qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Philippe Mathieu-Daudé" <philmd@linaro.org>
To: qemu-devel@nongnu.org
Cc: "Siarhei Volkau" <lis8215@gmail.com>,
	"Huacai Chen" <chenhuacai@kernel.org>,
	"Philippe Mathieu-Daudé" <philmd@linaro.org>,
	"Jiaxun Yang" <jiaxun.yang@flygoat.com>
Subject: [PULL 12/44] target/mips/mxu: Add S32CPS D16CPS Q8ABD Q16SAT insns
Date: Tue, 11 Jul 2023 00:25:39 +0200	[thread overview]
Message-ID: <20230710222611.50978-13-philmd@linaro.org> (raw)
In-Reply-To: <20230710222611.50978-1-philmd@linaro.org>

From: Siarhei Volkau <lis8215@gmail.com>

These instructions are part of pool2, see the grand tree above
in the file.

Signed-off-by: Siarhei Volkau <lis8215@gmail.com>
Message-Id: <20230608104222.1520143-10-lis8215@gmail.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
 target/mips/tcg/mxu_translate.c | 296 +++++++++++++++++++++++++++++++-
 1 file changed, 293 insertions(+), 3 deletions(-)

diff --git a/target/mips/tcg/mxu_translate.c b/target/mips/tcg/mxu_translate.c
index 034287e54b..3bd5fcb98a 100644
--- a/target/mips/tcg/mxu_translate.c
+++ b/target/mips/tcg/mxu_translate.c
@@ -359,6 +359,7 @@ enum {
     OPC_MXU_S32MSUB  = 0x04,
     OPC_MXU_S32MSUBU = 0x05,
     OPC_MXU__POOL01  = 0x06,
+    OPC_MXU__POOL02  = 0x07,
     OPC_MXU_D16MUL   = 0x08,
     OPC_MXU_D16MAC   = 0x0A,
     OPC_MXU__POOL04  = 0x10,
@@ -405,6 +406,16 @@ enum {
     OPC_MXU_Q8ADD    = 0x07,
 };
 
+/*
+ * MXU pool 02
+ */
+enum {
+    OPC_MXU_S32CPS   = 0x00,
+    OPC_MXU_D16CPS   = 0x02,
+    OPC_MXU_Q8ABD    = 0x04,
+    OPC_MXU_Q16SAT   = 0x06,
+};
+
 /*
  * MXU pool 04 05 06 07 08 09 10 11
  */
@@ -1675,12 +1686,155 @@ static void gen_mxu_q8avg(DisasContext *ctx, bool round45)
 
 
 /*
- *                 MXU instruction category: Arithmetic
- *                 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *      MXU instruction category: Addition and subtraction
+ *      ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
- *                       Q8ADD
+ *              S32CPS      D16CPS
+ *                                       Q8ADD
  */
 
