[Qemu-devel] [PATCH v3 7/8] target/mips: Add MXU instructions Q8MUL and Q8MULSU

[Craig Janeczek <jancraig@amazon.com>]

Adds support for emulating the Q8MUL and Q8MULSU instructions.

Signed-off-by: Craig Janeczek <jancraig@amazon.com>
---
 v1
    - initial patch
 v2
    - changed bitfield usage to extract32
 v3
    - Split gen_mxu function into command specific gen_mxu_<ins> functions

 target/mips/translate.c | 86 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 86 insertions(+)

diff --git a/target/mips/translate.c b/target/mips/translate.c
index 7c17867d30..a28ea124c2 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -4041,6 +4041,88 @@ static void gen_mxu_d16mac(DisasContext *ctx, uint32_t opc)
     tcg_temp_free(t3);
 }
 
+/* Q8MUL XRa, XRb, XRc, XRd - Parallel unsigned 8 bit pattern multiply */
+/* Q8MULSU XRa, XRb, XRc, XRd - Parallel signed 8 bit pattern multiply */
+static void gen_mxu_q8mul(DisasContext *ctx, uint32_t opc)
+{
+    TCGv t0, t1, t2, t3, t4, t5, t6, t7;
+    uint32_t xra, xrb, xrc, xrd, sel;
+
+    t0 = tcg_temp_new();
+    t1 = tcg_temp_new();
+    t2 = tcg_temp_new();
+    t3 = tcg_temp_new();
+    t4 = tcg_temp_new();
+    t5 = tcg_temp_new();
+    t6 = tcg_temp_new();
+    t7 = tcg_temp_new();
+
+    xra = extract32(ctx->opcode, 6, 4);
+    xrb = extract32(ctx->opcode, 10, 4);
+    xrc = extract32(ctx->opcode, 14, 4);
+    xrd = extract32(ctx->opcode, 18, 4);
+    sel = extract32(ctx->opcode, 22, 4);
+
+    gen_load_mxu_gpr(t3, xrb);
+    gen_load_mxu_gpr(t7, xrc);
+
+    if (sel == 0x2) {
+        /* Q8MULSU */
+        tcg_gen_ext8s_tl(t0, t3);
+        tcg_gen_shri_tl(t3, t3, 8);
+        tcg_gen_ext8s_tl(t1, t3);
+        tcg_gen_shri_tl(t3, t3, 8);
+        tcg_gen_ext8s_tl(t2, t3);
+        tcg_gen_shri_tl(t3, t3, 8);
+        tcg_gen_ext8s_tl(t3, t3);
+    } else {
+        /* Q8MUL */
+        tcg_gen_ext8u_tl(t0, t3);
+        tcg_gen_shri_tl(t3, t3, 8);
+        tcg_gen_ext8u_tl(t1, t3);
+        tcg_gen_shri_tl(t3, t3, 8);
+        tcg_gen_ext8u_tl(t2, t3);
+        tcg_gen_shri_tl(t3, t3, 8);
+        tcg_gen_ext8u_tl(t3, t3);
+    }
+
+    tcg_gen_ext8u_tl(t4, t7);
+    tcg_gen_shri_tl(t7, t7, 8);
+    tcg_gen_ext8u_tl(t5, t7);
+    tcg_gen_shri_tl(t7, t7, 8);
+    tcg_gen_ext8u_tl(t6, t7);
+    tcg_gen_shri_tl(t7, t7, 8);
+    tcg_gen_ext8u_tl(t7, t7);
+
+    tcg_gen_mul_tl(t0, t0, t4);
+    tcg_gen_mul_tl(t1, t1, t5);
+    tcg_gen_mul_tl(t2, t2, t6);
+    tcg_gen_mul_tl(t3, t3, t7);
+
+    tcg_gen_andi_tl(t0, t0, 0xFFFF);
+    tcg_gen_andi_tl(t1, t1, 0xFFFF);
+    tcg_gen_andi_tl(t2, t2, 0xFFFF);
+    tcg_gen_andi_tl(t3, t3, 0xFFFF);
+
+    tcg_gen_shli_tl(t1, t1, 16);
+    tcg_gen_shli_tl(t3, t3, 16);
+
+    tcg_gen_or_tl(t0, t0, t1);
+    tcg_gen_or_tl(t1, t2, t3);
+
+    gen_store_mxu_gpr(t0, xrd);
+    gen_store_mxu_gpr(t1, xra);
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+    tcg_temp_free(t2);
+    tcg_temp_free(t3);
+    tcg_temp_free(t4);
+    tcg_temp_free(t5);
+    tcg_temp_free(t6);
+    tcg_temp_free(t7);
+}
+
 /* Godson integer instructions */
 static void gen_loongson_integer(DisasContext *ctx, uint32_t opc,
                                  int rd, int rs, int rt)
@@ -18158,6 +18240,10 @@ static void decode_opc_special2_legacy(CPUMIPSState *env, DisasContext *ctx)
         gen_mxu_d16mac(ctx, op1);
         break;
 
+    case OPC_MXU_Q8MUL:
+        gen_mxu_q8mul(ctx, op1);
+        break;
+
     case OPC_CLO:
     case OPC_CLZ:
         check_insn(ctx, ISA_MIPS32);
-- 
2.18.0