gather_scatter_info *gs_info)
+ gather_scatter_info *gs_info, tree scalar_mask)
{
/* Invariant loads need no special support. */
if (memory_access_type == VMAT_INVARIANT)
@@ -1912,7 +1913,7 @@ check_load_store_masking (loop_vec_info loop_vinfo, tree vectype,
return;
}
unsigned int ncopies = vect_get_num_copies (loop_vinfo, vectype);
- vect_record_loop_mask (loop_vinfo, masks, ncopies, vectype);
+ vect_record_loop_mask (loop_vinfo, masks, ncopies, vectype, scalar_mask);
return;
}
@@ -1936,7 +1937,7 @@ check_load_store_masking (loop_vec_info loop_vinfo, tree vectype,
return;
}
unsigned int ncopies = vect_get_num_copies (loop_vinfo, vectype);
- vect_record_loop_mask (loop_vinfo, masks, ncopies, vectype);
+ vect_record_loop_mask (loop_vinfo, masks, ncopies, vectype, scalar_mask);
return;
}
@@ -1974,7 +1975,7 @@ check_load_store_masking (loop_vec_info loop_vinfo, tree vectype,
poly_uint64 vf = LOOP_VINFO_VECT_FACTOR (loop_vinfo);
unsigned int nvectors;
if (can_div_away_from_zero_p (group_size * vf, nunits, &nvectors))
- vect_record_loop_mask (loop_vinfo, masks, nvectors, vectype);
+ vect_record_loop_mask (loop_vinfo, masks, nvectors, vectype, scalar_mask);
else
gcc_unreachable ();
}
@@ -3436,7 +3437,9 @@ vectorizable_call (stmt_vec_info stmt_info, gimple_stmt_iterator *gsi,
unsigned int nvectors = (slp_node
? SLP_TREE_NUMBER_OF_VEC_STMTS (slp_node)
: ncopies);
- vect_record_loop_mask (loop_vinfo, masks, nvectors, vectype_out);
+ tree scalar_mask = gimple_call_arg (stmt_info->stmt, mask_opno);
+ vect_record_loop_mask (loop_vinfo, masks, nvectors,
+ vectype_out, scalar_mask);
}
return true;
}
@@ -7390,7 +7393,7 @@ vectorizable_store (stmt_vec_info stmt_info, gimple_stmt_iterator *gsi,
if (loop_vinfo
&& LOOP_VINFO_CAN_FULLY_MASK_P (loop_vinfo))
check_load_store_masking (loop_vinfo, vectype, vls_type, group_size,
- memory_access_type, &gs_info);
+ memory_access_type, &gs_info, mask);
STMT_VINFO_TYPE (stmt_info) = store_vec_info_type;
vect_model_store_cost (stmt_info, ncopies, rhs_dt, memory_access_type,
@@ -8637,7 +8640,7 @@ vectorizable_load (stmt_vec_info stmt_info, gimple_stmt_iterator *gsi,
if (loop_vinfo
&& LOOP_VINFO_CAN_FULLY_MASK_P (loop_vinfo))
check_load_store_masking (loop_vinfo, vectype, VLS_LOAD, group_size,
- memory_access_type, &gs_info);
+ memory_access_type, &gs_info, mask);
STMT_VINFO_TYPE (stmt_info) = load_vec_info_type;
vect_model_load_cost (stmt_info, ncopies, memory_access_type,
@@ -10007,6 +10010,35 @@ vectorizable_condition (stmt_vec_info stmt_info, gimple_stmt_iterator *gsi,
/* Handle cond expr. */
for (j = 0; j < ncopies; j++)
{
+ tree loop_mask = NULL_TREE;
+ bool swap_cond_operands = false;
+
+ /* See whether another part of the vectorized code applies a loop
+ mask to the condition, or to its inverse. */
+
+ if (loop_vinfo && LOOP_VINFO_FULLY_MASKED_P (loop_vinfo))