+/*
+ *  S32CPS
+ *    Update XRa if XRc < 0 by value of 0 - XRb
+ *    else XRa = XRb
+ */
+static void gen_mxu_S32CPS(DisasContext *ctx)
+{
+    uint32_t pad, XRc, XRb, XRa;
+
+    pad = extract32(ctx->opcode, 21, 5);
+    XRc = extract32(ctx->opcode, 14, 4);
+    XRb = extract32(ctx->opcode, 10, 4);
+    XRa = extract32(ctx->opcode,  6, 4);
+
+    if (unlikely(pad != 0)) {
+        /* opcode padding incorrect -> do nothing */
+    } else if (unlikely(XRa == 0)) {
+        /* destination is zero register -> do nothing */
+    } else if (unlikely(XRb == 0)) {
+        /* XRc make no sense 0 - 0 = 0 -> just set destination to zero */
+        tcg_gen_movi_tl(mxu_gpr[XRa - 1], 0);
+    } else if (unlikely(XRc == 0)) {
+        /* condition always false -> just move XRb to XRa */
+        tcg_gen_mov_tl(mxu_gpr[XRa - 1], mxu_gpr[XRb - 1]);
+    } else {
+        /* the most general case */
+        TCGv t0 = tcg_temp_new();
+        TCGLabel *l_not_less = gen_new_label();
+        TCGLabel *l_done = gen_new_label();
+
+        tcg_gen_brcondi_tl(TCG_COND_GE, mxu_gpr[XRc - 1], 0, l_not_less);
+        tcg_gen_neg_tl(t0, mxu_gpr[XRb - 1]);
+        tcg_gen_br(l_done);
+        gen_set_label(l_not_less);
+        gen_load_mxu_gpr(t0, XRb);
+        gen_set_label(l_done);
+        gen_store_mxu_gpr(t0, XRa);
+    }
+}
+
+/*
+ *  D16CPS
+ *    Update XRa[0..1] if XRc[0..1] < 0 by value of 0 - XRb[0..1]
+ *    else XRa[0..1] = XRb[0..1]
+ */
+static void gen_mxu_D16CPS(DisasContext *ctx)
+{
+    uint32_t pad, XRc, XRb, XRa;
+
+    pad = extract32(ctx->opcode, 21, 5);
+    XRc = extract32(ctx->opcode, 14, 4);
+    XRb = extract32(ctx->opcode, 10, 4);
+    XRa = extract32(ctx->opcode,  6, 4);
+
+    if (unlikely(pad != 0)) {
+        /* opcode padding incorrect -> do nothing */
+    } else if (unlikely(XRa == 0)) {
+        /* destination is zero register -> do nothing */
+    } else if (unlikely(XRb == 0)) {
+        /* XRc make no sense 0 - 0 = 0 -> just set destination to zero */
+        tcg_gen_movi_tl(mxu_gpr[XRa - 1], 0);
+    } else if (unlikely(XRc == 0)) {
+        /* condition always false -> just move XRb to XRa */
+        tcg_gen_mov_tl(mxu_gpr[XRa - 1], mxu_gpr[XRb - 1]);
+    } else {
+        /* the most general case */
+        TCGv t0 = tcg_temp_new();
+        TCGv t1 = tcg_temp_new();
+        TCGLabel *l_done_hi = gen_new_label();
+        TCGLabel *l_not_less_lo = gen_new_label();
+        TCGLabel *l_done_lo = gen_new_label();
+
+        tcg_gen_sextract_tl(t0, mxu_gpr[XRc - 1], 16, 16);
+        tcg_gen_sextract_tl(t1, mxu_gpr[XRb - 1], 16, 16);
+        tcg_gen_brcondi_tl(TCG_COND_GE, t0, 0, l_done_hi);
+        tcg_gen_subfi_tl(t1, 0, t1);
+
+        gen_set_label(l_done_hi);
+        tcg_gen_shli_i32(t1, t1, 16);
+
+        tcg_gen_sextract_tl(t0, mxu_gpr[XRc - 1],  0, 16);
+        tcg_gen_brcondi_tl(TCG_COND_GE, t0, 0, l_not_less_lo);
+        tcg_gen_sextract_tl(t0, mxu_gpr[XRb - 1],  0, 16);
+        tcg_gen_subfi_tl(t0, 0, t0);
+        tcg_gen_br(l_done_lo);
+
+        gen_set_label(l_not_less_lo);
+        tcg_gen_extract_tl(t0, mxu_gpr[XRb - 1],  0, 16);
+
+        gen_set_label(l_done_lo);
+        tcg_gen_deposit_tl(mxu_gpr[XRa - 1], t1, t0, 0, 16);
+    }
+}
+
+/*
+ *  Q8ABD XRa, XRb, XRc
+ *  Gets absolute difference for quadruple of 8-bit
+ *  packed in XRb to another one in XRc,
+ *  put the result in XRa.
+ *  a.k.a. XRa[0..3] = abs(XRb[0..3] - XRc[0..3]);
+ */
+static void gen_mxu_Q8ABD(DisasContext *ctx)
+{
+    uint32_t pad, XRc, XRb, XRa;
+
+    pad = extract32(ctx->opcode, 21, 3);
+    XRc = extract32(ctx->opcode, 14, 4);
+    XRb = extract32(ctx->opcode, 10, 4);
+    XRa = extract32(ctx->opcode,  6, 4);
+
+    if (unlikely(pad != 0)) {
+        /* opcode padding incorrect -> do nothing */
+    } else if (unlikely(XRa == 0)) {
+        /* destination is zero register -> do nothing */
+    } else if (unlikely((XRb == 0) && (XRc == 0))) {
+        /* both operands zero registers -> just set destination to zero */
+        tcg_gen_movi_tl(mxu_gpr[XRa - 1], 0);
+    } else {
+        /* the most general case */
+        TCGv t0 = tcg_temp_new();
+        TCGv t1 = tcg_temp_new();
+        TCGv t2 = tcg_temp_new();
+        TCGv t3 = tcg_temp_new();
+        TCGv t4 = tcg_temp_new();
+
+        gen_load_mxu_gpr(t3, XRb);
+        gen_load_mxu_gpr(t4, XRc);
+        tcg_gen_movi_tl(t2, 0);
+
+        for (int i = 0; i < 4; i++) {
+            tcg_gen_extract_tl(t0, t3, 8 * i, 8);
+            tcg_gen_extract_tl(t1, t4, 8 * i, 8);
+
+            tcg_gen_sub_tl(t0, t0, t1);
+            tcg_gen_abs_tl(t0, t0);
+
+            tcg_gen_deposit_tl(t2, t2, t0, 8 * i, 8);
+        }
+        gen_store_mxu_gpr(t2, XRa);
+    }
+}
+
 /*
  *  Q8ADD XRa, XRb, XRc, ptn2
  *  Add/subtract quadruple of 8-bit packed in XRb
@@ -1746,6 +1900,114 @@ static void gen_mxu_Q8ADD(DisasContext *ctx)
     }
 }
 
