[PATCH i-g-t v5 04/17] lib/gpgpu_shader: Add write_on_exception template
Manszewski, Christoph
christoph.manszewski at intel.com
Wed Sep 4 13:27:38 UTC 2024
Hi Zbigniew,
On 4.09.2024 14:23, Zbigniew Kempczyński wrote:
> On Thu, Aug 29, 2024 at 04:45:34PM +0200, Christoph Manszewski wrote:
>> From: Andrzej Hajda <andrzej.hajda at 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 at intel.com>
>> ---
>> lib/gpgpu_shader.c | 56 ++++++++++++++++++++
>> lib/gpgpu_shader.h | 2 +
>> lib/iga64_generated_codes.c | 102 +++++++++++++++++++++++++++++++++++-
>> 3 files changed, 159 insertions(+), 1 deletion(-)
>>
>> diff --git a/lib/gpgpu_shader.c b/lib/gpgpu_shader.c
>> index c723577e6..4097857f2 100644
>> --- a/lib/gpgpu_shader.c
>> +++ b/lib/gpgpu_shader.c
>> @@ -634,6 +634,62 @@ 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\
>> + // Clear message header \n\
>> +(W) mov (16|M0) r4.0<1>:ud 0x0:ud \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\
>
> ARG(4)-ARG(6) are unused and confusing here. Please get rid of them.
Yup, already did it locally for the next revision based on your feedback
from the previous patch as it is a similar case (this time for code
actually added by this series =)). Thanks!
>
>> +#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\
>> + // 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);
>
> I thought first and third argument might be directly entered in the code
> but after replace there's harder to find where they are used. I mean
> I looked for ARG(0) to find the place where 2 lands. So I suggest just
> to remove 'value' duplicates for ARG(4)-ARG(6) only.
Arghh. Ok then, I will bring them back before sending the next revision.
Thanks,
Christoph
>
> --
> Zbigniew
>
>> +}
>> +
>> /**
>> * 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 dd849eebc..c084ddcd7 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 33b7cd843e3b009c123a85a6c520d7d0
>> +#define MD5_SUM_IGA64_ASMS 85cd452f0cdcf3fe54bb0b2a7424e12a
>>
>> struct iga64_template const iga64_code_gpgpu_fill[] = {
>> { .gen_ver = 2000, .size = 44, .code = (const uint32_t []) {
>> @@ -192,6 +192,106 @@ 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 []) {
>> + 0x80100061, 0x04054220, 0x00000000, 0x00000000,
>> + 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,
>> + 0x80041961, 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 = 1270, .size = 72, .code = (const uint32_t []) {
>> + 0x80040061, 0x04054220, 0x00000000, 0x00000000,
>> + 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 = 1260, .size = 68, .code = (const uint32_t []) {
>> + 0x80100061, 0x04054220, 0x00000000, 0x00000000,
>> + 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 = 72, .code = (const uint32_t []) {
>> + 0x80040061, 0x04054220, 0x00000000, 0x00000000,
>> + 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 = 68, .code = (const uint32_t []) {
>> + 0x80040061, 0x04054220, 0x00000000, 0x00000000,
>> + 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 []) {
>> 0x80100061, 0x04054220, 0x00000000, 0x00000000,
>> --
>> 2.34.1
>>
More information about the igt-dev
mailing list