[PATCH i-g-t 1/2] lib/gpgpu_shader: Add x_offset parameter for gpgpu_shader__write_on_exception

Manszewski, Christoph christoph.manszewski at intel.com
Fri Oct 4 12:24:48 UTC 2024


Hi Zbigniew,

On 1.10.2024 17:07, Zbigniew Kempczyński wrote:
> On Wed, Sep 25, 2024 at 03:30:02PM +0200, Christoph Manszewski wrote:
>> Currently gpgpu_shader__write_on_exception always writes the first
>> column equal to thread group ID x. Make it possible to specify an offset
>> from that value.
>>
>> Signed-off-by: Christoph Manszewski <christoph.manszewski at intel.com>
>> Cc: Zbigniew Kempczyński <zbigniew.kempczynski at intel.com>
>> ---
>>   lib/gpgpu_shader.c          | 29 +++++++-------
>>   lib/gpgpu_shader.h          |  4 +-
>>   lib/iga64_generated_codes.c | 77 ++++++++++++++++++++-----------------
>>   tests/intel/xe_exec_sip.c   |  6 +--
>>   4 files changed, 62 insertions(+), 54 deletions(-)
>>
>> diff --git a/lib/gpgpu_shader.c b/lib/gpgpu_shader.c
>> index 6d8c7ebb8..8df8d9612 100644
>> --- a/lib/gpgpu_shader.c
>> +++ b/lib/gpgpu_shader.c
>> @@ -670,6 +670,7 @@ void gpgpu_shader__set_exception(struct gpgpu_shader *shdr, uint32_t value)
>>    * gpgpu_shader__write_on_exception:
>>    * @shdr: shader to be modified
>>    * @value: dword to be written
>> + * @x_offset: write target offset within the surface in columns added to the 'thread group id x'
>>    * @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
>> @@ -678,45 +679,47 @@ void gpgpu_shader__set_exception(struct gpgpu_shader *shdr, uint32_t value)
>>    * to provided ones: cr0.1 & @mask == @expected,
>>    * if yes fill dword in (row, column/dword) == (tg_id_y + @y_offset, tg_id_x).
> 
> tg_id_x + @x_offset

Sure, nice catch!

> 
>>    */
>> -void gpgpu_shader__write_on_exception(struct gpgpu_shader *shdr, uint32_t value,
>> +void gpgpu_shader__write_on_exception(struct gpgpu_shader *shdr, uint32_t value, uint32_t x_offset,
>>   				      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)               r5.0<1>:ud    ARG(4):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\
>> +(W)	add (1|M0)               r4.0<1>:ud    r0.1<0;1,0>:ud	 ARG(1):ud		\n\
>> +(W)	shl (1|M0)               r4.0<1>:ud    r4.0<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\
>> +(W)	add (1|M0)               r4.1<1>:ud    r4.1<0;1,0>:ud   ARG(2):ud		\n\
> 
> You may drop mov and below should be enough:
> 
> 	add (1|M0)               r4.1<1>:ud    r0.6<0;1,0>:ud    ARG(2):ud

Ok, makes sense.

> 
>>   	// block width [0,63] representing 1 to 64 bytes				\n\
>> -(W)	mov (1|M0)               r4.2<1>:ud    ARG(2):ud				\n\
>> +(W)	mov (1|M0)               r4.2<1>:ud    ARG(3):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\
>> +	// Load r2.0 with tg id (X + ARG(1)) << ARG(0)					\n\
>> +(W)	add (1|M0)               r2.0<1>:ud    r0.1<0;1,0>:ud	 ARG(1):ud		\n\
>> +(W)	shl (1|M0)               r2.0<1>:ud    r2.0<0;1,0>:ud    ARG(0):ud		\n\
>> +	// Load r2.4-7 with tg id Y + ARG(2):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\
>> +(W)	add (1|M0)               r2.1<1>:ud    r2.1<0;1,0>:ud    ARG(2):ud		\n\
> 
> Same here.