+/*
+ *                 MXU instruction category: Miscellaneous
+ *                 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *                       Q16SAT
+ */
+
+/*
+ *  Q16SAT XRa, XRb, XRc
+ *  Packs four 16-bit signed integers in XRb and XRc to
+ *  four saturated unsigned 8-bit into XRa.
+ *
+ */
+static void gen_mxu_Q16SAT(DisasContext *ctx)
+{
+    uint32_t pad, XRc, XRb, XRa;
+
+    pad = extract32(ctx->opcode, 21, 3);
+    XRc = extract32(ctx->opcode, 14, 4);
+    XRb = extract32(ctx->opcode, 10, 4);
+    XRa = extract32(ctx->opcode,  6, 4);
+
+    if (unlikely(pad != 0)) {
+        /* opcode padding incorrect -> do nothing */
+    } else if (unlikely(XRa == 0)) {
+        /* destination is zero register -> do nothing */
+    } else {
+        /* the most general case */
+        TCGv t0 = tcg_temp_new();
+        TCGv t1 = tcg_temp_new();
+        TCGv t2 = tcg_temp_new();
+
+        tcg_gen_movi_tl(t2, 0);
+        if (XRb != 0) {
+            TCGLabel *l_less_hi = gen_new_label();
+            TCGLabel *l_less_lo = gen_new_label();
+            TCGLabel *l_lo = gen_new_label();
+            TCGLabel *l_greater_hi = gen_new_label();
+            TCGLabel *l_greater_lo = gen_new_label();
+            TCGLabel *l_done = gen_new_label();
+
+            tcg_gen_sari_tl(t0, mxu_gpr[XRb - 1], 16);
+            tcg_gen_brcondi_tl(TCG_COND_LT, t0, 0, l_less_hi);
+            tcg_gen_brcondi_tl(TCG_COND_GT, t0, 255, l_greater_hi);
+            tcg_gen_br(l_lo);
+            gen_set_label(l_less_hi);
+            tcg_gen_movi_tl(t0, 0);
+            tcg_gen_br(l_lo);
+            gen_set_label(l_greater_hi);
+            tcg_gen_movi_tl(t0, 255);
+
+            gen_set_label(l_lo);
+            tcg_gen_shli_tl(t1, mxu_gpr[XRb - 1], 16);
+            tcg_gen_sari_tl(t1, t1, 16);
+            tcg_gen_brcondi_tl(TCG_COND_LT, t1, 0, l_less_lo);
+            tcg_gen_brcondi_tl(TCG_COND_GT, t1, 255, l_greater_lo);
+            tcg_gen_br(l_done);
+            gen_set_label(l_less_lo);
+            tcg_gen_movi_tl(t1, 0);
+            tcg_gen_br(l_done);
+            gen_set_label(l_greater_lo);
+            tcg_gen_movi_tl(t1, 255);
+
+            gen_set_label(l_done);
+            tcg_gen_shli_tl(t2, t0, 24);
+            tcg_gen_shli_tl(t1, t1, 16);
+            tcg_gen_or_tl(t2, t2, t1);
+        }
+
+        if (XRc != 0) {
+            TCGLabel *l_less_hi = gen_new_label();
+            TCGLabel *l_less_lo = gen_new_label();
+            TCGLabel *l_lo = gen_new_label();
+            TCGLabel *l_greater_hi = gen_new_label();
+            TCGLabel *l_greater_lo = gen_new_label();
+            TCGLabel *l_done = gen_new_label();
+
+            tcg_gen_sari_tl(t0, mxu_gpr[XRc - 1], 16);
+            tcg_gen_brcondi_tl(TCG_COND_LT, t0, 0, l_less_hi);
+            tcg_gen_brcondi_tl(TCG_COND_GT, t0, 255, l_greater_hi);
+            tcg_gen_br(l_lo);
+            gen_set_label(l_less_hi);
+            tcg_gen_movi_tl(t0, 0);
+            tcg_gen_br(l_lo);
+            gen_set_label(l_greater_hi);
+            tcg_gen_movi_tl(t0, 255);
+
+            gen_set_label(l_lo);
+            tcg_gen_shli_tl(t1, mxu_gpr[XRc - 1], 16);
+            tcg_gen_sari_tl(t1, t1, 16);
+            tcg_gen_brcondi_tl(TCG_COND_LT, t1, 0, l_less_lo);
+            tcg_gen_brcondi_tl(TCG_COND_GT, t1, 255, l_greater_lo);
+            tcg_gen_br(l_done);
+            gen_set_label(l_less_lo);
+            tcg_gen_movi_tl(t1, 0);
+            tcg_gen_br(l_done);
+            gen_set_label(l_greater_lo);
+            tcg_gen_movi_tl(t1, 255);
+
+            gen_set_label(l_done);
+            tcg_gen_shli_tl(t0, t0, 8);
+            tcg_gen_or_tl(t2, t2, t0);
+            tcg_gen_or_tl(t2, t2, t1);
+        }
+        gen_store_mxu_gpr(t2, XRa);
+    }
+}
+
 
