@@ -74,14 +74,6 @@ VCGE_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 1 .... @3same
VCGE_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same
# The shift operations are of the form Vd = Vm << Vn.
-# By reversing the names of the fields here, we can use standard expanders.
-@3same_rev .... ... . . . size:2 .... .... .... . q:1 . . .... \
- &3same vn=%vm_dp vm=%vn_dp vd=%vd_dp
-
-VSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 0 .... @3same_rev
-VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev
-
-# Insns operating on 64-bit elements (size!=0b11 handled elsewhere)
# The _rev suffix indicates that Vn and Vm are reversed. This is
# the case for shifts. In the Arm ARM these insns are documented
# with the Vm and Vn fields in their usual places, but in the
@@ -92,15 +84,42 @@ VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev
# function code (where we would otherwise need to manually swap
# the operands over to call Neon helper functions that are shared
# with AArch64 which does not have this odd reversed-operand situation).
+@3same_rev .... ... . . . size:2 .... .... .... . q:1 . . .... \
+ &3same vn=%vm_dp vm=%vn_dp vd=%vd_dp
+
+VSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 0 .... @3same_rev
+VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev
+
+# Insns operating on 64-bit elements (size!=0b11 handled elsewhere)
+# The _rev suffix indicates that Vn and Vm are reversed (as explained
+# by the comment for the @3same_rev format).
@3same_64_rev .... ... . . . 11 .... .... .... . q:1 . . .... \
&3same vm=%vn_dp vn=%vm_dp vd=%vd_dp size=3
-VQSHL_S64_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
-VQSHL_U64_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
-VRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
-VRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
-VQRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
-VQRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
+{
+ VQSHL_S64_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
+ VQSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_rev
+}
+{
+ VQSHL_U64_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
+ VQSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_rev
+}
+{
+ VRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
+ VRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_rev
+}
+{
+ VRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
+ VRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_rev
+}
+{
+ VQRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
+ VQRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_rev
+}
+{
+ VQRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
+ VQRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_rev
+}
VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same
VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same
@@ -875,9 +875,52 @@ DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64)
return do_3same(s, a, gen_##INSN##_3s); \
}
+/*
+ * Some helper functions need to be passed the cpu_env. In order
+ * to use those with the gvec APIs like tcg_gen_gvec_3() we need
+ * to create wrapper functions whose prototype is a NeonGenTwoOpFn()
+ * and which call a NeonGenTwoOpEnvFn().
+ */
+#define WRAP_ENV_FN(WRAPNAME, FUNC) \
+ static void WRAPNAME(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m) \
+ { \
+ FUNC(d, cpu_env, n, m); \
+ }
+
+#define DO_3SAME_32_ENV(INSN, FUNC) \
+ WRAP_ENV_FN(gen_##INSN##_tramp8, gen_helper_neon_##FUNC##8); \
+ WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##16); \
+ WRAP_ENV_FN(gen_##INSN##_tramp32, gen_helper_neon_##FUNC##32); \
+ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \
+ uint32_t rn_ofs, uint32_t rm_ofs, \
+ uint32_t oprsz, uint32_t maxsz) \
+ { \
+ static const GVecGen3 ops[4] = { \
+ { .fni4 = gen_##INSN##_tramp8 }, \
+ { .fni4 = gen_##INSN##_tramp16 }, \
+ { .fni4 = gen_##INSN##_tramp32 }, \
+ { 0 }, \
+ }; \
+ tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops[vece]); \
+ } \
+ static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \
+ { \
+ if (a->size > 2) { \
+ return false; \
+ } \
+ return do_3same(s, a, gen_##INSN##_3s); \
+ }
+
DO_3SAME_32(VHADD_S, hadd_s)
DO_3SAME_32(VHADD_U, hadd_u)
DO_3SAME_32(VHSUB_S, hsub_s)
DO_3SAME_32(VHSUB_U, hsub_u)
DO_3SAME_32(VRHADD_S, rhadd_s)
DO_3SAME_32(VRHADD_U, rhadd_u)
+DO_3SAME_32(VRSHL_S, rshl_s)
+DO_3SAME_32(VRSHL_U, rshl_u)
+
+DO_3SAME_32_ENV(VQSHL_S, qshl_s)
+DO_3SAME_32_ENV(VQSHL_U, qshl_u)
+DO_3SAME_32_ENV(VQRSHL_S, qrshl_s)
+DO_3SAME_32_ENV(VQRSHL_U, qrshl_u)
@@ -5439,6 +5439,9 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
case NEON_3R_VHSUB:
case NEON_3R_VABD:
case NEON_3R_VABA:
+ case NEON_3R_VQSHL:
+ case NEON_3R_VRSHL:
+ case NEON_3R_VQRSHL:
/* Already handled by decodetree */
return 1;
}
@@ -5449,17 +5452,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
}
pairwise = 0;
switch (op) {
- case NEON_3R_VQSHL:
- case NEON_3R_VRSHL:
- case NEON_3R_VQRSHL:
- {
- int rtmp;
- /* Shift instruction operands are reversed. */
- rtmp = rn;
- rn = rm;
- rm = rtmp;
- }
- break;
case NEON_3R_VPADD_VQRDMLAH:
case NEON_3R_VPMAX:
case NEON_3R_VPMIN:
@@ -5519,14 +5511,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
tmp2 = neon_load_reg(rm, pass);
}
switch (op) {
- case NEON_3R_VQSHL:
- GEN_NEON_INTEGER_OP_ENV(qshl);
- break;
- case NEON_3R_VRSHL:
- GEN_NEON_INTEGER_OP(rshl);
- break;
- case NEON_3R_VQRSHL:
- GEN_NEON_INTEGER_OP_ENV(qrshl);
break;
case NEON_3R_VPMAX:
GEN_NEON_INTEGER_OP(pmax);
Convert the VQSHL, VRSHL and VQRSHL insns in the 3-reg-same group to decodetree. We have already implemented the size==0b11 case of these insns; this commit handles the remaining sizes. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/neon-dp.decode | 47 +++++++++++++++++++++++---------- target/arm/translate-neon.inc.c | 43 ++++++++++++++++++++++++++++++ target/arm/translate.c | 22 +++------------ 3 files changed, 79 insertions(+), 33 deletions(-) -- 2.20.1