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 25/44] target/mips/mxu: Add S32MUL S32MULU S32EXTR S32EXTRV insns
Date: Tue, 11 Jul 2023 00:25:52 +0200	[thread overview]
Message-ID: <20230710222611.50978-26-philmd@linaro.org> (raw)
In-Reply-To: <20230710222611.50978-1-philmd@linaro.org>

From: Siarhei Volkau <lis8215@gmail.com>

These instructions are part of pool15, see the grand opcode organization
tree on top of the file.

Signed-off-by: Siarhei Volkau <lis8215@gmail.com>
Message-Id: <20230608104222.1520143-23-lis8215@gmail.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
---
 target/mips/tcg/mxu_translate.c | 200 +++++++++++++++++++++++++++++++-
 1 file changed, 196 insertions(+), 4 deletions(-)

diff --git a/target/mips/tcg/mxu_translate.c b/target/mips/tcg/mxu_translate.c
index caf5257952..0704a8c7ff 100644
--- a/target/mips/tcg/mxu_translate.c
+++ b/target/mips/tcg/mxu_translate.c
@@ -290,9 +290,9 @@
  *          ├─ 100010 ─ OPC_MXU_S8LDD
  *          ├─ 100011 ─ OPC_MXU_S8STD       15..14
  *          ├─ 100100 ─ OPC_MXU_S8LDI    ┌─ 00 ─ OPC_MXU_S32MUL
- *          ├─ 100101 ─ OPC_MXU_S8SDI    ├─ 00 ─ OPC_MXU_S32MULU
- *          │                            ├─ 00 ─ OPC_MXU_S32EXTR
- *          ├─ 100110 ─ OPC_MXU__POOL15 ─┴─ 00 ─ OPC_MXU_S32EXTRV
+ *          ├─ 100101 ─ OPC_MXU_S8SDI    ├─ 01 ─ OPC_MXU_S32MULU
+ *          │                            ├─ 10 ─ OPC_MXU_S32EXTR
+ *          ├─ 100110 ─ OPC_MXU__POOL15 ─┴─ 11 ─ OPC_MXU_S32EXTRV
  *          │
  *          │                               20..18
  *          ├─ 100111 ─ OPC_MXU__POOL16 ─┬─ 000 ─ OPC_MXU_D32SARW
@@ -385,6 +385,7 @@ enum {
     OPC_MXU_S8STD    = 0x23,
     OPC_MXU_S8LDI    = 0x24,
     OPC_MXU_S8SDI    = 0x25,
+    OPC_MXU__POOL15  = 0x26,
     OPC_MXU__POOL16  = 0x27,
     OPC_MXU__POOL17  = 0x28,
     OPC_MXU_S16LDD   = 0x2A,
@@ -477,6 +478,16 @@ enum {
     OPC_MXU_D8SUMC    = 0x02,
 };
 
+/*
+ * MXU pool 15
+ */
+enum {
+    OPC_MXU_S32MUL    = 0x00,
+    OPC_MXU_S32MULU   = 0x01,
+    OPC_MXU_S32EXTR   = 0x02,
+    OPC_MXU_S32EXTRV  = 0x03,
+};
+
 /*
  * MXU pool 16
  */
@@ -871,6 +882,47 @@ static void gen_mxu_s16std(DisasContext *ctx, bool postmodify)
     tcg_gen_qemu_st_tl(t1, t0, ctx->mem_idx, MO_UW);
 }
 
