From: David Gibson <david@gibson.dropbear.id.au>
To: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Cc: gkurz@kaod.org, qemu-ppc@nongnu.org, qemu-devel@nongnu.org,
rth@twiddle.net
Subject: Re: [Qemu-devel] [PATCH v2 04/15] target/ppc: introduce separate VSX_CMP macro for xvcmp* instructions
Date: Wed, 12 Jun 2019 11:52:24 +1000 [thread overview]
Message-ID: <20190612015224.GG3998@umbus.fritz.box> (raw)
In-Reply-To: <20190602110903.3431-5-mark.cave-ayland@ilande.co.uk>
[-- Attachment #1: Type: text/plain, Size: 10552 bytes --]
On Sun, Jun 02, 2019 at 12:08:52PM +0100, Mark Cave-Ayland wrote:
> Rather than perform the VSR register decoding within the helper itself,
> introduce a new VSX_CMP macro which performs the decode based upon xT, xA
> and xB at translation time.
>
> Subsequent commits will make the same changes for other instructions however
> the xvcmp* instructions are different in that they return a set of flags to be
> optionally written back to the crf[6] register. Move this logic from the
> helper function to the generator function, along with the
> float_status update.
What's the advantage of this. Since we still have a helper, don't we
suffer the cost of the helper call *plus* the now-generated
instructions?
>
> Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
> ---
> target/ppc/fpu_helper.c | 15 +++++-------
> target/ppc/helper.h | 20 +++++++++------
> target/ppc/translate/vsx-impl.inc.c | 49 +++++++++++++++++++++++++++++++------
> 3 files changed, 59 insertions(+), 25 deletions(-)
>
> diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
> index 5edf913a89..4b9b695333 100644
> --- a/target/ppc/fpu_helper.c
> +++ b/target/ppc/fpu_helper.c
> @@ -2746,12 +2746,11 @@ VSX_MAX_MINJ(xsminjdp, 0);
> * exp - expected result of comparison
> */
> #define VSX_CMP(op, nels, tp, fld, cmp, svxvc, exp) \
> -void helper_##op(CPUPPCState *env, uint32_t opcode) \
> +uint32_t helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \
> + ppc_vsr_t *xa, ppc_vsr_t *xb) \
> { \
> - ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
> - ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
> - ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
> ppc_vsr_t t = *xt; \
> + uint32_t crf6 = 0; \
> int i; \
> int all_true = 1; \
> int all_false = 1; \
> @@ -2780,11 +2779,9 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \
> } \
> \
> *xt = t; \
> - if ((opcode >> (31 - 21)) & 1) { \
> - env->crf[6] = (all_true ? 0x8 : 0) | (all_false ? 0x2 : 0); \
> - } \
> - do_float_check_status(env, GETPC()); \
> - }
> + crf6 = (all_true ? 0x8 : 0) | (all_false ? 0x2 : 0); \
> + return crf6; \
> +}
>
> VSX_CMP(xvcmpeqdp, 2, float64, VsrD(i), eq, 0, 1)
> VSX_CMP(xvcmpgedp, 2, float64, VsrD(i), le, 1, 1)
> diff --git a/target/ppc/helper.h b/target/ppc/helper.h
> index 02b67a333e..8666415169 100644
> --- a/target/ppc/helper.h
> +++ b/target/ppc/helper.h
