target/ppc: Implemented vector divide extended word

Implement the following PowerISA v3.1 instructions:
vdivesw: Vector Divide Extended Signed Word
vdiveuw: Vector Divide Extended Unsigned Word

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220525134954.85056-4-lucas.araujo@eldorado.org.br>
Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>

diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index 01bfde8c5ede2acd39fceaeff819ee5a7eaa5af7..f6d2d4b257c251d711a8c719143a192170e951e0 100644 (file)
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -795,3 +795,6 @@ VDIVSD          000100 ..... ..... ..... 00111001011    @VX
 VDIVUD          000100 ..... ..... ..... 00011001011    @VX
 VDIVSQ          000100 ..... ..... ..... 00100001011    @VX
 VDIVUQ          000100 ..... ..... ..... 00000001011    @VX
+
+VDIVESW         000100 ..... ..... ..... 01110001011    @VX
+VDIVEUW         000100 ..... ..... ..... 01010001011    @VX

diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index 22572e6a790069ac6cefd6b26a54f88531b30273..8c542bcb294e4f865d40a260f1785c94d43c5225 100644 (file)
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -3320,6 +3320,54 @@ TRANS_FLAGS2(ISA310, VDIVUD, do_vdiv_vmod, MO_64, NULL, do_divud)
 TRANS_FLAGS2(ISA310, VDIVSQ, do_vx_helper, gen_helper_VDIVSQ)
 TRANS_FLAGS2(ISA310, VDIVUQ, do_vx_helper, gen_helper_VDIVUQ)
 
+static void do_dives_i32(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i64 val1, val2;
+
+    val1 = tcg_temp_new_i64();
+    val2 = tcg_temp_new_i64();
+
+    tcg_gen_ext_i32_i64(val1, a);
+    tcg_gen_ext_i32_i64(val2, b);
+
+    /* (a << 32)/b */
+    tcg_gen_shli_i64(val1, val1, 32);
+    tcg_gen_div_i64(val1, val1, val2);
+
+    /* if quotient doesn't fit in 32 bits the result is undefined */
+    tcg_gen_extrl_i64_i32(t, val1);
+
+    tcg_temp_free_i64(val1);
+    tcg_temp_free_i64(val2);
+}
+
+static void do_diveu_i32(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i64 val1, val2;
+
+    val1 = tcg_temp_new_i64();
+    val2 = tcg_temp_new_i64();
+
+    tcg_gen_extu_i32_i64(val1, a);
+    tcg_gen_extu_i32_i64(val2, b);
+
+    /* (a << 32)/b */
+    tcg_gen_shli_i64(val1, val1, 32);
+    tcg_gen_divu_i64(val1, val1, val2);
+
+    /* if quotient doesn't fit in 32 bits the result is undefined */
+    tcg_gen_extrl_i64_i32(t, val1);
+
+    tcg_temp_free_i64(val1);
+    tcg_temp_free_i64(val2);
+}
+
+DIVS32(do_divesw, do_dives_i32)
+DIVU32(do_diveuw, do_diveu_i32)
+
+TRANS_FLAGS2(ISA310, VDIVESW, do_vdiv_vmod, MO_32, do_divesw, NULL)
+TRANS_FLAGS2(ISA310, VDIVEUW, do_vdiv_vmod, MO_32, do_diveuw, NULL)
+
 #undef DIVS32
 #undef DIVU32
 #undef DIVS64