On Mon, May 23, 2022 at 12:38:06PM +0200, Richard Biener wrote:
> On Sat, May 21, 2022 at 5:02 AM H.J. Lu via Gcc-patches
> <gcc-patches@gcc.gnu.org> wrote:
> >
> > When recording store for RTL dead store elimination, check if the source
> > register is set only once to a constant. If yes, record the constant
> > as the store source. It eliminates unrolled zero stores after memset 0
> > in a loop where a vector register is used as the zero store source.
> >
> > gcc/
> >
> > PR rtl-optimization/105638
> > * dse.cc (record_store): Use the constant source if the source
> > register is set only once.
> >
> > gcc/testsuite/
> >
> > PR rtl-optimization/105638
> > * g++.target/i386/pr105638.C: New test.
> > ---
> > gcc/dse.cc | 19 ++++++++++
> > gcc/testsuite/g++.target/i386/pr105638.C | 44 ++++++++++++++++++++++++
> > 2 files changed, 63 insertions(+)
> > create mode 100644 gcc/testsuite/g++.target/i386/pr105638.C
> >
> > diff --git a/gcc/dse.cc b/gcc/dse.cc
> > index 30c11cee034..0433dd3d846 100644
> > --- a/gcc/dse.cc
> > +++ b/gcc/dse.cc
> > @@ -1508,6 +1508,25 @@ record_store (rtx body, bb_info_t bb_info)
> >
> > if (tem && CONSTANT_P (tem))
> > const_rhs = tem;
> > + else
> > + {
> > + /* If RHS is set only once to a constant, set CONST_RHS
> > + to the constant. */
> > + df_ref def = DF_REG_DEF_CHAIN (REGNO (rhs));
> > + if (def != nullptr
> > + && !DF_REF_IS_ARTIFICIAL (def)
> > + && !DF_REF_NEXT_REG (def))
> > + {
> > + rtx_insn *def_insn = DF_REF_INSN (def);
> > + rtx def_body = PATTERN (def_insn);
> > + if (GET_CODE (def_body) == SET)
> > + {
> > + rtx def_src = SET_SRC (def_body);
> > + if (CONSTANT_P (def_src))
> > + const_rhs = def_src;
>
> doesn't DSE have its own tracking of stored values? Shouldn't we
It tracks stored values only within the basic block. When RTL loop
invariant motion hoists a constant initialization out of the loop into
a separate basic block, the constant store value becomes unknown
within the original basic block.
> improve _that_ if it is not enough? I also wonder if you need to
My patch extends DSE stored value tracking to include the constant which
is set only once in another basic block.
> verify the SET isn't partial?
>
Here is the v2 patch to check that the constant is set by a non-partial
unconditional load.
OK for master?
Thanks.
H.J.
---
RTL DSE tracks redundant constant stores within a basic block. When RTL
loop invariant motion hoists a constant initialization out of the loop
into a separate basic block, the constant store value becomes unknown
within the original basic block. When recording store for RTL DSE, check
if the source register is set only once to a constant by a non-partial
unconditional load. If yes, record the constant as the constant store
source. It eliminates unrolled zero stores after memset 0 in a loop
where a vector register is used as the zero store source.
gcc/
PR rtl-optimization/105638
* dse.cc (record_store): Use the constant source if the source
register is set only once.
gcc/testsuite/
PR rtl-optimization/105638
* g++.target/i386/pr105638.C: New test.
---
gcc/dse.cc | 22 ++++++++++++
gcc/testsuite/g++.target/i386/pr105638.C | 44 ++++++++++++++++++++++++
2 files changed, 66 insertions(+)
create mode 100644 gcc/testsuite/g++.target/i386/pr105638.C
diff --git a/gcc/dse.cc b/gcc/dse.cc
index 30c11cee034..af8e88dac32 100644
--- a/gcc/dse.cc
+++ b/gcc/dse.cc
@@ -1508,6 +1508,28 @@ record_store (rtx body, bb_info_t bb_info)
if (tem && CONSTANT_P (tem))
const_rhs = tem;
+ else
+ {
+ /* If RHS is set only once to a constant, set CONST_RHS
+ to the constant. */
+ df_ref def = DF_REG_DEF_CHAIN (REGNO (rhs));
+ if (def != nullptr
+ && !DF_REF_IS_ARTIFICIAL (def)
+ && !(DF_REF_FLAGS (def)
+ & (DF_REF_PARTIAL | DF_REF_CONDITIONAL))
+ && !DF_REF_NEXT_REG (def))
+ {
+ rtx_insn *def_insn = DF_REF_INSN (def);
+ rtx def_body = PATTERN (def_insn);
+ if (GET_CODE (def_body) == SET)
+ {
+ rtx def_src = SET_SRC (def_body);
+ if (CONSTANT_P (def_src)
+ && GET_MODE (def_src) == GET_MODE (rhs))
+ const_rhs = def_src;
+ }
+ }
+ }
}
}
diff --git a/gcc/testsuite/g++.target/i386/pr105638.C
b/gcc/testsuite/g++.target/i386/pr105638.C
new file mode 100644
index 00000000000..ff40a459de1
--- /dev/null
+++ b/gcc/testsuite/g++.target/i386/pr105638.C
@@ -0,0 +1,44 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-std=gnu++20 -O2 -march=skylake" } */
+/* { dg-final { scan-assembler-not "vpxor" } } */
+
+#include <stdint.h>
+#include <vector>
+#include <tr1/array>
+
+class FastBoard {
+public:
+ typedef std::pair<int, int> movescore_t;
+ typedef std::tr1::array<movescore_t, 24> scoredlist_t;
+
+protected:
+ std::vector<int> m_critical;
+
+ int m_boardsize;
+};
+
+class FastState {
+public:
+ FastBoard board;
+
+ int movenum;
+protected:
+ FastBoard::scoredlist_t scoredmoves;
+};
+
+class KoState : public FastState {
+private:
+ std::vector<uint64_t> ko_hash_history;
+ std::vector<uint64_t> hash_history;
+};
+
+class GameState : public KoState {
+public:
+ void foo ();
+private:
+ std::vector<KoState> game_history;
+};
+
+void GameState::foo() {
+ game_history.resize(movenum);
+}
--
2.36.1