> @@ -108,6 +108,10 @@ DEF_HELPER_FLAGS_1(ftsqrt, TCG_CALL_NO_RWG_SE, i32, i64)
> #define dh_ctype_avr ppc_avr_t *
> #define dh_is_signed_avr dh_is_signed_ptr
>
> +#define dh_alias_vsr ptr
> +#define dh_ctype_vsr ppc_vsr_t *
> +#define dh_is_signed_vsr dh_is_signed_ptr
> +
> DEF_HELPER_3(vavgub, void, avr, avr, avr)
> DEF_HELPER_3(vavguh, void, avr, avr, avr)
> DEF_HELPER_3(vavguw, void, avr, avr, avr)
> @@ -468,10 +472,10 @@ DEF_HELPER_2(xvnmsubadp, void, env, i32)
> DEF_HELPER_2(xvnmsubmdp, void, env, i32)
> DEF_HELPER_2(xvmaxdp, void, env, i32)
> DEF_HELPER_2(xvmindp, void, env, i32)
> -DEF_HELPER_2(xvcmpeqdp, void, env, i32)
> -DEF_HELPER_2(xvcmpgedp, void, env, i32)
> -DEF_HELPER_2(xvcmpgtdp, void, env, i32)
> -DEF_HELPER_2(xvcmpnedp, void, env, i32)
> +DEF_HELPER_FLAGS_4(xvcmpeqdp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
> +DEF_HELPER_FLAGS_4(xvcmpgedp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
> +DEF_HELPER_FLAGS_4(xvcmpgtdp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
> +DEF_HELPER_FLAGS_4(xvcmpnedp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
> DEF_HELPER_2(xvcvdpsp, void, env, i32)
> DEF_HELPER_2(xvcvdpsxds, void, env, i32)
> DEF_HELPER_2(xvcvdpsxws, void, env, i32)
> @@ -506,10 +510,10 @@ DEF_HELPER_2(xvnmsubasp, void, env, i32)
> DEF_HELPER_2(xvnmsubmsp, void, env, i32)
> DEF_HELPER_2(xvmaxsp, void, env, i32)
> DEF_HELPER_2(xvminsp, void, env, i32)
> -DEF_HELPER_2(xvcmpeqsp, void, env, i32)
> -DEF_HELPER_2(xvcmpgesp, void, env, i32)
> -DEF_HELPER_2(xvcmpgtsp, void, env, i32)
> -DEF_HELPER_2(xvcmpnesp, void, env, i32)
> +DEF_HELPER_FLAGS_4(xvcmpeqsp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
> +DEF_HELPER_FLAGS_4(xvcmpgesp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
> +DEF_HELPER_FLAGS_4(xvcmpgtsp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
> +DEF_HELPER_FLAGS_4(xvcmpnesp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
> DEF_HELPER_2(xvcvspdp, void, env, i32)
> DEF_HELPER_2(xvcvsphp, void, env, i32)
> DEF_HELPER_2(xvcvhpsp, void, env, i32)
> diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
> index 199d22da97..fb52a5bbf7 100644
> --- a/target/ppc/translate/vsx-impl.inc.c
> +++ b/target/ppc/translate/vsx-impl.inc.c
> @@ -20,6 +20,13 @@ static inline void set_cpu_vsrl(int n, TCGv_i64 src)
> tcg_gen_st_i64(src, cpu_env, vsr64_offset(n, false));
> }
>
> +static inline TCGv_ptr gen_vsr_ptr(int reg)
> +{
> + TCGv_ptr r = tcg_temp_new_ptr();
> + tcg_gen_addi_ptr(r, cpu_env, vsr_full_offset(reg));
> + return r;
> +}
> +
> #define VSX_LOAD_SCALAR(name, operation) \
> static void gen_##name(DisasContext *ctx) \
> { \
> @@ -957,6 +964,40 @@ VSX_VECTOR_MOVE(xvnabssp, OP_NABS, SGN_MASK_SP)
> VSX_VECTOR_MOVE(xvnegsp, OP_NEG, SGN_MASK_SP)
> VSX_VECTOR_MOVE(xvcpsgnsp, OP_CPSGN, SGN_MASK_SP)
>
> +#define VSX_CMP(name, op1, op2, inval, type) \