 /*
  *                 MXU instruction category: align
@@ -2085,6 +2347,31 @@ static void decode_opc_mxu__pool01(DisasContext *ctx)
         break;
     }
 }
+
+static void decode_opc_mxu__pool02(DisasContext *ctx)
+{
+    uint32_t opcode = extract32(ctx->opcode, 18, 3);
+
+    switch (opcode) {
+    case OPC_MXU_S32CPS:
+        gen_mxu_S32CPS(ctx);
+        break;
+    case OPC_MXU_D16CPS:
+        gen_mxu_D16CPS(ctx);
+        break;
+    case OPC_MXU_Q8ABD:
+        gen_mxu_Q8ABD(ctx);
+        break;
+    case OPC_MXU_Q16SAT:
+        gen_mxu_Q16SAT(ctx);
+        break;
+    default:
+        MIPS_INVAL("decode_opc_mxu");
+        gen_reserved_instruction(ctx);
+        break;
+    }
+}
+
 static void decode_opc_mxu__pool04(DisasContext *ctx)
 {
     uint32_t reversed = extract32(ctx->opcode, 20, 1);
@@ -2334,6 +2621,9 @@ bool decode_ase_mxu(DisasContext *ctx, uint32_t insn)
         case OPC_MXU__POOL01:
             decode_opc_mxu__pool01(ctx);
             break;
+        case OPC_MXU__POOL02:
+            decode_opc_mxu__pool02(ctx);
+            break;
         case OPC_MXU__POOL04:
             decode_opc_mxu__pool04(ctx);
             break;
-- 
2.38.1



