From: "Grzegorzek, Dominik" <dominik.grzegorzek@intel.com>
To: "igt-dev@lists.freedesktop.org" <igt-dev@lists.freedesktop.org>,
"Manszewski, Christoph" <christoph.manszewski@intel.com>
Cc: "Patelczyk, Maciej" <maciej.patelczyk@intel.com>,
"Hajda, Andrzej" <andrzej.hajda@intel.com>,
"Kempczynski, Zbigniew" <zbigniew.kempczynski@intel.com>,
"Piatkowski, Dominik Karol" <dominik.karol.piatkowski@intel.com>,
"Sikora, Pawel" <pawel.sikora@intel.com>,
"Kuoppala, Mika" <mika.kuoppala@intel.com>,
"Mun, Gwan-gyeong" <gwan-gyeong.mun@intel.com>,
"kamil.konieczny@linux.intel.com"
<kamil.konieczny@linux.intel.com>,
Kolanupaka Naveena <kolanupaka.naveena@intel.com>
Subject: Re: [PATCH i-g-t v3 07/14] lib/gpgpu_shader: Add write_on_exception template
Date: Mon, 19 Aug 2024 10:09:15 +0000 [thread overview]
Message-ID: <2f3fe337c9a19d7e2477de8ada969b0b1a3fb537.camel@intel.com> (raw)
In-Reply-To: <20240809123813.109365-8-christoph.manszewski@intel.com>
On Fri, 2024-08-09 at 14:38 +0200, Christoph Manszewski wrote:
> From: Andrzej Hajda <andrzej.hajda@intel.com>
>
> Writing specific value to memory location on unexpected value in exception
> register allows to report errors from inside shader or siplet.
>
> Signed-off-by: Andrzej Hajda <andrzej.hajda@intel.com>
> Signed-off-by: Christoph Manszewski <christoph.manszewski@intel.com>
> ---
> lib/gpgpu_shader.c | 56 ++++++++++++++++++++++++++
> lib/gpgpu_shader.h | 2 +
> lib/iga64_generated_codes.c | 79 ++++++++++++++++++++++++++++++++++++-
> 3 files changed, 136 insertions(+), 1 deletion(-)
>
> diff --git a/lib/gpgpu_shader.c b/lib/gpgpu_shader.c
> index 3b16db593..a98abc57e 100644
> --- a/lib/gpgpu_shader.c
> +++ b/lib/gpgpu_shader.c
> @@ -628,6 +628,62 @@ void gpgpu_shader__write_dword(struct gpgpu_shader *shdr, uint32_t value,
> ", 2, y_offset, 3, value, value, value, value);
> }
>
> +/**
> + * gpgpu_shader__write_on_exception:
> + * @shdr: shader to be modified
> + * @value: dword to be written
> + * @y_offset: write target offset within the surface in rows
> + * @mask: mask to be applied on exception register
> + * @expected: expected value of exception register with @mask applied
> + *
> + * Check if bits specified by @mask in exception register(cr0.1) are equal
> + * to provided ones: cr0.1 & @mask == @expected,
> + * if yes fill dword in (row, column/dword) == (tg_id_y + @y_offset, tg_id_x).
> + */
> +void gpgpu_shader__write_on_exception(struct gpgpu_shader *shdr, uint32_t value,
> + uint32_t y_offset, uint32_t mask, uint32_t expected)
> +{
> + emit_iga64_code(shdr, write_on_exception, " \n\
> + // Payload \n\
> +(W) mov (1|M0) r5.0<1>:ud ARG(3):ud \n\
> +(W) mov (1|M0) r5.1<1>:ud ARG(4):ud \n\
> +(W) mov (1|M0) r5.2<1>:ud ARG(5):ud \n\
> +(W) mov (1|M0) r5.3<1>:ud ARG(6):ud \n\
> +#if GEN_VER < 2000 // prepare Media Block Write \n\
> + // X offset of the block in bytes := (thread group id X << ARG(0)) \n\
> +(W) shl (1|M0) r4.0<1>:ud r0.1<0;1,0>:ud ARG(0):ud \n\
> + // Y offset of the block in rows := thread group id Y \n\
> +(W) mov (1|M0) r4.1<1>:ud r0.6<0;1,0>:ud \n\
> +(W) add (1|M0) r4.1<1>:ud r4.1<0;1,0>:ud ARG(1):ud \n\
> + // block width [0,63] representing 1 to 64 bytes \n\
> +(W) mov (1|M0) r4.2<1>:ud ARG(2):ud \n\
> + // FFTID := FFTID from R0 header \n\
> +(W) mov (1|M0) r4.4<1>:ud r0.5<0;1,0>:ud \n\
> +#else // prepare Typed 2D Block Store \n\
> + // Load r2.0-3 with tg id X << ARG(0) \n\
> +(W) shl (1|M0) r2.0<1>:ud r0.1<0;1,0>:ud ARG(0):ud \n\
> + // Load r2.4-7 with tg id Y + ARG(1):ud \n\
> +(W) mov (1|M0) r2.1<1>:ud r0.6<0;1,0>:ud \n\
> +(W) add (1|M0) r2.1<1>:ud r2.1<0;1,0>:ud ARG(1):ud \n\
> + // payload setup \n\
> +(W) mov (16|M0) r4.0<1>:ud 0x0:ud \n\
Move r4.0 clearing part before to common code before the if statement like in [1].
