From: Amit Machhiwal <amachhiw@linux.ibm.com>
To: Chinmay Rath <rathc@linux.ibm.com>
Cc: qemu-devel@nongnu.org, qemu-ppc@nongnu.org,
harshpb@linux.ibm.com, milesg@linux.ibm.com, npiggin@gmail.com,
richard.henderson@linaro.org, vishalc@linux.ibm.com,
tshah@linux.ibm.com, shivangu@linux.ibm.com,
ojaswin@linux.ibm.com, aboorvad@linux.ibm.com,
amachhiw@linux.ibm.com, shivani@linux.ibm.com,
mkchauras@gmail.com, uverma@linux.ibm.com,
nikhilks@linux.ibm.com
Subject: Re: [PATCH v2 25/37] target/ppc: Move rlwimi, rlwinm instructions to decodetree
Date: Wed, 26 Aug 2026 21:11:14 +0530 [thread overview]
Message-ID: <20260826210722.30d51e70-b7-amachhiw@linux.ibm.com> (raw)
In-Reply-To: <20260826050923.74756-26-rathc@linux.ibm.com>
On 2026/08/26 10:38 AM, Chinmay Rath wrote:
> From: Tanushree Shah <tshah@linux.ibm.com>
>
> -Moving the following instructions to decodetree specification:
> rlwimi : M-form
> rlwimi. : M-form
> rlwinm : M-form
> rlwinm. : M-form
> The changes were verified by validating that the tcg ops generated by
> those instructions remain the same, which were captured with the
> "-d in_asm,op" flag.
>
> Additionally, validated using small assembly tests confirming the
> destination register is correctly updated based on rotated and masked
> source values and confirmed that the value was same before and after
> the change
>
> Signed-off-by: Tanushree Shah <tshah@linux.ibm.com>
> Reviewed-by: Glenn Miles <milesg@linux.ibm.com>
> Signed-off-by: Chinmay Rath <rathc@linux.ibm.com>
> ---
> target/ppc/insn32.decode | 6 ++
> target/ppc/translate.c | 106 ---------------------
> target/ppc/translate/fixedpoint-impl.c.inc | 98 +++++++++++++++++++
> 3 files changed, 104 insertions(+), 106 deletions(-)
>
> diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
> index eed963bd71..8f027e7ff5 100644
> --- a/target/ppc/insn32.decode
> +++ b/target/ppc/insn32.decode
> @@ -312,6 +312,9 @@
>
> @Z23_te_tbp ...... ....0 te:5 ....0 rmc:2 ........ rc:1 &Z23_te_tb frt=%z23_frtp frb=%z23_frbp
>
> +&M ra rs sh mb me rc:bool
> +@M ...... rs:5 ra:5 sh:5 mb:5 me:5 rc:1 &M
> +
> ### Fixed-Point Load Instructions
>
> LBZ 100010 ..... ..... ................ @D
> @@ -561,6 +564,9 @@ SRADI 011111 ..... ..... ..... 110011101 . . @XS
>
> EXTSWSLI 011111 ..... ..... ..... 110111101 . . @XS
>
> +RLWIMI 010100 ..... ..... ..... ..... ...... @M
> +RLWINM 010101 ..... ..... ..... ..... ...... @M
> +
> ## BCD Assist
>
> ADDG6S 011111 ..... ..... ..... - 001001010 - @X
> diff --git a/target/ppc/translate.c b/target/ppc/translate.c
> index 712990cf2d..d2c51b4d59 100644
> --- a/target/ppc/translate.c
> +++ b/target/ppc/translate.c
> @@ -2012,110 +2012,6 @@ static void gen_pause(DisasContext *ctx)
>
> /*** Integer rotate ***/
>
> -/* rlwimi & rlwimi. */
> -static void gen_rlwimi(DisasContext *ctx)
> -{
> - TCGv t_ra = cpu_gpr[rA(ctx->opcode)];
> - TCGv t_rs = cpu_gpr[rS(ctx->opcode)];
> - uint32_t sh = SH(ctx->opcode);
> - uint32_t mb = MB(ctx->opcode);
> - uint32_t me = ME(ctx->opcode);
> -
> - if (sh == (31 - me) && mb <= me) {
> - tcg_gen_deposit_tl(t_ra, t_ra, t_rs, sh, me - mb + 1);
> - } else {
> - target_ulong mask;
