aboutsummaryrefslogtreecommitdiff
path: root/tcg/i386
diff options
context:
space:
mode:
authorRichard Henderson <richard.henderson@linaro.org>2020-03-10 22:14:26 -0700
committerRichard Henderson <richard.henderson@linaro.org>2020-03-17 08:41:07 -0700
commit312b426fea4d6dd322d7472c80010a8ba7a166d2 (patch)
tree638325efa9778bcff81cf578f671bdc9690a6bc9 /tcg/i386
parent40c67636f67c2a89745f2e698522fe917326a952 (diff)
tcg/i386: Bound shift count expanding sari_vec
A given RISU testcase for SVE can produce tcg-op-vec.c:511: do_shifti: Assertion `i >= 0 && i < (8 << vece)' failed. because expand_vec_sari gave a shift count of 32 to a MO_32 vector shift. In 44f1441dbe1, we changed from direct expansion of vector opcodes to re-use of the tcg expanders. So while the comment correctly notes that the hw will handle such a shift count, we now have to take our own sanity checks into account. Which is easy in this particular case. Fixes: 44f1441dbe1 Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Diffstat (limited to 'tcg/i386')
-rw-r--r--tcg/i386/tcg-target.inc.c9
1 files changed, 6 insertions, 3 deletions
diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c
index cdedcb2b25..223dba9c8c 100644
--- a/tcg/i386/tcg-target.inc.c
+++ b/tcg/i386/tcg-target.inc.c
@@ -3391,12 +3391,15 @@ static void expand_vec_sari(TCGType type, unsigned vece,
case MO_64:
if (imm <= 32) {
- /* We can emulate a small sign extend by performing an arithmetic
+ /*
+ * We can emulate a small sign extend by performing an arithmetic
* 32-bit shift and overwriting the high half of a 64-bit logical
- * shift (note that the ISA says shift of 32 is valid).
+ * shift. Note that the ISA says shift of 32 is valid, but TCG
+ * does not, so we have to bound the smaller shift -- we get the
+ * same result in the high half either way.
*/
t1 = tcg_temp_new_vec(type);
- tcg_gen_sari_vec(MO_32, t1, v1, imm);
+ tcg_gen_sari_vec(MO_32, t1, v1, MIN(imm, 31));
tcg_gen_shri_vec(MO_64, v0, v1, imm);
vec_gen_4(INDEX_op_x86_blend_vec, type, MO_32,
tcgv_vec_arg(v0), tcgv_vec_arg(v0),