+ {
+ scalar_cond_masked_key cond (cond_expr, ncopies);
+ if (loop_vinfo->scalar_cond_masked_set.contains (cond))
+ {
+ vec_loop_masks *masks = &LOOP_VINFO_MASKS (loop_vinfo);
+ loop_mask = vect_get_loop_mask (gsi, masks, ncopies, vectype, j);
+ }
+ else
+ {
+ bool honor_nans = HONOR_NANS (TREE_TYPE (cond.op0));
+ cond.code = invert_tree_comparison (cond.code, honor_nans);
+ if (loop_vinfo->scalar_cond_masked_set.contains (cond))
+ {
+ vec_loop_masks *masks = &LOOP_VINFO_MASKS (loop_vinfo);
+ loop_mask = vect_get_loop_mask (gsi, masks, ncopies,
+ vectype, j);
+ cond_code = cond.code;
+ swap_cond_operands = true;
+ }
+ }
+ }
+
stmt_vec_info new_stmt_info = NULL;
if (j == 0)
{
@@ -10084,6 +10116,9 @@ vectorizable_condition (stmt_vec_info stmt_info, gimple_stmt_iterator *gsi,
vec_then_clause = vec_oprnds2[i];
vec_else_clause = vec_oprnds3[i];
+ if (swap_cond_operands)
+ std::swap (vec_then_clause, vec_else_clause);
+
if (masked)
vec_compare = vec_cond_lhs;
else
@@ -10122,6 +10157,48 @@ vectorizable_condition (stmt_vec_info stmt_info, gimple_stmt_iterator *gsi,
}
}
}
+
+ /* If we decided to apply a loop mask to result of vec
+ comparison, so later passes will reuse the same condition.
+
+ For example:
+ for (int i = 0; i < 100; ++i)
+ x[i] = y[i] ? z[i] : 10;
+
+ results in following optimized GIMPLE:
+
+ mask__35.8_43 = vect__4.7_41 != { 0, ... };
+ vec_mask_and_46 = loop_mask_40 & mask__35.8_43;
+ _19 = &MEM[base: z_12(D), index: ivtmp_56, step: 4, offset: 0B];
+ vect_iftmp.11_47 = .MASK_LOAD (_19, 4B, vec_mask_and_46);
+ vect_iftmp.12_52 = VEC_COND_EXPR <vec_mask_and_46,
+ vect_iftmp.11_47, { 10, ... }>;
+
+ instead of using a masked and unmasked forms of
+ vec != { 0, ... } (masked in the MASK_LOAD,
+ unmasked in the VEC_COND_EXPR). */
+
+ if (loop_mask)
+ {
+ if (COMPARISON_CLASS_P (vec_compare))
+ {
+ tree tmp = make_ssa_name (vec_cmp_type);
+ tree op0 = TREE_OPERAND (vec_compare, 0);
+ tree op1 = TREE_OPERAND (vec_compare, 1);
+ gassign *g = gimple_build_assign (tmp,
+ TREE_CODE (vec_compare),
+ op0, op1);
+ vect_finish_stmt_generation (stmt_info, g, gsi);
+ vec_compare = tmp;
+ }
+
+ tree tmp2 = make_ssa_name (vec_cmp_type);
+ gassign *g = gimple_build_assign (tmp2, BIT_AND_EXPR,
+ vec_compare, loop_mask);
+ vect_finish_stmt_generation (stmt_info, g, gsi);
+ vec_compare = tmp2;
+ }
+
if (reduction_type == EXTRACT_LAST_REDUCTION)
{
if (!is_gimple_val (vec_compare))
diff --git a/gcc/tree-vectorizer.c b/gcc/tree-vectorizer.c
index 3e8637f070d..27304181f9f 100644
--- a/gcc/tree-vectorizer.c
+++ b/gcc/tree-vectorizer.c
@@ -1516,3 +1516,36 @@ make_pass_ipa_increase_alignment (gcc::context *ctxt)
{
return new pass_ipa_increase_alignment (ctxt);
}
+
+/* If code(T) is comparison op or def of comparison stmt,
+ extract it's operands.
