diff mbox series

[PULL,16/44] target/mips/mxu: Add S16MAD instruction

Message ID 20230710222611.50978-17-philmd@linaro.org
State New
Headers show
Series [PULL,01/44] target/mips: Rework cp0_timer with clock API | expand

Commit Message

Philippe Mathieu-Daudé July 10, 2023, 10:25 p.m. UTC 
From: Siarhei Volkau <lis8215@gmail.com>

The instruction is similar to multiply and accumulate
but works with MXU registers set.

Signed-off-by: Siarhei Volkau <lis8215@gmail.com>
Message-Id: <20230608104222.1520143-14-lis8215@gmail.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
 target/mips/tcg/mxu_translate.c | 65 +++++++++++++++++++++++++++++++++
 1 file changed, 65 insertions(+)
diff mbox series

Patch

diff --git a/target/mips/tcg/mxu_translate.c b/target/mips/tcg/mxu_translate.c
index 202e1c6d35..88d5d659c6 100644
--- a/target/mips/tcg/mxu_translate.c
+++ b/target/mips/tcg/mxu_translate.c
@@ -365,6 +365,7 @@  enum {
     OPC_MXU_D16MAC   = 0x0A,
     OPC_MXU_D16MACF  = 0x0B,
     OPC_MXU_D16MADL  = 0x0C,
+    OPC_MXU_S16MAD   = 0x0D,
     OPC_MXU_D16MACE  = 0x0F,
     OPC_MXU__POOL04  = 0x10,
     OPC_MXU__POOL05  = 0x11,
@@ -978,6 +979,67 @@  static void gen_mxu_d16madl(DisasContext *ctx)
     tcg_gen_or_tl(mxu_gpr[XRd - 1], t3, t2);
 }
 
+/*
+ * S16MAD XRa, XRb, XRc, XRd, aptn2, optn2 - Single packed
+ * signed 16 bit pattern multiply and 32-bit add/subtract.
+ */
+static void gen_mxu_s16mad(DisasContext *ctx)
+{
+    TCGv t0, t1;
+    uint32_t XRa, XRb, XRc, XRd, optn2, aptn1, pad;
+
+    t0 = tcg_temp_new();
+    t1 = 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);
+    optn2 = extract32(ctx->opcode, 22, 2);
+    aptn1 = extract32(ctx->opcode, 24, 1);
+    pad = extract32(ctx->opcode, 25, 1);
+
+    if (pad) {
+        /* FIXME check if it influence the result */
+    }
+
+    gen_load_mxu_gpr(t0, XRb);
+    gen_load_mxu_gpr(t1, XRc);
+
+    switch (optn2) {
+    case MXU_OPTN2_WW: /* XRB.H*XRC.H */
+        tcg_gen_sextract_tl(t0, t0, 16, 16);
+        tcg_gen_sextract_tl(t1, t1, 16, 16);
+        break;
+    case MXU_OPTN2_LW: /* XRB.L*XRC.L */
+        tcg_gen_sextract_tl(t0, t0,  0, 16);
+        tcg_gen_sextract_tl(t1, t1,  0, 16);
+        break;
+    case MXU_OPTN2_HW: /* XRB.H*XRC.L */
+        tcg_gen_sextract_tl(t0, t0, 16, 16);
+        tcg_gen_sextract_tl(t1, t1,  0, 16);
+        break;
+    case MXU_OPTN2_XW: /* XRB.L*XRC.H */
+        tcg_gen_sextract_tl(t0, t0,  0, 16);
+        tcg_gen_sextract_tl(t1, t1, 16, 16);
+        break;
+    }
+    tcg_gen_mul_tl(t0, t0, t1);
+
+    gen_load_mxu_gpr(t1, XRa);
+
+    switch (aptn1) {
+    case MXU_APTN1_A:
+        tcg_gen_add_tl(t1, t1, t0);
+        break;
+    case MXU_APTN1_S:
+        tcg_gen_sub_tl(t1, t1, t0);
+        break;
+    }
+
+    gen_store_mxu_gpr(t1, XRd);
+}
+
 /*
  * Q8MUL   XRa, XRb, XRc, XRd - Parallel unsigned 8 bit pattern multiply
  * Q8MULSU XRa, XRb, XRc, XRd - Parallel signed 8 bit pattern multiply
@@ -2841,6 +2903,9 @@  bool decode_ase_mxu(DisasContext *ctx, uint32_t insn)
         case OPC_MXU_D16MADL:
             gen_mxu_d16madl(ctx);
             break;
+        case OPC_MXU_S16MAD:
+            gen_mxu_s16mad(ctx);
+            break;
         case OPC_MXU_D16MACE:
             gen_mxu_d16mac(ctx, true, false);
             break;