> +static void gen_##name(DisasContext *ctx) \
> +{ \
> + TCGv_i32 ignored; \
> + TCGv_ptr xt, xa, xb; \
> + if (unlikely(!ctx->vsx_enabled)) { \
> + gen_exception(ctx, POWERPC_EXCP_VSXU); \
> + return; \
> + } \
> + xt = gen_vsr_ptr(xT(ctx->opcode)); \
> + xa = gen_vsr_ptr(xA(ctx->opcode)); \
> + xb = gen_vsr_ptr(xB(ctx->opcode)); \
> + if ((ctx->opcode >> (31 - 21)) & 1) { \
> + gen_helper_##name(cpu_crf[6], cpu_env, xt, xa, xb); \
> + } else { \
> + ignored = tcg_temp_new_i32(); \
> + gen_helper_##name(ignored, cpu_env, xt, xa, xb); \
> + tcg_temp_free_i32(ignored); \
> + } \
> + gen_helper_float_check_status(cpu_env); \
> + tcg_temp_free_ptr(xt); \
> + tcg_temp_free_ptr(xa); \
> + tcg_temp_free_ptr(xb); \
> +}
> +
> +VSX_CMP(xvcmpeqdp, 0x0C, 0x0C, 0, PPC2_VSX)
> +VSX_CMP(xvcmpgedp, 0x0C, 0x0E, 0, PPC2_VSX)
> +VSX_CMP(xvcmpgtdp, 0x0C, 0x0D, 0, PPC2_VSX)
> +VSX_CMP(xvcmpnedp, 0x0C, 0x0F, 0, PPC2_ISA300)
> +VSX_CMP(xvcmpeqsp, 0x0C, 0x08, 0, PPC2_VSX)
> +VSX_CMP(xvcmpgesp, 0x0C, 0x0A, 0, PPC2_VSX)
> +VSX_CMP(xvcmpgtsp, 0x0C, 0x09, 0, PPC2_VSX)
> +VSX_CMP(xvcmpnesp, 0x0C, 0x0B, 0, PPC2_VSX)
> +
> #define GEN_VSX_HELPER_2(name, op1, op2, inval, type) \
> static void gen_##name(DisasContext *ctx) \
> { \
> @@ -1096,10 +1137,6 @@ GEN_VSX_HELPER_2(xvnmsubadp, 0x04, 0x1E, 0, PPC2_VSX)
> GEN_VSX_HELPER_2(xvnmsubmdp, 0x04, 0x1F, 0, PPC2_VSX)
> GEN_VSX_HELPER_2(xvmaxdp, 0x00, 0x1C, 0, PPC2_VSX)
> GEN_VSX_HELPER_2(xvmindp, 0x00, 0x1D, 0, PPC2_VSX)
> -GEN_VSX_HELPER_2(xvcmpeqdp, 0x0C, 0x0C, 0, PPC2_VSX)
> -GEN_VSX_HELPER_2(xvcmpgtdp, 0x0C, 0x0D, 0, PPC2_VSX)
> -GEN_VSX_HELPER_2(xvcmpgedp, 0x0C, 0x0E, 0, PPC2_VSX)
> -GEN_VSX_HELPER_2(xvcmpnedp, 0x0C, 0x0F, 0, PPC2_ISA300)
> GEN_VSX_HELPER_2(xvcvdpsp, 0x12, 0x18, 0, PPC2_VSX)
> GEN_VSX_HELPER_2(xvcvdpsxds, 0x10, 0x1D, 0, PPC2_VSX)
> GEN_VSX_HELPER_2(xvcvdpsxws, 0x10, 0x0D, 0, PPC2_VSX)
> @@ -1134,10 +1171,6 @@ GEN_VSX_HELPER_2(xvnmsubasp, 0x04, 0x1A, 0, PPC2_VSX)
> GEN_VSX_HELPER_2(xvnmsubmsp, 0x04, 0x1B, 0, PPC2_VSX)
> GEN_VSX_HELPER_2(xvmaxsp, 0x00, 0x18, 0, PPC2_VSX)
> GEN_VSX_HELPER_2(xvminsp, 0x00, 0x19, 0, PPC2_VSX)
> -GEN_VSX_HELPER_2(xvcmpeqsp, 0x0C, 0x08, 0, PPC2_VSX)
> -GEN_VSX_HELPER_2(xvcmpgtsp, 0x0C, 0x09, 0, PPC2_VSX)
> -GEN_VSX_HELPER_2(xvcmpgesp, 0x0C, 0x0A, 0, PPC2_VSX)
> -GEN_VSX_HELPER_2(xvcmpnesp, 0x0C, 0x0B, 0, PPC2_VSX)
> GEN_VSX_HELPER_2(xvcvspdp, 0x12, 0x1C, 0, PPC2_VSX)
> GEN_VSX_HELPER_2(xvcvhpsp, 0x16, 0x1D, 0x18, PPC2_ISA300)
> GEN_VSX_HELPER_2(xvcvsphp, 0x16, 0x1D, 0x19, PPC2_ISA300)
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
next prev parent reply other threads:[~2019-06-12 2:03 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-02 11:08 [Qemu-devel] [PATCH v2 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
2019-06-02 11:08 ` [Qemu-devel] [PATCH v2 01/15] target/ppc: remove getVSR()/putVSR() from fpu_helper.c Mark Cave-Ayland
2019-06-12 19:45 ` Richard Henderson