  parent reply	other threads:[~2023-07-10 22:29 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-07-10 22:25 [PULL 00/44] MIPS patches for 2023-07-10 Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 01/44] target/mips: Rework cp0_timer with clock API Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 02/44] target/mips: Implement Loongson CSR instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 03/44] hw/mips/loongson3_virt: Relax CPU restrictions for TCG Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 04/44] target/mips: Add emulation of MXU instructions for 32-bit load/store Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 05/44] target/mips: Add support of two XBurst CPUs Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 06/44] target/mips/mxu: Add LXW LXB LXH LXBU LXHU instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 07/44] target/mips/mxu: Add S32MADD/MADDU/MSUB/MSUBU instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 08/44] target/mips/mxu: Add Q8SLT Q8SLTU instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 09/44] target/mips/mxu: Fix D16MAX D16MIN Q8MAX Q8MIN instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 10/44] target/mips/mxu: Add S32SLT D16SLT D16AVG[R] Q8AVG[R] insns Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 11/44] target/mips/mxu: Add Q8ADD instruction Philippe Mathieu-Daudé
2023-07-10 22:25 ` Philippe Mathieu-Daudé [this message]
2023-07-10 22:25 ` [PULL 13/44] target/mips/mxu: Add D16MULF D16MULE instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 14/44] target/mips/mxu: Add D16MACF D16MACE instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 15/44] target/mips/mxu: Add D16MADL instruction Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 16/44] target/mips/mxu: Add S16MAD instruction Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 17/44] target/mips/mxu: Add Q16ADD instruction Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 18/44] target/mips/mxu: Add D32ADD instruction Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 19/44] target/mips/mxu: Add D32ACC D32ACCM D32ASUM instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 20/44] target/mips/mxu: Add D32ADDC instruction Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 21/44] target/mips/mxu: Add Q16ACC Q16ACCM D16ASUM instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 22/44] target/mips/mxu: Add Q8ADDE Q8ACCE D8SUM D8SUMC instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 23/44] target/mips/mxu: Add S8STD S8LDI S8SDI instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 24/44] target/mips/mxu: Add S16LDD S16STD S16LDI S16SDI instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 25/44] target/mips/mxu: Add S32MUL S32MULU S32EXTR S32EXTRV insns Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 26/44] target/mips/mxu: Add S32ALN S32LUI insns Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 27/44] target/mips/mxu: Add D32SARL D32SARW instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 28/44] target/mips/mxu: Add D32SLL D32SLR D32SAR instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 29/44] target/mips/mxu: Add Q16SLL Q16SLR Q16SAR instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 30/44] target/mips/mxu: Add D32/Q16- SLLV/SLRV/SARV instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 31/44] target/mips/mxu: Add S32/D16/Q8- MOVZ/MOVN instructions Philippe Mathieu-Daudé
2023-07-10 22:25 ` [PULL 32/44] target/mips/mxu: Add Q8MAC Q8MACSU instructions Philippe Mathieu-Daudé
2023-07-10 22:26 ` [PULL 33/44] target/mips/mxu: Add Q16SCOP instruction Philippe Mathieu-Daudé
2023-07-10 22:26 ` [PULL 34/44] target/mips/mxu: Add Q8MADL instruction Philippe Mathieu-Daudé
2023-07-10 22:26 ` [PULL 35/44] target/mips/mxu: Add S32SFL instruction Philippe Mathieu-Daudé
2023-07-10 22:26 ` [PULL 36/44] target/mips/mxu: Add Q8SAD instruction Philippe Mathieu-Daudé
2023-07-10 22:26 ` [PULL 37/44] target/mips: enable GINVx support for I6400 and I6500 Philippe Mathieu-Daudé
2023-07-10 22:26 ` [PULL 38/44] hw/ide/pci: Expose legacy interrupts as named GPIOs Philippe Mathieu-Daudé
2023-07-10 22:26 ` [PULL 39/44] hw/ide/via: Wire up IDE legacy interrupts in host device Philippe Mathieu-Daudé
2023-07-10 22:26 ` [PULL 40/44] hw/isa/vt82c686: Remove via_isa_set_irq() Philippe Mathieu-Daudé
2023-07-10 22:26 ` [PULL 41/44] hw/ide: Extract IDEBus assignment into bmdma_init() Philippe Mathieu-Daudé
2023-07-10 22:26 ` [PULL 42/44] hw/ide: Extract bmdma_status_writeb() Philippe Mathieu-Daudé
2023-07-10 22:26 ` [PULL 43/44] hw/ide/pci: Replace some magic numbers by constants Philippe Mathieu-Daudé
2023-07-10 22:26 ` [PULL 44/44] hw/ide/piix: Move registration of VMStateDescription to DeviceClass Philippe Mathieu-Daudé
2023-07-11  8:32 ` [PULL 00/44] MIPS patches for 2023-07-10 Richard Henderson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230710222611.50978-13-philmd@linaro.org \
    --to=philmd@linaro.org \
    --cc=chenhuacai@kernel.org \
    --cc=jiaxun.yang@flygoat.com \
    --cc=lis8215@gmail.com \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).