Many thanks to H.J. for pointing out a better idiom for traversing
the USEs (and also DEFs) of TImode registers in an instruction.
This revised patched has been tested on x86_64-pc-linux-gnu with
make bootstrap and make -k check, both with and without
--target_board=unix{-m32}, with no new failures. Ok for mainline?
2022-07-30 Roger Sayle <ro...@nextmovesoftware.com>
H.J. Lu <hjl.to...@gmail.com>
gcc/ChangeLog
PR target/106450
* config/i386/i386-features.cc (timode_check_non_convertible_regs):
Do nothing if REGNO is set in the REGS bitmap, or is a hard reg.
(timode_remove_non_convertible_regs): Update comment.
Call timode_check_non_convertible_reg on all TImode register
DEFs and USEs in each instruction.
gcc/testsuite/ChangeLog
PR target/106450
* gcc.target/i386/pr106450.c: New test case.
Thanks (H.J. and Uros),
Roger
--
> -----Original Message-----
> From: H.J. Lu <hjl.to...@gmail.com>
> Sent: 28 July 2022 17:55
> To: Roger Sayle <ro...@nextmovesoftware.com>
> Cc: GCC Patches <gcc-patches@gcc.gnu.org>
> Subject: Re: [x86_64 PATCH] PR target/106450: Tweak
> timode_remove_non_convertible_regs.
>
> On Thu, Jul 28, 2022 at 9:43 AM Roger Sayle <ro...@nextmovesoftware.com>
> wrote:
> >
> > This patch resolves PR target/106450, some more fall-out from more
> > aggressive TImode scalar-to-vector (STV) optimizations. I continue to
> > be caught out by how far TImode STV has diverged from DImode/SImode
> > STV, and therefore requires additional (unexpected) tweaking. Many
> > thanks to H.J. Lu for pointing out timode_remove_non_convertible_regs
> > needs to be extended to handle XOR (and other new operations).
> >
> > Unhelpfully the comment above this function states that it's the
> > TImode version of "remove_non_convertible_regs", which doesn't exist
> > anymore, so I've resurrected an explanatory comment from the git history.
> > By refactoring the checks for hard regs and already "marked" regs into
> > timode_check_non_convertible_regs itself, all its callers are
> > simplified. This patch then uses GET_RTX_CLASS to generically handle
> > unary and binary operations, calling timode_check_non_convertible_regs
> > on each TImode register operand in the single_set's SET_SRC.
> >
> > This patch has been tested on x86_64-pc-linux-gnu with make bootstrap
> > and make -k check, both with and without --target_board=unix{-m32},
> > with no new failures. Ok for mainline?
> >
> >
> > 2022-07-28 Roger Sayle <ro...@nextmovesoftware.com>
> >
> > gcc/ChangeLog
> > PR target/106450
> > * config/i386/i386-features.cc (timode_check_non_convertible_regs):
> > Do nothing if REGNO is set in the REGS bitmap, or is a hard reg.
> > (timode_remove_non_convertible_regs): Update comment.
> > Call timode_check_non_convertible_regs on all register operands
> > of supported (binary and unary) operations.
>
> Should we use
>
> df_ref ref;
> FOR_EACH_INSN_USE (ref, insn)
> if (!DF_REF_REG_MEM_P (ref))
> timode_check_non_convertible_regs (candidates, regs,
> DF_REF_REGNO (ref));
>
> to check each use?
>
> > gcc/testsuite/ChangeLog
> > PR target/106450
> > * gcc.target/i386/pr106450.c: New test case.
> >
> >
> > Thanks in advance,
> > Roger
> > --
> --
> H.J.
diff --git a/gcc/config/i386/i386-features.cc b/gcc/config/i386/i386-features.cc
index aa5de71..e4cc4a3 100644
--- a/gcc/config/i386/i386-features.cc
+++ b/gcc/config/i386/i386-features.cc
@@ -1808,6 +1808,11 @@ static void
timode_check_non_convertible_regs (bitmap candidates, bitmap regs,
unsigned int regno)
{
+ /* Do nothing if REGNO is already in REGS or is a hard reg. */
+ if (bitmap_bit_p (regs, regno)
+ || HARD_REGISTER_NUM_P (regno))
+ return;
+
for (df_ref def = DF_REG_DEF_CHAIN (regno);
def;
def = DF_REF_NEXT_REG (def))
@@ -1843,7 +1848,13 @@ timode_check_non_convertible_regs (bitmap candidates,
bitmap regs,
}
}
-/* The TImode version of remove_non_convertible_regs. */
+/* For a given bitmap of insn UIDs scans all instructions and
+ remove insn from CANDIDATES in case it has both convertible
+ and not convertible definitions.
+
+ All insns in a bitmap are conversion candidates according to
+ scalar_to_vector_candidate_p. Currently it implies all insns
+ are single_set. */
static void
timode_remove_non_convertible_regs (bitmap candidates)
@@ -1857,25 +1868,20 @@ timode_remove_non_convertible_regs (bitmap candidates)
changed = false;
EXECUTE_IF_SET_IN_BITMAP (candidates, 0, id, bi)
{
- rtx def_set = single_set (DF_INSN_UID_GET (id)->insn);
- rtx dest = SET_DEST (def_set);
- rtx src = SET_SRC (def_set);
-
- if ((!REG_P (dest)
- || bitmap_bit_p (regs, REGNO (dest))
- || HARD_REGISTER_P (dest))
- && (!REG_P (src)
- || bitmap_bit_p (regs, REGNO (src))
- || HARD_REGISTER_P (src)))
- continue;
-
- if (REG_P (dest))
- timode_check_non_convertible_regs (candidates, regs,
- REGNO (dest));
-
- if (REG_P (src))
- timode_check_non_convertible_regs (candidates, regs,
- REGNO (src));
+ rtx_insn *insn = DF_INSN_UID_GET (id)->insn;
+ df_ref ref;
+
+ FOR_EACH_INSN_DEF (ref, insn)
+ if (!DF_REF_REG_MEM_P (ref)
+ && GET_MODE (DF_REF_REG (ref)) == TImode)
+ timode_check_non_convertible_regs (candidates, regs,
+ DF_REF_REGNO (ref));
+
+ FOR_EACH_INSN_USE (ref, insn)
+ if (!DF_REF_REG_MEM_P (ref)
+ && GET_MODE (DF_REF_REG (ref)) == TImode)
+ timode_check_non_convertible_regs (candidates, regs,
+ DF_REF_REGNO (ref));
}
EXECUTE_IF_SET_IN_BITMAP (regs, 0, id, bi)
diff --git a/gcc/testsuite/gcc.target/i386/pr106450.c
b/gcc/testsuite/gcc.target/i386/pr106450.c
new file mode 100644
index 0000000..d16231f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr106450.c
@@ -0,0 +1,14 @@
+/* { dg-do compile { target int128 } } */
+/* { dg-options "-O2 -fsplit-paths" } */
+
+__int128 n;
+
+__attribute__ ((simd)) void
+foo (void)
+{
+ __int128 uninitialized;
+ unsigned __int128 *p = &n;
+
+ n >>= *p ? : 2;
+ n |= uninitialized;
+}