+/*
+ * S32MUL  XRa, XRd, rs, rt - Signed 32x32=>64 bit multiplication
+ * of GPR's and stores result into pair of MXU registers.
+ * It strains HI and LO registers.
+ *
+ * S32MULU XRa, XRd, rs, rt - Unsigned 32x32=>64 bit multiplication
+ * of GPR's and stores result into pair of MXU registers.
+ * It strains HI and LO registers.
+ */
+static void gen_mxu_s32mul(DisasContext *ctx, bool mulu)
+{
+    TCGv t0, t1;
+    uint32_t XRa, XRd, rs, rt;
+
+    t0 = tcg_temp_new();
+    t1 = tcg_temp_new();
+
+    XRa = extract32(ctx->opcode,  6, 4);
+    XRd = extract32(ctx->opcode, 10, 4);
+    rs  = extract32(ctx->opcode, 16, 5);
+    rt  = extract32(ctx->opcode, 21, 5);
+
+    if (unlikely(rs == 0 || rt == 0)) {
+        tcg_gen_movi_tl(t0, 0);
+        tcg_gen_movi_tl(t1, 0);
+    } else {
+        gen_load_gpr(t0, rs);
+        gen_load_gpr(t1, rt);
+
+        if (mulu) {
+            tcg_gen_mulu2_tl(t0, t1, t0, t1);
+        } else {
+            tcg_gen_muls2_tl(t0, t1, t0, t1);
+        }
+    }
+    tcg_gen_mov_tl(cpu_HI[0], t1);
+    tcg_gen_mov_tl(cpu_LO[0], t0);
+    gen_store_mxu_gpr(t1, XRa);
+    gen_store_mxu_gpr(t0, XRd);
+}
+
 /*
  * D16MUL  XRa, XRb, XRc, XRd, optn2 - Signed 16 bit pattern multiplication
  * D16MULF XRa, XRb, XRc, optn2 - Signed Q15 fraction pattern multiplication
@@ -3014,9 +3066,122 @@ static void gen_mxu_d32asum(DisasContext *ctx)
  *                 MXU instruction category: Miscellaneous
  *                 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
- *                       Q16SAT
+ *               S32EXTR
+ *               S32EXTRV
+ *                            Q16SAT
  */
 
+/*
+ *  S32EXTR XRa, XRd, rs, bits5
+ *    Extract bits5 bits from 64-bit pair {XRa:XRd}
+ *    starting from rs[4:0] offset and put to the XRa.
+ */
+static void gen_mxu_s32extr(DisasContext *ctx)
+{
+    TCGv t0, t1, t2, t3;
+    uint32_t XRa, XRd, rs, bits5;
+
+    t0 = tcg_temp_new();
+    t1 = tcg_temp_new();
+    t2 = tcg_temp_new();
+    t3 = tcg_temp_new();
+
+    XRa   = extract32(ctx->opcode,  6, 4);
+    XRd   = extract32(ctx->opcode, 10, 4);
+    bits5 = extract32(ctx->opcode, 16, 5);
+    rs    = extract32(ctx->opcode, 21, 5);
+
+    /* {tmp} = {XRa:XRd} >> (64 - rt - bits5); */
+    /* {XRa} = extract({tmp}, 0, bits5); */
+    if (bits5 > 0) {
+        TCGLabel *l_xra_only = gen_new_label();
+        TCGLabel *l_done = gen_new_label();
+
+        gen_load_mxu_gpr(t0, XRd);
+        gen_load_mxu_gpr(t1, XRa);
+        gen_load_gpr(t2, rs);
+        tcg_gen_andi_tl(t2, t2, 0x1f);
+        tcg_gen_subfi_tl(t2, 32, t2);
+        tcg_gen_brcondi_tl(TCG_COND_GE, t2, bits5, l_xra_only);
+        tcg_gen_subfi_tl(t2, bits5, t2);
+        tcg_gen_subfi_tl(t3, 32, t2);
+        tcg_gen_shr_tl(t0, t0, t3);
+        tcg_gen_shl_tl(t1, t1, t2);
+        tcg_gen_or_tl(t0, t0, t1);
+        tcg_gen_br(l_done);
+        gen_set_label(l_xra_only);
+        tcg_gen_subi_tl(t2, t2, bits5);
+        tcg_gen_shr_tl(t0, t1, t2);
+        gen_set_label(l_done);
+        tcg_gen_extract_tl(t0, t0, 0, bits5);
+    } else {
+        /* unspecified behavior but matches tests on real hardware*/
+        tcg_gen_movi_tl(t0, 0);
+    }
+    gen_store_mxu_gpr(t0, XRa);
+}
+
+/*
+ *  S32EXTRV XRa, XRd, rs, rt
+ *    Extract rt[4:0] bits from 64-bit pair {XRa:XRd}
+ *    starting from rs[4:0] offset and put to the XRa.
+ */
+static void gen_mxu_s32extrv(DisasContext *ctx)
+{
+    TCGv t0, t1, t2, t3, t4;
+    uint32_t XRa, XRd, rs, rt;
+
+    t0 = tcg_temp_new();
+    t1 = tcg_temp_new();
+    t2 = tcg_temp_new();
+    t3 = tcg_temp_new();
+    t4 = tcg_temp_new();
+    TCGLabel *l_xra_only = gen_new_label();
+    TCGLabel *l_done = gen_new_label();
+    TCGLabel *l_zero = gen_new_label();
+    TCGLabel *l_extract = gen_new_label();
+
+    XRa = extract32(ctx->opcode,  6, 4);
+    XRd = extract32(ctx->opcode, 10, 4);
+    rt  = extract32(ctx->opcode, 16, 5);
+    rs  = extract32(ctx->opcode, 21, 5);
+
+    /* {tmp} = {XRa:XRd} >> (64 - rs - rt) */
+    gen_load_mxu_gpr(t0, XRd);
+    gen_load_mxu_gpr(t1, XRa);
+    gen_load_gpr(t2, rs);
+    gen_load_gpr(t4, rt);
+    tcg_gen_brcondi_tl(TCG_COND_EQ, t4, 0, l_zero);
+    tcg_gen_andi_tl(t2, t2, 0x1f);
+    tcg_gen_subfi_tl(t2, 32, t2);
+    tcg_gen_brcond_tl(TCG_COND_GE, t2, t4, l_xra_only);
+    tcg_gen_sub_tl(t2, t4, t2);
+    tcg_gen_subfi_tl(t3, 32, t2);
+    tcg_gen_shr_tl(t0, t0, t3);
+    tcg_gen_shl_tl(t1, t1, t2);
+    tcg_gen_or_tl(t0, t0, t1);
+    tcg_gen_br(l_extract);
+
+    gen_set_label(l_xra_only);
+    tcg_gen_sub_tl(t2, t2, t4);
+    tcg_gen_shr_tl(t0, t1, t2);
+    tcg_gen_br(l_extract);
+
+    /* unspecified behavior but matches tests on real hardware*/
+    gen_set_label(l_zero);
+    tcg_gen_movi_tl(t0, 0);
+    tcg_gen_br(l_done);
+
+    /* {XRa} = extract({tmp}, 0, rt) */
+    gen_set_label(l_extract);
+    tcg_gen_subfi_tl(t4, 32, t4);
+    tcg_gen_shl_tl(t0, t0, t4);
+    tcg_gen_shr_tl(t0, t0, t4);
+
+    gen_set_label(l_done);
+    gen_store_mxu_gpr(t0, XRa);
+}
+
 /*
  *  Q16SAT XRa, XRb, XRc
  *  Packs four 16-bit signed integers in XRb and XRc to
@@ -3695,6 +3860,30 @@ static void decode_opc_mxu__pool14(DisasContext *ctx)
     }
 }
 