2019-06-16 8:01 ` Mark Cave-Ayland
2019-06-02 11:08 ` [Qemu-devel] [PATCH v2 02/15] target/ppc: remove getVSR()/putVSR() from mem_helper.c Mark Cave-Ayland
2019-06-12 1:04 ` David Gibson
2019-06-16 7:40 ` Mark Cave-Ayland
2019-06-12 19:47 ` Richard Henderson
2019-06-16 7:57 ` Mark Cave-Ayland
2019-06-02 11:08 ` [Qemu-devel] [PATCH v2 03/15] target/ppc: remove getVSR()/putVSR() from int_helper.c Mark Cave-Ayland
2019-06-12 19:49 ` Richard Henderson
2019-06-02 11:08 ` [Qemu-devel] [PATCH v2 04/15] target/ppc: introduce separate VSX_CMP macro for xvcmp* instructions Mark Cave-Ayland
2019-06-12 1:52 ` David Gibson [this message]
2019-06-12 4:22 ` Richard Henderson
2019-06-12 5:16 ` David Gibson
2019-06-12 15:58 ` Richard Henderson
2019-06-12 19:59 ` Richard Henderson
2019-06-02 11:08 ` [Qemu-devel] [PATCH v2 05/15] target/ppc: introduce GEN_VSX_HELPER_X3 macro to fpu_helper.c Mark Cave-Ayland
2019-06-12 20:02 ` Richard Henderson
2019-06-02 11:08 ` [Qemu-devel] [PATCH v2 06/15] target/ppc: introduce separate generator and helper for xscvqpdp Mark Cave-Ayland
2019-06-12 20:04 ` Richard Henderson
2019-06-02 11:08 ` [Qemu-devel] [PATCH v2 07/15] target/ppc: introduce GEN_VSX_HELPER_X2 macro to fpu_helper.c Mark Cave-Ayland
2019-06-12 20:05 ` Richard Henderson
2019-06-02 11:08 ` [Qemu-devel] [PATCH v2 08/15] target/ppc: introduce GEN_VSX_HELPER_X2_AB " Mark Cave-Ayland
2019-06-12 20:06 ` Richard Henderson
2019-06-02 11:08 ` [Qemu-devel] [PATCH v2 09/15] target/ppc: introduce GEN_VSX_HELPER_X1 " Mark Cave-Ayland
2019-06-13 3:28 ` Richard Henderson
2019-06-02 11:08 ` [Qemu-devel] [PATCH v2 10/15] target/ppc: introduce GEN_VSX_HELPER_R3 " Mark Cave-Ayland
2019-06-13 3:29 ` Richard Henderson
2019-06-02 11:08 ` [Qemu-devel] [PATCH v2 11/15] target/ppc: introduce GEN_VSX_HELPER_R2 " Mark Cave-Ayland
2019-06-13 3:31 ` Richard Henderson
2019-06-02 11:09 ` [Qemu-devel] [PATCH v2 12/15] target/ppc: introduce GEN_VSX_HELPER_R2_AB " Mark Cave-Ayland
2019-06-02 11:09 ` [Qemu-devel] [PATCH v2 13/15] target/ppc: decode target register in VSX_VECTOR_LOAD_STORE_LENGTH at translation time Mark Cave-Ayland
2019-06-02 11:09 ` [Qemu-devel] [PATCH v2 14/15] target/ppc: decode target register in VSX_EXTRACT_INSERT " Mark Cave-Ayland
2019-06-02 11:09 ` [Qemu-devel] [PATCH v2 15/15] target/ppc: improve VSX_FMADD with new GEN_VSX_HELPER_VSX_MADD macro Mark Cave-Ayland
2019-06-13 3:41 ` Richard Henderson
2019-06-03 10:48 ` [Qemu-devel] [PATCH v2 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up no-reply
2019-06-04 18:48 ` Mark Cave-Ayland
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=20190612015224.GG3998@umbus.fritz.box \
--to=david@gibson.dropbear.id.au \
--cc=gkurz@kaod.org \
--cc=mark.cave-ayland@ilande.co.uk \
--cc=qemu-devel@nongnu.org \
--cc=qemu-ppc@nongnu.org \
--cc=rth@twiddle.net \
/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).