For < 2000 we depend on clear r4.0 register. If it was used before, by any different shader, we may
have broken code.
[1] https://patchwork.freedesktop.org/patch/608230/?series=137284&rev=2
With that, it is:
Reviewed-by: Dominik Grzegorzek <dominik.grzegorzek@intel.com>
> + // Store X and Y block start (160:191 and 192:223) \n\
> +(W) mov (2|M0) r4.5<1>:ud r2.0<2;2,1>:ud \n\
> + // Store X and Y block max_size (224:231 and 232:239) \n\
> +(W) mov (1|M0) r4.7<1>:ud ARG(2):ud \n\
> +#endif \n\
> + // Check if masked exception is equal to provided value and write conditionally \n\
> +(W) and (1|M0) r3.0<1>:ud cr0.1<0;1,0>:ud ARG(7):ud \n\
> +(W) mov (1|M0) f0.0<1>:ud 0x0:ud \n\
> +(W) cmp (1|M0) (eq)f0.0 null:ud r3.0<0;1,0>:ud ARG(8):ud \n\
> +#if GEN_VER < 2000 // Media Block Write \n\
> +(W&f0.0) send.dc1 (16|M0) null r4 src1_null 0 0x40A8000 \n\
> +#else // Typed 2D Block Store \n\
> +(W&f0.0) send.tgm (16|M0) null r4 null:0 0 0x64000007 \n\
> +#endif \n\
> + ", 2, y_offset, 3, value, value, value, value, mask, expected);
> +}
> +
> /**
> * gpgpu_shader__end_system_routine:
> * @shdr: shader to be modified
> diff --git a/lib/gpgpu_shader.h b/lib/gpgpu_shader.h
> index e4ca0be4c..76ff4989e 100644
> --- a/lib/gpgpu_shader.h
> +++ b/lib/gpgpu_shader.h
> @@ -74,6 +74,8 @@ void gpgpu_shader__end_system_routine_step_if_eq(struct gpgpu_shader *shdr,
> void gpgpu_shader__write_aip(struct gpgpu_shader *shdr, uint32_t y_offset);
> void gpgpu_shader__write_dword(struct gpgpu_shader *shdr, uint32_t value,
> uint32_t y_offset);
> +void gpgpu_shader__write_on_exception(struct gpgpu_shader *shdr, uint32_t dw,
> + uint32_t y_offset, uint32_t mask, uint32_t value);
> void gpgpu_shader__label(struct gpgpu_shader *shdr, int label_id);
> void gpgpu_shader__jump(struct gpgpu_shader *shdr, int label_id);
> void gpgpu_shader__jump_neq(struct gpgpu_shader *shdr, int label_id,
> diff --git a/lib/iga64_generated_codes.c b/lib/iga64_generated_codes.c
> index fea436dee..71429d442 100644
> --- a/lib/iga64_generated_codes.c
> +++ b/lib/iga64_generated_codes.c
> @@ -3,7 +3,7 @@
>
> #include "gpgpu_shader.h"
>
> -#define MD5_SUM_IGA64_ASMS 61a15534954fe7c6bd0e983fbfd54c27
> +#define MD5_SUM_IGA64_ASMS 88529cc180578939c0b8c4bb29da7db6
>
> struct iga64_template const iga64_code_end_system_routine_step_if_eq[] = {
> { .gen_ver = 2000, .size = 44, .code = (const uint32_t []) {
> @@ -93,6 +93,83 @@ struct iga64_template const iga64_code_breakpoint_suppress[] = {
> }}
> };
>
> +struct iga64_template const iga64_code_write_on_exception[] = {
> + { .gen_ver = 2000, .size = 68, .code = (const uint32_t []) {
> + 0x80000061, 0x05054220, 0x00000000, 0xc0ded003,
> + 0x80000061, 0x05154220, 0x00000000, 0xc0ded004,
> + 0x80000061, 0x05254220, 0x00000000, 0xc0ded005,
> + 0x80000061, 0x05354220, 0x00000000, 0xc0ded006,
> + 0x80000069, 0x02058220, 0x02000014, 0xc0ded000,
> + 0x80000061, 0x02150220, 0x00000064, 0x00000000,
> + 0x80001940, 0x02158220, 0x02000214, 0xc0ded001,
> + 0x80100061, 0x04054220, 0x00000000, 0x00000000,
> + 0x80041a61, 0x04550220, 0x00220205, 0x00000000,
> + 0x80000061, 0x04754220, 0x00000000, 0xc0ded002,
> + 0x80000965, 0x03058220, 0x02008010, 0xc0ded007,
> + 0x80000961, 0x30014220, 0x00000000, 0x00000000,
> + 0x80001a70, 0x00018220, 0x12000304, 0xc0ded008,
> + 0x84134031, 0x00000000, 0xd00e0494, 0x04000000,