+ Else return <NE_EXPR, T, 0>. */
+
+void
+scalar_cond_masked_key::get_cond_ops_from_tree (tree t)
+{
+ if (TREE_CODE_CLASS (TREE_CODE (t)) == tcc_comparison)
+ {
+ this->code = TREE_CODE (t);
+ this->op0 = TREE_OPERAND (t, 0);
+ this->op1 = TREE_OPERAND (t, 1);
+ return;
+ }
+
+ if (TREE_CODE (t) == SSA_NAME)
+ if (gassign *stmt = dyn_cast<gassign *> (SSA_NAME_DEF_STMT (t)))
+ {
+ tree_code code = gimple_assign_rhs_code (stmt);
+ if (TREE_CODE_CLASS (code) == tcc_comparison)
+ {
+ this->code = code;
+ this->op0 = gimple_assign_rhs1 (stmt);
+ this->op1 = gimple_assign_rhs2 (stmt);
+ return;
+ }
+ }
+
+ this->code = NE_EXPR;
+ this->op0 = t;
+ this->op1 = build_zero_cst (TREE_TYPE (t));
+}
diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index 291304fe95e..d563420e926 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -177,7 +177,75 @@ public:
#define SLP_TREE_TWO_OPERATORS(S) (S)->two_operators
#define SLP_TREE_DEF_TYPE(S) (S)->def_type
+/* Key for map that records association between
+ scalar conditions and corresponding loop mask, and
+ is populated by vect_record_loop_mask. */
+
+struct scalar_cond_masked_key
+{
+ scalar_cond_masked_key (tree t, unsigned ncopies_)
+ : ncopies (ncopies_)
+ {
+ get_cond_ops_from_tree (t);
+ }
+
+ void get_cond_ops_from_tree (tree);
+
+ unsigned ncopies;
+ tree_code code;
+ tree op0;
+ tree op1;
+};
+template<>
+struct default_hash_traits<scalar_cond_masked_key>
+{
+ typedef scalar_cond_masked_key compare_type;
+ typedef scalar_cond_masked_key value_type;
+
+ static inline hashval_t
+ hash (value_type v)
+ {
+ inchash::hash h;
+ h.add_int (v.code);
+ inchash::add_expr (v.op0, h, 0);
+ inchash::add_expr (v.op1, h, 0);
+ h.add_int (v.ncopies);
+ return h.end ();
+ }
+
+ static inline bool
+ equal (value_type existing, value_type candidate)
+ {
+ return (existing.ncopies == candidate.ncopies
+ && existing.code == candidate.code
+ && operand_equal_p (existing.op0, candidate.op0, 0)
+ && operand_equal_p (existing.op1, candidate.op1, 0));
+ }
+
+ static inline void
+ mark_empty (value_type &v)
+ {
+ v.ncopies = 0;
+ }
+
+ static inline bool
+ is_empty (value_type v)
+ {
+ return v.ncopies == 0;
+ }
+
+ static inline void mark_deleted (value_type &) {}
+
+ static inline bool is_deleted (const value_type &)
+ {
+ return false;
+ }
+
+ static inline void remove (value_type &) {}
+};
+
+typedef hash_set<scalar_cond_masked_key> scalar_cond_masked_set_type;
/* Describes two objects whose addresses must be unequal for the vectorized
loop to be valid. */
@@ -258,6 +326,9 @@ public:
/* Cost data used by the target cost model. */
void *target_cost_data;
+ /* Set of scalar conditions that have loop mask applied. */
+ scalar_cond_masked_set_type scalar_cond_masked_set;
+
private:
stmt_vec_info new_stmt_vec_info (gimple *stmt);
void set_vinfo_for_stmt (gimple *, stmt_vec_info);
@@ -1642,7 +1713,7 @@ extern void vect_gen_vector_loop_niters (loop_vec_info, tree, tree *,
extern tree vect_halve_mask_nunits (tree);
extern tree vect_double_mask_nunits (tree);
extern void vect_record_loop_mask (loop_vec_info, vec_loop_masks *,
- unsigned int, tree);
+ unsigned int, tree, tree);
extern tree vect_get_loop_mask (gimple_stmt_iterator *, vec_loop_masks *,
unsigned int, tree, unsigned int);
extern stmt_vec_info info_for_reduction (stmt_vec_info);
