aarch64: More SME vs -mtrack-speculation

The sequence to commit a lazy save includes a branch based on
whether TPIDR2_EL0 is zero.  The code assumed that CBZ could
be used for this, but that instruction is forbidden when
-mtrack-speculation is being used.

gcc/
	* config/aarch64/aarch64.cc (aarch64_mode_emit_local_sme_state):
	Use aarch64_gen_compare_zero_and_branch rather than emitting
	a CBZ directly.

gcc/testsuite/
	* gcc.target/aarch64/sme/locally_streaming_1_ts.c: New test.
	* gcc.target/aarch64/sme/sibcall_7_ts.c: Likewise.

diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 8a3aa98a32e901fa2e4b1612580436df123dfe3b..28d1555dada90282c0f8a5921b05306a10012182 100644 (file)
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -29344,7 +29344,8 @@ aarch64_mode_emit_local_sme_state (aarch64_local_sme_state mode,
       auto tmp_reg = gen_reg_rtx (DImode);
       emit_insn (gen_aarch64_read_tpidr2 (tmp_reg));
       auto label = gen_label_rtx ();
-      auto jump = emit_jump_insn (gen_aarch64_cbeqdi1 (tmp_reg, label));
+      rtx branch = aarch64_gen_compare_zero_and_branch (EQ, tmp_reg, label);
+      auto jump = emit_jump_insn (branch);
       JUMP_LABEL (jump) = label;
       emit_insn (gen_aarch64_tpidr2_save ());
       emit_insn (gen_aarch64_clear_tpidr2 ());

diff --git a/gcc/testsuite/gcc.target/aarch64/sme/locally_streaming_1_ts.c b/gcc/testsuite/gcc.target/aarch64/sme/locally_streaming_1_ts.c
new file mode 100644 (file)
index 0000000..25ac345
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sme/locally_streaming_1_ts.c
@@ -0,0 +1,3 @@
+// { dg-options "-O -fomit-frame-pointer -mtrack-speculation" }
+
+#include "locally_streaming_1.c"

diff --git a/gcc/testsuite/gcc.target/aarch64/sme/sibcall_7_ts.c b/gcc/testsuite/gcc.target/aarch64/sme/sibcall_7_ts.c
new file mode 100644 (file)
index 0000000..4b47678
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sme/sibcall_7_ts.c
@@ -0,0 +1,3 @@
+// { dg-options "-O2 -mtrack-speculation" }
+
+#include "sibcall_7.c"