On Wed, Jul 17, 2024 at 5:24 AM Richard Biener
<richard.guent...@gmail.com> wrote:
>
> On Tue, Jul 16, 2024 at 3:36 PM Eikansh Gupta <quic_eikag...@quicinc.com>
> wrote:
> >
> > This patch adds match pattern for `(a ? x : y) eq/ne (b ? x : y)`.
> > In forwprop1 pass, depending on the type of `a` and `b`, GCC produces
> > `vec_cond` or `cond_expr`. Based on the observation that `(x != y)` is
> > TRUE, the pattern can be optimized to produce `(a^b ? TRUE : FALSE)`.
> >
> > The patch adds match pattern for a, b:
> > (a ? x : y) != (b ? x : y) --> (a^b) ? TRUE : FALSE
> > (a ? x : y) == (b ? x : y) --> (a^b) ? FALSE : TRUE
> > (a ? x : y) != (b ? y : x) --> (a^b) ? TRUE : FALSE
> > (a ? x : y) == (b ? y : x) --> (a^b) ? FALSE : TRUE
>
> OK.
Pushed as r15-2106-g44fcc1ca11e7ea (with one small change to the
commit message in the changelog where tabs should be used before the
*; most likely a copy and paste error).
Thanks,
Andrew
>
> Richard.
>
> > PR tree-optimization/111150
> >
> > gcc/ChangeLog:
> >
> > * match.pd (`(a ? x : y) eq/ne (b ? x : y)`): New pattern.
> > (`(a ? x : y) eq/ne (b ? y : x)`): New pattern.
> >
> > gcc/testsuite/ChangeLog:
> >
> > * gcc.dg/tree-ssa/pr111150.c: New test.
> > * gcc.dg/tree-ssa/pr111150-1.c: New test.
> > * g++.dg/tree-ssa/pr111150.C: New test.
> >
> > Signed-off-by: Eikansh Gupta <quic_eikag...@quicinc.com>
> > ---
> > gcc/match.pd | 15 +++++
> > gcc/testsuite/g++.dg/tree-ssa/pr111150.C | 33 ++++++++++
> > gcc/testsuite/gcc.dg/tree-ssa/pr111150-1.c | 72 ++++++++++++++++++++++
> > gcc/testsuite/gcc.dg/tree-ssa/pr111150.c | 22 +++++++
> > 4 files changed, 142 insertions(+)
> > create mode 100644 gcc/testsuite/g++.dg/tree-ssa/pr111150.C
> > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr111150-1.c
> > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr111150.c
> >
> > diff --git a/gcc/match.pd b/gcc/match.pd
> > index 3759c64d461..7c125255ea3 100644
> > --- a/gcc/match.pd
> > +++ b/gcc/match.pd
> > @@ -5577,6 +5577,21 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> > (vec_cond (bit_and (bit_not @0) @1) @2 @3)))
> > #endif
> >
> > +/* (a ? x : y) != (b ? x : y) --> (a^b) ? TRUE : FALSE */
> > +/* (a ? x : y) == (b ? x : y) --> (a^b) ? FALSE : TRUE */
> > +/* (a ? x : y) != (b ? y : x) --> (a^b) ? FALSE : TRUE */
> > +/* (a ? x : y) == (b ? y : x) --> (a^b) ? TRUE : FALSE */
> > +(for cnd (cond vec_cond)
> > + (for eqne (eq ne)
> > + (simplify
> > + (eqne:c (cnd @0 @1 @2) (cnd @3 @1 @2))
> > + (cnd (bit_xor @0 @3) { constant_boolean_node (eqne == NE_EXPR, type); }
> > + { constant_boolean_node (eqne != NE_EXPR, type); }))
> > + (simplify
> > + (eqne:c (cnd @0 @1 @2) (cnd @3 @2 @1))
> > + (cnd (bit_xor @0 @3) { constant_boolean_node (eqne != NE_EXPR, type); }
> > + { constant_boolean_node (eqne == NE_EXPR, type); }))))
> > +
> > /* Canonicalize mask ? { 0, ... } : { -1, ...} to ~mask if the mask
> > types are compatible. */
> > (simplify
> > diff --git a/gcc/testsuite/g++.dg/tree-ssa/pr111150.C
> > b/gcc/testsuite/g++.dg/tree-ssa/pr111150.C
> > new file mode 100644
> > index 00000000000..ca02d8dc51e
> > --- /dev/null
> > +++ b/gcc/testsuite/g++.dg/tree-ssa/pr111150.C
> > @@ -0,0 +1,33 @@
> > +/* PR tree-optimization/111150 */
> > +/* { dg-do compile } */
> > +/* { dg-options "-O1 -fdump-tree-forwprop1" } */
> > +typedef int v4si __attribute((__vector_size__(4 * sizeof(int))));
> > +
> > +/* Before the patch, VEC_COND_EXPR was generated for each statement in the
> > + function. This resulted in 3 VEC_COND_EXPR. */
> > +v4si f1_(v4si a, v4si b, v4si c, v4si d, v4si e, v4si f) {
> > + v4si X = a == b ? e : f;
> > + v4si Y = c == d ? e : f;
> > + return (X != Y);
> > +}
> > +
> > +v4si f2_(v4si a, v4si b, v4si c, v4si d, v4si e, v4si f) {
