aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--sysdeps/x86_64/multiarch/avx-rtm-vecs.h1
-rw-r--r--sysdeps/x86_64/sysdep.h18
2 files changed, 19 insertions, 0 deletions
diff --git a/sysdeps/x86_64/multiarch/avx-rtm-vecs.h b/sysdeps/x86_64/multiarch/avx-rtm-vecs.h
index 3f531dd..6ca9f5e 100644
--- a/sysdeps/x86_64/multiarch/avx-rtm-vecs.h
+++ b/sysdeps/x86_64/multiarch/avx-rtm-vecs.h
@@ -20,6 +20,7 @@
#ifndef _AVX_RTM_VECS_H
#define _AVX_RTM_VECS_H 1
+#define COND_VZEROUPPER COND_VZEROUPPER_XTEST
#define ZERO_UPPER_VEC_REGISTERS_RETURN \
ZERO_UPPER_VEC_REGISTERS_RETURN_XTEST
diff --git a/sysdeps/x86_64/sysdep.h b/sysdeps/x86_64/sysdep.h
index f14d507..4f512d5 100644
--- a/sysdeps/x86_64/sysdep.h
+++ b/sysdeps/x86_64/sysdep.h
@@ -106,6 +106,24 @@ lose: \
vzeroupper; \
ret
+/* Can be used to replace vzeroupper that is not directly before a
+ return. This is useful when hoisting a vzeroupper from multiple
+ return paths to decrease the total number of vzerouppers and code
+ size. */
+#define COND_VZEROUPPER_XTEST \
+ xtest; \
+ jz 1f; \
+ vzeroall; \
+ jmp 2f; \
+1: \
+ vzeroupper; \
+2:
+
+/* In RTM define this as COND_VZEROUPPER_XTEST. */
+#ifndef COND_VZEROUPPER
+# define COND_VZEROUPPER vzeroupper
+#endif
+
/* Zero upper vector registers and return. */
#ifndef ZERO_UPPER_VEC_REGISTERS_RETURN
# define ZERO_UPPER_VEC_REGISTERS_RETURN \