> + 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> + 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> + 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> + }},
> + { .gen_ver = 1272, .size = 64, .code = (const uint32_t []) {
> + 0x80000061, 0x05054220, 0x00000000, 0xc0ded003,
> + 0x80000061, 0x05154220, 0x00000000, 0xc0ded004,
> + 0x80000061, 0x05254220, 0x00000000, 0xc0ded005,
> + 0x80000061, 0x05354220, 0x00000000, 0xc0ded006,
> + 0x80000069, 0x04058220, 0x02000014, 0xc0ded000,
> + 0x80000061, 0x04150220, 0x00000064, 0x00000000,
> + 0x80001940, 0x04158220, 0x02000414, 0xc0ded001,
> + 0x80000061, 0x04254220, 0x00000000, 0xc0ded002,
> + 0x80000061, 0x04450220, 0x00000054, 0x00000000,
> + 0x80000965, 0x03058220, 0x02008010, 0xc0ded007,
> + 0x80000961, 0x30014220, 0x00000000, 0x00000000,
> + 0x80001a70, 0x00018220, 0x12000304, 0xc0ded008,
> + 0x84134031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> + 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> + 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> + }},
> + { .gen_ver = 1250, .size = 68, .code = (const uint32_t []) {
> + 0x80000061, 0x05054220, 0x00000000, 0xc0ded003,
> + 0x80000061, 0x05254220, 0x00000000, 0xc0ded004,
> + 0x80000061, 0x05454220, 0x00000000, 0xc0ded005,
> + 0x80000061, 0x05654220, 0x00000000, 0xc0ded006,
> + 0x80000069, 0x04058220, 0x02000024, 0xc0ded000,
> + 0x80000061, 0x04250220, 0x000000c4, 0x00000000,
> + 0x80001940, 0x04258220, 0x02000424, 0xc0ded001,
> + 0x80000061, 0x04454220, 0x00000000, 0xc0ded002,
> + 0x80000061, 0x04850220, 0x000000a4, 0x00000000,
> + 0x80000965, 0x03058220, 0x02008020, 0xc0ded007,
> + 0x80000961, 0x30014220, 0x00000000, 0x00000000,
> + 0x80001a70, 0x00018220, 0x12000304, 0xc0ded008,
> + 0x80001a01, 0x00010000, 0x00000000, 0x00000000,
> + 0x81044031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> + 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> + 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> + }},
> + { .gen_ver = 0, .size = 64, .code = (const uint32_t []) {
> + 0x80000061, 0x05054220, 0x00000000, 0xc0ded003,
> + 0x80000061, 0x05254220, 0x00000000, 0xc0ded004,
> + 0x80000061, 0x05454220, 0x00000000, 0xc0ded005,
> + 0x80000061, 0x05654220, 0x00000000, 0xc0ded006,
> + 0x80000069, 0x04058220, 0x02000024, 0xc0ded000,
> + 0x80000061, 0x04250220, 0x000000c4, 0x00000000,
> + 0x80000140, 0x04258220, 0x02000424, 0xc0ded001,
> + 0x80000061, 0x04454220, 0x00000000, 0xc0ded002,
> + 0x80000061, 0x04850220, 0x000000a4, 0x00000000,
> + 0x80000165, 0x03058220, 0x02008020, 0xc0ded007,
> + 0x80000161, 0x30014220, 0x00000000, 0x00000000,
> + 0x80000270, 0x00018220, 0x12000304, 0xc0ded008,
> + 0x8104a031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> + 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> + 0x80000101, 0x00010000, 0x00000000, 0x00000000,
> + }}
> +};
> +
> struct iga64_template const iga64_code_media_block_write[] = {
> { .gen_ver = 2000, .size = 56, .code = (const uint32_t []) {
> 0x80000061, 0x05054220, 0x00000000, 0xc0ded003,
next prev parent reply other threads:[~2024-08-19 10:09 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-09 12:37 [PATCH i-g-t v3 00/14] Test coverage for GPU debug support Christoph Manszewski
2024-08-09 12:38 ` [PATCH i-g-t v3 01/14] drm-uapi/xe: Sync with oa uapi fix Christoph Manszewski
2024-08-09 14:21 ` Kamil Konieczny