> - bool mask_in_32b = true;
> - TCGv t1;
> -
> -#if defined(TARGET_PPC64)
> - mb += 32;
> - me += 32;
> -#endif
> - mask = MASK(mb, me);
> -
> -#if defined(TARGET_PPC64)
> - if (mask > 0xffffffffu) {
> - mask_in_32b = false;
> - }
> -#endif
> - t1 = tcg_temp_new();
> - if (mask_in_32b) {
> - TCGv_i32 t0 = tcg_temp_new_i32();
> - tcg_gen_trunc_tl_i32(t0, t_rs);
> - tcg_gen_rotli_i32(t0, t0, sh);
> - tcg_gen_extu_i32_tl(t1, t0);
> - } else {
> -#if defined(TARGET_PPC64)
> - tcg_gen_deposit_i64(t1, t_rs, t_rs, 32, 32);
> - tcg_gen_rotli_i64(t1, t1, sh);
> -#else
> - g_assert_not_reached();
> -#endif
> - }
> -
> - tcg_gen_andi_tl(t1, t1, mask);
> - tcg_gen_andi_tl(t_ra, t_ra, ~mask);
> - tcg_gen_or_tl(t_ra, t_ra, t1);
> - }
> - if (unlikely(Rc(ctx->opcode) != 0)) {
> - gen_set_Rc0(ctx, t_ra);
> - }
> -}
> -
> -/* rlwinm & rlwinm. */
> -static void gen_rlwinm(DisasContext *ctx)
> -{
> - TCGv t_ra = cpu_gpr[rA(ctx->opcode)];
> - TCGv t_rs = cpu_gpr[rS(ctx->opcode)];
> - int sh = SH(ctx->opcode);
> - int mb = MB(ctx->opcode);
> - int me = ME(ctx->opcode);
> - int len = me - mb + 1;
> - int rsh = (32 - sh) & 31;
> -
> - if (sh != 0 && len > 0 && me == (31 - sh)) {
> - tcg_gen_deposit_z_tl(t_ra, t_rs, sh, len);
> - } else if (me == 31 && rsh + len <= 32) {
> - tcg_gen_extract_tl(t_ra, t_rs, rsh, len);
> - } else {
> - target_ulong mask;
> - bool mask_in_32b = true;
> -#if defined(TARGET_PPC64)
> - mb += 32;
> - me += 32;
> -#endif
> - mask = MASK(mb, me);
> -#if defined(TARGET_PPC64)
> - if (mask > 0xffffffffu) {
> - mask_in_32b = false;
> - }
> -#endif
> - if (mask_in_32b) {
> - if (sh == 0) {
> - tcg_gen_andi_tl(t_ra, t_rs, mask);
> - } else {
> - TCGv_i32 t0 = tcg_temp_new_i32();
> - tcg_gen_trunc_tl_i32(t0, t_rs);
> - tcg_gen_rotli_i32(t0, t0, sh);
> - tcg_gen_andi_i32(t0, t0, mask);
> - tcg_gen_extu_i32_tl(t_ra, t0);
> - }
> - } else {
> -#if defined(TARGET_PPC64)
> - tcg_gen_deposit_i64(t_ra, t_rs, t_rs, 32, 32);
> - tcg_gen_rotli_i64(t_ra, t_ra, sh);
> - tcg_gen_andi_i64(t_ra, t_ra, mask);
> -#else
> - g_assert_not_reached();
> -#endif
> - }
> - }
> - if (unlikely(Rc(ctx->opcode) != 0)) {
> - gen_set_Rc0(ctx, t_ra);
> - }
> -}
> -
> /* rlwnm & rlwnm. */
> static void gen_rlwnm(DisasContext *ctx)
> {
> @@ -4807,8 +4703,6 @@ GEN_HANDLER(invalid, 0x00, 0x00, 0x00, 0xFFFFFFFF, PPC_NONE),
> GEN_HANDLER_E(copy, 0x1F, 0x06, 0x18, 0x03C00001, PPC_NONE, PPC2_ISA300),
> GEN_HANDLER_E(cp_abort, 0x1F, 0x06, 0x1A, 0x03FFF801, PPC_NONE, PPC2_ISA300),
> GEN_HANDLER_E(paste, 0x1F, 0x06, 0x1C, 0x03C00000, PPC_NONE, PPC2_ISA300),
> -GEN_HANDLER(rlwimi, 0x14, 0xFF, 0xFF, 0x00000000, PPC_INTEGER),
> -GEN_HANDLER(rlwinm, 0x15, 0xFF, 0xFF, 0x00000000, PPC_INTEGER),
> GEN_HANDLER(rlwnm, 0x17, 0xFF, 0xFF, 0x00000000, PPC_INTEGER),
> /* handles lfdp, lxsd, lxssp */
> GEN_HANDLER_E(dform39, 0x39, 0xFF, 0xFF, 0x00000000, PPC_NONE, PPC2_ISA205),
> diff --git a/target/ppc/translate/fixedpoint-impl.c.inc b/target/ppc/translate/fixedpoint-impl.c.inc
> index 82fb645279..8fcee7a89d 100644
> --- a/target/ppc/translate/fixedpoint-impl.c.inc
> +++ b/target/ppc/translate/fixedpoint-impl.c.inc
> @@ -1874,6 +1874,104 @@ static bool trans_SRAWI(DisasContext *ctx, arg_SRAWI *a)
> return true;
> }
>
> +static bool trans_RLWIMI(DisasContext *ctx, arg_RLWIMI *a)
> +{
> + TCGv t_ra = cpu_gpr[a->ra];
> + TCGv t_rs = cpu_gpr[a->rs];
> +
> + if (a->sh == (31 - a->me) && a->mb <= a->me) {
> + tcg_gen_deposit_tl(t_ra, t_ra, t_rs, a->sh, a->me - a->mb + 1);
> + } else {
> + target_ulong mask;
> + bool mask_in_32b = true;
> + TCGv t1;
> +
> +#if defined(TARGET_PPC64)
> + a->mb += 32;
> + a->me += 32;
The old gen_rlwimi/gen_rlwinm used local int mb/int me for this
adjustment, keeping the opcode struct immutable. Writing back into a->
fields is contrary to normal decodetree style — the arg_* struct is an
input, not a scratch pad. Please use local copies instead:
> +#endif
> + mask = MASK((uint32_t)a->mb, (uint32_t)a->me);
MASK() takes uint64_t on PPC64 builds. Both translators in this patch
should use the same form. If the local-variable suggestion above is
adopted, the cast becomes unnecessary in both (the local int will
promote cleanly), and both can just use MASK(mb, me).
> +
> +#if defined(TARGET_PPC64)
> + if (mask > 0xffffffffu) {
> + mask_in_32b = false;
> + }
> +#endif
> + t1 = tcg_temp_new();
> + if (mask_in_32b) {
> + TCGv_i32 t0 = tcg_temp_new_i32();
> + tcg_gen_trunc_tl_i32(t0, t_rs);
> + tcg_gen_rotli_i32(t0, t0, a->sh);
> + tcg_gen_extu_i32_tl(t1, t0);
> + } else {
> +#if defined(TARGET_PPC64)
> + tcg_gen_deposit_i64(t1, t_rs, t_rs, 32, 32);
> + tcg_gen_rotli_i64(t1, t1, a->sh);
> +#else
> + g_assert_not_reached();
> +#endif
> + }
> +
> + tcg_gen_andi_tl(t1, t1, mask);
> + tcg_gen_andi_tl(t_ra, t_ra, ~mask);
> + tcg_gen_or_tl(t_ra, t_ra, t1);
> + }
> + if (unlikely(a->rc)) {
> + gen_set_Rc0(ctx, t_ra);
> + }
> + return true;
> +}
> +
> +static bool trans_RLWINM(DisasContext *ctx, arg_RLWINM *a)
> +{
> + TCGv t_ra = cpu_gpr[a->ra];
> + TCGv t_rs = cpu_gpr[a->rs];
> + int len = a->me - a->mb + 1;
> + int rsh = (32 - a->sh) & 31;
> +
> + if (a->sh != 0 && len > 0 && a->me == (31 - a->sh)) {
> + tcg_gen_deposit_z_tl(t_ra, t_rs, a->sh, len);
> + } else if (a->me == 31 && rsh + len <= 32) {
> + tcg_gen_extract_tl(t_ra, t_rs, rsh, len);
> + } else {
> + target_ulong mask;
> + bool mask_in_32b = true;
> +#if defined(TARGET_PPC64)
> + a->mb += 32;
> + a->me += 32;
> +#endif
> + mask = MASK(a->mb, a->me);
> +#if defined(TARGET_PPC64)
> + if (mask > 0xffffffffu) {
> + mask_in_32b = false;
> + }
> +#endif
> + if (mask_in_32b) {
> + if (a->sh == 0) {
> + tcg_gen_andi_tl(t_ra, t_rs, mask);
> + } else {
> + TCGv_i32 t0 = tcg_temp_new_i32();
> + tcg_gen_trunc_tl_i32(t0, t_rs);
> + tcg_gen_rotli_i32(t0, t0, a->sh);
> + tcg_gen_andi_i32(t0, t0, mask);
> + tcg_gen_extu_i32_tl(t_ra, t0);
> + }
> + } else {
> +#if defined(TARGET_PPC64)
> + tcg_gen_deposit_i64(t_ra, t_rs, t_rs, 32, 32);
> + tcg_gen_rotli_i64(t_ra, t_ra, a->sh);
> + tcg_gen_andi_i64(t_ra, t_ra, mask);
> +#else
> + g_assert_not_reached();
> +#endif
> + }
> + }
> + if (unlikely(a->rc)) {
> + gen_set_Rc0(ctx, t_ra);
> + }
> + return true;
> +}
> +
> static void do_fetch_inc_conditional(DisasContext *ctx, MemOp memop,
> TCGv EA, int rt,
> TCGCond cond, int addend)
> --
> 2.55.0
>
next prev parent reply other threads:[~2026-08-26 15:42 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-26 5:08 [PATCH v2 00/37] target/ppc: PPC TCG Improvements (decodetree migrations + ISA 2.07 flag updates) Chinmay Rath
2026-08-26 5:08 ` [PATCH v2 01/37] target/ppc: Migrate extswsli to decodetree Chinmay Rath
2026-08-26 7:33 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 02/37] target/ppc: Migrate atomic loads " Chinmay Rath
2026-08-26 9:20 ` Amit Machhiwal
2026-08-26 12:28 ` Chinmay Rath
2026-08-26 12:30 ` Chinmay Rath
2026-08-26 5:08 ` [PATCH v2 03/37] target/ppc: Convert cache instructions " Chinmay Rath
2026-08-26 10:20 ` Amit Machhiwal
2026-08-26 13:09 ` Chinmay Rath
2026-08-26 13:17 ` Amit Machhiwal
2026-08-27 9:13 ` Chinmay Rath
2026-08-27 8:37 ` Chinmay Rath
2026-08-26 5:08 ` [PATCH v2 04/37] target/ppc: Move vector merge " Chinmay Rath
2026-08-26 10:57 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 05/37] target/ppc: Move vector pack " Chinmay Rath
2026-08-26 11:04 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 06/37] target/ppc: Move st{b, h, w, d, q}cx " Chinmay Rath
2026-08-26 11:18 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 07/37] target/ppc: convert slw, srw instruction via decode spec Chinmay Rath
2026-08-26 11:28 ` Amit Machhiwal
2026-08-26 11:30 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 08/37] target/ppc: convert sraw[i] " Chinmay Rath
2026-08-26 11:41 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 09/37] target/ppc: Convert mcrf to decode tree Chinmay Rath
2026-08-26 11:52 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 10/37] target/ppc: Move fixed-point Shift insns to decodetree Chinmay Rath
2026-08-26 5:08 ` [PATCH v2 11/37] target/ppc: Move fixed-point byte-reversal store " Chinmay Rath
2026-08-26 5:08 ` [PATCH v2 12/37] target/ppc: Move GPR atomic load/store instructions " Chinmay Rath
2026-08-26 12:05 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 13/37] target/ppc: Move isync instruction " Chinmay Rath
2026-08-26 12:20 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 14/37] target/ppc: Convert b{a, l, la} to decode tree Chinmay Rath
2026-08-26 12:24 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 15/37] target/ppc: move various conditional branch insns to decodetree Chinmay Rath
2026-08-26 12:38 ` Amit Machhiwal
2026-08-26 12:45 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 16/37] target/ppc: Fix TRANS* macro variadic arguments handling Chinmay Rath
2026-08-26 12:50 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 17/37] target/ppc: Move wait instruction to decodetree Chinmay Rath
2026-08-26 13:12 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 18/37] target/ppc: Move sleep & friends " Chinmay Rath
2026-08-26 13:26 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 19/37] target/ppc: Refactor sleep and its variants to use a common helper Chinmay Rath
2026-08-26 13:38 ` Amit Machhiwal
2026-08-26 14:30 ` Miles Glenn
2026-08-26 5:08 ` [PATCH v2 20/37] target/ppc: Move Condition Register access instructions to decodetree Chinmay Rath
2026-08-26 14:24 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 21/37] target/ppc: Move Condition Register logical " Chinmay Rath
2026-08-26 14:43 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 22/37] target/ppc: make do_ea_calc_ra available for 32 bit builds Chinmay Rath
2026-08-26 14:48 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 23/37] target/ppc: Move Fixed-Point Load/Store String instructions to decodetree Chinmay Rath
2026-08-26 15:19 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 24/37] target/ppc: Move VMX integer arithmetic and BCD " Chinmay Rath
2026-08-26 15:30 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 25/37] target/ppc: Move rlwimi, rlwinm " Chinmay Rath
2026-08-26 15:41 ` Amit Machhiwal [this message]
2026-08-26 5:08 ` [PATCH v2 26/37] target/ppc: Move lmw, stmw " Chinmay Rath
2026-08-26 15:44 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 27/37] target/ppc: Move mfmsr, mtmsr[d] " Chinmay Rath
2026-08-26 15:49 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 28/37] target/ppc: Move byte-reverse " Chinmay Rath
2026-08-26 15:54 ` Amit Machhiwal
2026-08-27 10:52 ` Chinmay Rath
2026-08-26 5:08 ` [PATCH v2 29/37] target/ppc: Move system call and rfi " Chinmay Rath
2026-08-26 16:54 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 30/37] target/ppc: Replace PPC2_VSX207 flag with PPC2_ISA207 Chinmay Rath
2026-08-26 16:56 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 31/37] target/ppc: Use PPC2_ISA207 instead of PPC2_BCTAR_ISA207 Chinmay Rath
2026-08-26 16:58 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 32/37] target/ppc: Use PPC2_ISA207 instead of PPC2_LSQ_ISA207 Chinmay Rath
2026-08-26 17:01 ` Amit Machhiwal
2026-08-26 5:08 ` [PATCH v2 33/37] target/ppc: Use PPC2_ISA207 instead of PPC2_ALTIVEC_207 Chinmay Rath
2026-08-26 17:23 ` Amit Machhiwal
2026-08-26 5:09 ` [PATCH v2 34/37] target/ppc: Use PPC2_ISA207 instead of PPC2_ISA207S Chinmay Rath
2026-08-26 5:09 ` [PATCH v2 35/37] target/ppc: Reorder PPC2 flags Chinmay Rath
2026-08-26 5:09 ` [PATCH v2 36/37] target/ppc: Add ICBT support for ISA version 2.07 Chinmay Rath
2026-08-26 5:09 ` [PATCH v2 37/37] target/ppc: Add self as maintainer for PowerPC TCG CPUs Chinmay Rath
2026-08-26 5:41 ` Amit Machhiwal
2026-08-26 6:25 ` Gautam Menghani
2026-08-26 9:37 ` Aditya Gupta
2026-08-27 9:50 ` [PATCH v2 00/37] target/ppc: PPC TCG Improvements (decodetree migrations + ISA 2.07 flag updates) Aniket Sahu
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=20260826210722.30d51e70-b7-amachhiw@linux.ibm.com \
--to=amachhiw@linux.ibm.com \
--cc=aboorvad@linux.ibm.com \
--cc=harshpb@linux.ibm.com \
--cc=milesg@linux.ibm.com \
--cc=mkchauras@gmail.com \
--cc=nikhilks@linux.ibm.com \
--cc=npiggin@gmail.com \
--cc=ojaswin@linux.ibm.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-ppc@nongnu.org \
--cc=rathc@linux.ibm.com \
--cc=richard.henderson@linaro.org \
--cc=shivangu@linux.ibm.com \
--cc=shivani@linux.ibm.com \
--cc=tshah@linux.ibm.com \
--cc=uverma@linux.ibm.com \
--cc=vishalc@linux.ibm.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.