> > + v4si X = a == b ? e : f;
> > + v4si Y = c == d ? e : f;
> > + return (X == Y);
> > +}
> > +
> > +v4si f3_(v4si a, v4si b, v4si c, v4si d, v4si e, v4si f) {
> > + v4si X = a == b ? e : f;
> > + v4si Y = c == d ? f : e;
> > + return (X != Y);
> > +}
> > +
> > +v4si f4_(v4si a, v4si b, v4si c, v4si d, v4si e, v4si f) {
> > + v4si X = a == b ? e : f;
> > + v4si Y = c == d ? f : e;
> > + return (X == Y);
> > +}
> > +
> > +/* For each testcase, should produce only one VEC_COND_EXPR for X^Y. */
> > +/* { dg-final { scan-tree-dump-times " VEC_COND_EXPR " 4 "forwprop1" } } */
> > diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr111150-1.c
> > b/gcc/testsuite/gcc.dg/tree-ssa/pr111150-1.c
> > new file mode 100644
> > index 00000000000..6f4b21ac6bc
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr111150-1.c
> > @@ -0,0 +1,72 @@
> > +/* PR tree-optimization/111150 */
> > +/* { dg-do compile } */
> > +/* { dg-options "-O1 -fgimple -fdump-tree-forwprop1-raw" } */
> > +
> > +/* Checks if pattern (X ? e : f) == (Y ? e : f) gets optimized. */
> > +__GIMPLE()
> > +_Bool f1_(int a, int b, int c, int d, int e, int f) {
> > + _Bool X;
> > + _Bool Y;
> > + _Bool t;
> > + int t1;
> > + int t2;
> > + X = a == b;
> > + Y = c == d;
> > + /* Before the patch cond_expr was generated for these 2 statements. */
> > + t1 = X ? e : f;
> > + t2 = Y ? e : f;
> > + t = t1 == t2;
> > + return t;
> > +}
> > +
> > +/* Checks if pattern (X ? e : f) != (Y ? e : f) gets optimized. */
> > +__GIMPLE()
> > +_Bool f2_(int a, int b, int c, int d, int e, int f) {
> > + _Bool X;
> > + _Bool Y;
> > + _Bool t;
> > + int t1;
> > + int t2;
> > + X = a == b;
> > + Y = c == d;
> > + t1 = X ? e : f;
> > + t2 = Y ? e : f;
> > + t = t1 != t2;
> > + return t;
> > +}
> > +
> > +/* Checks if pattern (X ? e : f) == (Y ? f : e) gets optimized. */
> > +__GIMPLE()
> > +_Bool f3_(int a, int b, int c, int d, int e, int f) {
> > + _Bool X;
> > + _Bool Y;
> > + _Bool t;
> > + int t1;
> > + int t2;
> > + X = a == b;
> > + Y = c == d;
> > + t1 = X ? e : f;
> > + t2 = Y ? f : e;
> > + t = t1 == t2;
> > + return t;
> > +}
> > +
> > +/* Checks if pattern (X ? e : f) != (Y ? f : e) gets optimized. */
> > +__GIMPLE()
> > +_Bool f4_(int a, int b, int c, int d, int e, int f) {
> > + _Bool X;
> > + _Bool Y;
> > + _Bool t;
> > + int t1;
> > + int t2;
> > + X = a == b;
> > + Y = c == d;
> > + t1 = X ? e : f;
> > + t2 = Y ? f : e;
> > + t = t1 != t2;
> > + return t;
> > +}
> > +
> > +/* Should generate one bit_xor_expr for each testcase. */
> > +/* { dg-final { scan-tree-dump-not "cond_expr, " "forwprop1" } } */
> > +/* { dg-final { scan-tree-dump-times "bit_xor_expr, " 4 "forwprop1" } } */
> > diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr111150.c
> > b/gcc/testsuite/gcc.dg/tree-ssa/pr111150.c
> > new file mode 100644
> > index 00000000000..cf25c5d758c
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr111150.c
> > @@ -0,0 +1,22 @@
> > +/* PR tree-optimization/111150 */
> > +/* { dg-do compile } */
> > +/* { dg-options "-O1 -fdump-tree-forwprop1" } */
> > +
> > +typedef int v4si __attribute((__vector_size__(4 * sizeof(int))));
> > +
> > +/* Before the patch, VEC_COND_EXPR was generated for each statement in the
> > + function. This resulted in 3 VEC_COND_EXPR. */
> > +v4si f1_(v4si a, v4si b, v4si c, v4si d) {
> > + v4si X = a == b;
> > + v4si Y = c == d;
> > + return (X != Y);
> > +}
> > +
> > +v4si f2_(v4si a, v4si b, v4si c, v4si d) {
> > + v4si X = a == b;
> > + v4si Y = c == d;
> > + return (X == Y);
> > +}
> > +
> > +/* For each testcase, should produce only one VEC_COND_EXPR for X^Y. */
> > +/* { dg-final { scan-tree-dump-times " VEC_COND_EXPR " 2 "forwprop1" } } */
> > --
> > 2.17.1
> >