2024-08-09 12:38 ` [PATCH i-g-t v3 02/14] drm-uapi/xe: Sync with eudebug uapi Christoph Manszewski
2024-08-20 7:52 ` Zbigniew Kempczyński
2024-08-09 12:38 ` [PATCH i-g-t v3 03/14] lib/xe_ioctl: Add wrapper with vm_bind_op extension parameter Christoph Manszewski
2024-08-20 7:54 ` Zbigniew Kempczyński
2024-08-09 12:38 ` [PATCH i-g-t v3 04/14] lib/xe_eudebug: Introduce eu debug testing framework Christoph Manszewski
2024-08-19 8:30 ` Grzegorzek, Dominik
2024-08-19 15:33 ` Manszewski, Christoph
2024-08-20 8:14 ` Zbigniew Kempczyński
2024-08-20 16:14 ` Manszewski, Christoph
2024-08-20 17:45 ` Kamil Konieczny
2024-08-21 7:05 ` Manszewski, Christoph
2024-08-21 9:31 ` Zbigniew Kempczyński
2024-08-22 15:39 ` Kamil Konieczny
2024-08-23 7:58 ` Manszewski, Christoph
2024-08-09 12:38 ` [PATCH i-g-t v3 05/14] tests/xe_eudebug: Test eudebug resource tracking and manipulation Christoph Manszewski
2024-08-09 12:38 ` [PATCH i-g-t v3 06/14] lib/gpgpu_shader: Extend shader building library Christoph Manszewski
2024-08-09 12:38 ` [PATCH i-g-t v3 07/14] lib/gpgpu_shader: Add write_on_exception template Christoph Manszewski
2024-08-19 10:09 ` Grzegorzek, Dominik [this message]
2024-08-09 12:38 ` [PATCH i-g-t v3 08/14] lib/gpgpu_shader: Add set/clear exception register (cr0.1) helpers Christoph Manszewski
2024-08-09 12:38 ` [PATCH i-g-t v3 09/14] lib/intel_batchbuffer: Add helper to get pointer at specified offset Christoph Manszewski
2024-08-19 10:10 ` Grzegorzek, Dominik
2024-08-09 12:38 ` [PATCH i-g-t v3 10/14] lib/gpgpu_shader: Allow enabling illegal opcode exceptions in shader Christoph Manszewski
2024-08-19 10:12 ` Grzegorzek, Dominik
2024-08-09 12:38 ` [PATCH i-g-t v3 11/14] tests/xe_exec_sip: Extend SIP interaction testing Christoph Manszewski
2024-08-21 9:49 ` Zbigniew Kempczyński
2024-08-09 12:38 ` [PATCH i-g-t v3 12/14] lib/intel_batchbuffer: Add support for long-running mode execution Christoph Manszewski
2024-08-09 12:38 ` [PATCH i-g-t v3 13/14] tests/xe_eudebug_online: Debug client which runs workloads on EU Christoph Manszewski
2024-08-09 14:38 ` Kamil Konieczny
2024-08-19 15:31 ` Manszewski, Christoph
2024-08-19 9:58 ` Grzegorzek, Dominik
2024-08-19 15:36 ` Manszewski, Christoph
2024-08-09 12:38 ` [PATCH i-g-t v3 14/14] tests/xe_live_ktest: Add xe_eudebug live test Christoph Manszewski
2024-08-09 13:36 ` ✗ GitLab.Pipeline: warning for Test coverage for GPU debug support (rev3) Patchwork
2024-08-09 13:50 ` ✓ CI.xeBAT: success " Patchwork
2024-08-09 14:01 ` ✓ Fi.CI.BAT: " Patchwork
2024-08-09 14:24 ` [PATCH i-g-t v3 00/14] Test coverage for GPU debug support Kamil Konieczny
2024-08-09 15:40 ` ✗ CI.xeFULL: failure for Test coverage for GPU debug support (rev3) Patchwork
2024-08-10 18:30 ` ✗ Fi.CI.IGT: " Patchwork
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=2f3fe337c9a19d7e2477de8ada969b0b1a3fb537.camel@intel.com \
--to=dominik.grzegorzek@intel.com \
--cc=andrzej.hajda@intel.com \
--cc=christoph.manszewski@intel.com \
--cc=dominik.karol.piatkowski@intel.com \
--cc=gwan-gyeong.mun@intel.com \
--cc=igt-dev@lists.freedesktop.org \
--cc=kamil.konieczny@linux.intel.com \
--cc=kolanupaka.naveena@intel.com \
--cc=maciej.patelczyk@intel.com \
--cc=mika.kuoppala@intel.com \
--cc=pawel.sikora@intel.com \
--cc=zbigniew.kempczynski@intel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox