Optimize Altivec instruction vclzd (Vector Count Leading Zeros Doubleword).
This instruction counts the number of leading zeros of each doubleword element
in source register and places result in the appropriate doubleword element of
destination register.
Using tcg-s count leading zeros instruction two times(once for each
doubleword element of source register vB) and placing result in
appropriate doubleword element of destination register vD.
Signed-off-by: Stefan Brankovic <stefan.branko...@rt-rk.com>
---
target/ppc/translate/vmx-impl.inc.c | 28 +++++++++++++++++++++++++++-
1 file changed, 27 insertions(+), 1 deletion(-)
diff --git a/target/ppc/translate/vmx-impl.inc.c
b/target/ppc/translate/vmx-impl.inc.c
index 010f337..1c34908 100644
--- a/target/ppc/translate/vmx-impl.inc.c
+++ b/target/ppc/translate/vmx-impl.inc.c
@@ -877,6 +877,32 @@ static void trans_vgbbd(DisasContext *ctx)
tcg_temp_free_i64(result2);
}
+/*
+ * vclzd VRT,VRB - Vector Count Leading Zeros Doubleword
+ *
+ * Counting the number of leading zero bits of each doubleword element in
source
+ * register and placing result in appropriate doubleword element of destination
+ * register.
+ */
+static void trans_vclzd(DisasContext *ctx)
+{
+ int VT = rD(ctx->opcode);
+ int VB = rB(ctx->opcode);
+ TCGv_i64 avr = tcg_temp_new_i64();
+
+ /* high doubleword */
+ get_avr64(avr, VB, true);
+ tcg_gen_clzi_i64(avr, avr, 64);
+ set_avr64(VT, avr, true);
+
+ /* low doubleword */
+ get_avr64(avr, VB, false);
+ tcg_gen_clzi_i64(avr, avr, 64);
+ set_avr64(VT, avr, false);
+
+ tcg_temp_free_i64(avr);
+}
+
GEN_VXFORM(vmuloub, 4, 0);
GEN_VXFORM(vmulouh, 4, 1);
GEN_VXFORM(vmulouw, 4, 2);
@@ -1388,7 +1414,7 @@ GEN_VAFORM_PAIRED(vmaddfp, vnmsubfp, 23)
GEN_VXFORM_NOA(vclzb, 1, 28)
GEN_VXFORM_NOA(vclzh, 1, 29)
GEN_VXFORM_NOA(vclzw, 1, 30)
-GEN_VXFORM_NOA(vclzd, 1, 31)
+GEN_VXFORM_TRANS(vclzd, 1, 31)
GEN_VXFORM_NOA_2(vnegw, 1, 24, 6)
GEN_VXFORM_NOA_2(vnegd, 1, 24, 7)
GEN_VXFORM_NOA_2(vextsb2w, 1, 24, 16)
--
2.7.4
