From: Matheus Ferst
Implement the following PowerISA v3.1 instructions:
mtvsrbm: Move to VSR Byte Mask
mtvsrhm: Move to VSR Halfword Mask
mtvsrwm: Move to VSR Word Mask
mtvsrdm: Move to VSR Doubleword Mask
mtvsrqm: Move to VSR Quadword Mask
mtvsrbmi: Move to VSR Byte Mask Immediate
Suggested-by: Richard Henderson
Signed-off-by: Matheus Ferst
---
v2:
- Applied rth suggestions to do_mtvsrm and trans_MTVSRBMI
---
target/ppc/insn32.decode| 11 +++
target/ppc/translate/vmx-impl.c.inc | 115
2 files changed, 126 insertions(+)
diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index 639ac22bf0..f68931f4f3 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -40,6 +40,10 @@
%ds_rtp 22:4 !function=times_2
@DS_rtp .. 0 ra:5 .. .. &D rt=%ds_rtp
si=%ds_si
+&DX_b vrt b
+%dx_b 6:10 16:5 0:1
+@DX_b .. vrt:5 . .. . . &DX_b b=%dx_b
+
&DX rt d
%dx_d 6:s10 16:5 0:1
@DX .. rt:5 . .. . . &DX d=%dx_d
@@ -413,6 +417,13 @@ VSRDBI 000100 . . . 01 ... 010110 @VN
## Vector Mask Manipulation Instructions
+MTVSRBM 000100 . 1 . 1100110@VX_tb
+MTVSRHM 000100 . 10001 . 1100110@VX_tb
+MTVSRWM 000100 . 10010 . 1100110@VX_tb
+MTVSRDM 000100 . 10011 . 1100110@VX_tb
+MTVSRQM 000100 . 10100 . 1100110@VX_tb
+MTVSRBMI000100 . . .. 01010 . @DX_b
+
VEXPANDBM 000100 . 0 . 1100110@VX_tb
VEXPANDHM 000100 . 1 . 1100110@VX_tb
VEXPANDWM 000100 . 00010 . 1100110@VX_tb
diff --git a/target/ppc/translate/vmx-impl.c.inc
b/target/ppc/translate/vmx-impl.c.inc
index dd7337c2f2..404767e4ec 100644
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -1599,6 +1599,121 @@ static bool trans_VEXTRACTQM(DisasContext *ctx,
arg_VX_tb *a)
return true;
}
+static bool do_mtvsrm(DisasContext *ctx, arg_VX_tb *a, unsigned vece)
+{
+const uint64_t elem_width = 8 << vece, elem_count_half = 8 >> vece;
+uint64_t c;
+int i, j;
+TCGv_i64 hi, lo, t0, t1;
+
+REQUIRE_INSNS_FLAGS2(ctx, ISA310);
+REQUIRE_VECTOR(ctx);
+
+hi = tcg_temp_new_i64();
+lo = tcg_temp_new_i64();
+t0 = tcg_temp_new_i64();
+t1 = tcg_temp_new_i64();
+
+tcg_gen_extu_tl_i64(t0, cpu_gpr[a->vrb]);
+tcg_gen_extract_i64(hi, t0, elem_count_half, elem_count_half);
+tcg_gen_extract_i64(lo, t0, 0, elem_count_half);
+
+/*
+ * Spread the bits into their respective elements.
+ * E.g. for bytes:
+ * abcdefgh
+ * << 32 - 4
+ * abcdefgh
+ * |
+ * abcdefghabcdefgh
+ * << 16 - 2
+ * 00abcdefghabcdefgh00
+ * |
+ * 00abcdefgh00abcdefgh00abcdefgh00abcdefgh
+ * << 8 - 1
+ * 000abcdefgh00abcdefgh00abcdefgh00abcdefgh000
+ * |
+ * 000abcdefgXbcdefgXbcdefgXbcdefgXbcdefgXbcdefgXbcdefgXbcdefgh
+ * & dup(1)
+ * 000a000b000c000d000e000f000g000h
+ * * 0xff
+ *
+ */
+for (i = elem_count_half / 2, j = 32; i > 0; i >>= 1, j >>= 1) {
+tcg_gen_shli_i64(t0, hi, j - i);
+tcg_gen_shli_i64(t1, lo, j - i);
+tcg_gen_or_i64(hi, hi, t0);
+tcg_gen_or_i64(lo, lo, t1);
+}
+
+c = dup_const(vece, 1);
+tcg_gen_andi_i64(hi, hi, c);
+tcg_gen_andi_i64(lo, lo, c);
+
+c = MAKE_64BIT_MASK(0, elem_width);
+tcg_gen_muli_i64(hi, hi, c);
+tcg_gen_muli_i64(lo, lo, c);
+
+set_avr64(a->vrt, lo, false);
+set_avr64(a->vrt, hi, true);
+
+tcg_temp_free_i64(hi);
+tcg_temp_free_i64(lo);
+tcg_temp_free_i64(t0);
+tcg_temp_free_i64(t1);
+
+return true;
+}
+
+TRANS(MTVSRBM, do_mtvsrm, MO_8)
+TRANS(MTVSRHM, do_mtvsrm, MO_16)
+TRANS(MTVSRWM, do_mtvsrm, MO_32)
+TRANS(MTVSRDM, do_mtvsrm, MO_64)
+
+static bool trans_MTVSRQM(DisasContext *ctx, arg_VX_tb *a)
+{
+TCGv_i64 tmp;
+
+REQUIRE_INSNS_FLAGS2(ctx, ISA310);
+REQUIRE_VECTOR(ctx);
+
+tmp = tcg_temp_new_i64();
+
+tcg_gen_ext_tl_i64(tmp, cpu_gpr[a->vrb]);
+tcg_gen_sextract_i64(tmp, tmp, 0, 1);
+set_avr64(a->vrt, tmp, false);
+set_avr64(a->vrt, tmp, true);
+
+tcg_temp_free_i64(tmp);
+
+return true;
+}
+
+static bool trans_MTVSRBMI(DisasContext *ctx, arg_DX_b *a)
+{
+const uint64_t mask = dup_const(MO_8, 1);
+uint64_t hi, lo;
+
+REQUIRE_INSNS_FLAGS2(ctx, ISA310);
+