From c86e1c54c6f8771d08a8c070717b80607f990f8a Mon Sep 17 00:00:00 2001 From: kelefth Date: Mon, 16 Dec 2024 14:36:59 +0100 Subject: [PATCH] avoid-store-forwarding: fix reg init on load-eliminiation [PR117835] During the initialization of the base register for the zero-offset store, in the case that we are eliminating the load, we used a paradoxical subreg assuming that we don't care about the higher bits of the register. This led to writing wrong values when we were not updating the whole register. This patch fixes the issue by zero-extending the value stored in the base register instead of using a paradoxical subreg. Bootstrapped/regtested on x86 and AArch64. PR rtl-optimization/117835 PR rtl-optimization/117872 gcc/ChangeLog: * avoid-store-forwarding.cc (store_forwarding_analyzer::process_store_forwarding): Zero-extend the value stored in the base register instead of using a paradoxical subreg. gcc/testsuite/ChangeLog: * gcc.target/i386/pr117835.c: New test. --- gcc/avoid-store-forwarding.cc | 6 +----- gcc/testsuite/gcc.target/i386/pr117835.c | 20 ++++++++++++++++++++ 2 files changed, 21 insertions(+), 5 deletions(-) create mode 100644 gcc/testsuite/gcc.target/i386/pr117835.c diff --git a/gcc/avoid-store-forwarding.cc b/gcc/avoid-store-forwarding.cc index 1b8c35bc6cb..fa83e10fedc 100644 --- a/gcc/avoid-store-forwarding.cc +++ b/gcc/avoid-store-forwarding.cc @@ -238,11 +238,7 @@ process_store_forwarding (vec &stores, rtx_insn *load_insn, { start_sequence (); - /* We can use a paradoxical subreg to force this to a wider mode, as - the only use will be inserting the bits (i.e., we don't care about - the value of the higher bits). */ - rtx ext0 = lowpart_subreg (GET_MODE (dest), it->mov_reg, - GET_MODE (it->mov_reg)); + rtx ext0 = gen_rtx_ZERO_EXTEND (GET_MODE (dest), it->mov_reg); if (ext0) { rtx_insn *move0 = emit_move_insn (dest, ext0); diff --git a/gcc/testsuite/gcc.target/i386/pr117835.c b/gcc/testsuite/gcc.target/i386/pr117835.c new file mode 100644 index 00000000000..eac71aac916 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr117835.c @@ -0,0 +1,20 @@ +/* { dg-do run } */ +/* { dg-options "-O -favoid-store-forwarding -mno-push-args --param=store-forwarding-max-distance=0 -Wno-psabi" } */ + +typedef __attribute__((__vector_size__ (64))) unsigned short V; + +__attribute__((__noipa__)) V +foo (V v, V) +{ + return v; +} + +int main () +{ + V a = (V){3, 5, 0, 8, 9, 3, 5, 1, 3, 4, 2, 5, 5, 0, 5, 3, 61886}; + V b = (V){6, 80, 15, 2, 2, 1, 1, 3, 5}; + V x = foo (a, b); + for (unsigned i = 0; i < sizeof(x)/sizeof(x[0]); i++) + if (x[i] != a[i]) + __builtin_abort(); +} \ No newline at end of file