+static void decode_opc_mxu__pool15(DisasContext *ctx)
+{
+    uint32_t opcode = extract32(ctx->opcode, 14, 2);
+
+    switch (opcode) {
+    case OPC_MXU_S32MUL:
+        gen_mxu_s32mul(ctx, false);
+        break;
+    case OPC_MXU_S32MULU:
+        gen_mxu_s32mul(ctx, true);
+        break;
+    case OPC_MXU_S32EXTR:
+        gen_mxu_s32extr(ctx);
+        break;
+    case OPC_MXU_S32EXTRV:
+        gen_mxu_s32extrv(ctx);
+        break;
+    default:
+        MIPS_INVAL("decode_opc_mxu");
+        gen_reserved_instruction(ctx);
+        break;
+    }
+}
+
 static void decode_opc_mxu__pool16(DisasContext *ctx)
 {
     uint32_t opcode = extract32(ctx->opcode, 18, 3);
@@ -3884,6 +4073,9 @@ bool decode_ase_mxu(DisasContext *ctx, uint32_t insn)
         case OPC_MXU_S8SDI:
             gen_mxu_s8std(ctx, true);
             break;
+        case OPC_MXU__POOL15:
+            decode_opc_mxu__pool15(ctx);
+            break;
         case OPC_MXU__POOL16:
             decode_opc_mxu__pool16(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 ` [PULL 12/44] target/mips/mxu: Add S32CPS D16CPS Q8ABD Q16SAT insns Philippe Mathieu-Daudé
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 ` Philippe Mathieu-Daudé [this message]
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=20230710222611.50978-26-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).