Ok

> 
>>   	// 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\
>> +(W)	mov (1|M0)               r4.7<1>:ud    ARG(3):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(4):ud		\n\
>> +(W)      and (1|M0)              r3.0<1>:ud     cr0.1<0;1,0>:ud ARG(5):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(5):ud		\n\
>> +(W)      cmp (1|M0)     (eq)f0.0 null:ud        r3.0<0;1,0>:ud  ARG(6):ud		\n\
> 
> Adding argument in the middle of the list makes a lot of noise in ARG(x)
> changing. What a pity we don't have possibility of making definitions
> like:
> 
> #define x_offset ARG(1)
> #define y_offset ARG(2)
> 
> in the code. Changing definitions would keep code clear.
> 
> But that was my lousy thought, patch looks correct to me.
> Feel free to incorporate my suggestions or not:
> 
> Reviewed-by: Zbigniew Kempczyński <zbigniew.kempczynski at intel.com>

Thanks,
Christoph

> 
> --
> Zbigniew
> 
>>   #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, mask, expected);
>> +	", 2, x_offset, y_offset, 3, value, mask, expected);
>>   }
>>   
>>   /**
>> diff --git a/lib/gpgpu_shader.h b/lib/gpgpu_shader.h
>> index 53fe2869e..5f6260fb3 100644
>> --- a/lib/gpgpu_shader.h
>> +++ b/lib/gpgpu_shader.h
>> @@ -82,8 +82,8 @@ 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__write_on_exception(struct gpgpu_shader *shdr, uint32_t dw, uint32_t x_offset,
>> +				      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 fe6d68b70..91adc7313 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 aa5c79b36f48404f1da21d2316e9f9f3
>> +#define MD5_SUM_IGA64_ASMS a1dfb701367264e53d0d33f53d8769e3
>>   
>>   struct iga64_template const iga64_code_gpgpu_fill[] = {
>>   	{ .gen_ver = 2000, .size = 44, .code = (const uint32_t []) {
>> @@ -193,83 +193,88 @@ struct iga64_template const iga64_code_breakpoint_suppress[] = {
>>   };
>>   
>>   struct iga64_template const iga64_code_write_on_exception[] = {
>> -	{ .gen_ver = 2000, .size = 56, .code = (const uint32_t []) {
>> +	{ .gen_ver = 2000, .size = 60, .code = (const uint32_t []) {
>>   		0x80100061, 0x04054220, 0x00000000, 0x00000000,
>> -		0x80000061, 0x05054220, 0x00000000, 0xc0ded003,
>> -		0x80000069, 0x02058220, 0x02000014, 0xc0ded000,
>> +		0x80000061, 0x05054220, 0x00000000, 0xc0ded004,
>> +		0x80000040, 0x02058220, 0x02000014, 0xc0ded001,
>> +		0x80001969, 0x02058220, 0x02000204, 0xc0ded000,
>>   		0x80000061, 0x02150220, 0x00000064, 0x00000000,
>> -		0x80001940, 0x02158220, 0x02000214, 0xc0ded001,
>> +		0x80001940, 0x02158220, 0x02000214, 0xc0ded002,
>>   		0x80041961, 0x04550220, 0x00220205, 0x00000000,
>> -		0x80000061, 0x04754220, 0x00000000, 0xc0ded002,
>> -		0x80000965, 0x03058220, 0x02008010, 0xc0ded004,
>> +		0x80000061, 0x04754220, 0x00000000, 0xc0ded003,
>> +		0x80000965, 0x03058220, 0x02008010, 0xc0ded005,
>>   		0x80000961, 0x30014220, 0x00000000, 0x00000000,
>> -		0x80001a70, 0x00018220, 0x12000304, 0xc0ded005,
>> +		0x80001a70, 0x00018220, 0x12000304, 0xc0ded006,
>>   		0x84134031, 0x00000000, 0xd00e0494, 0x04000000,
>>   		0x80000001, 0x00010000, 0x20000000, 0x00000000,
>>   		0x80000001, 0x00010000, 0x30000000, 0x00000000,
>>   		0x80000901, 0x00010000, 0x00000000, 0x00000000,
>>   	}},
>> -	{ .gen_ver = 1270, .size = 60, .code = (const uint32_t []) {
>> +	{ .gen_ver = 1270, .size = 64, .code = (const uint32_t []) {
>>   		0x80040061, 0x04054220, 0x00000000, 0x00000000,
>> -		0x80000061, 0x05054220, 0x00000000, 0xc0ded003,
>> -		0x80000069, 0x04058220, 0x02000024, 0xc0ded000,
>> +		0x80000061, 0x05054220, 0x00000000, 0xc0ded004,
>> +		0x80000040, 0x04058220, 0x02000024, 0xc0ded001,
>> +		0x80001969, 0x04058220, 0x02000404, 0xc0ded000,
>>   		0x80000061, 0x04250220, 0x000000c4, 0x00000000,
>> -		0x80001940, 0x04258220, 0x02000424, 0xc0ded001,
>> -		0x80000061, 0x04454220, 0x00000000, 0xc0ded002,
>> +		0x80001940, 0x04258220, 0x02000424, 0xc0ded002,
>> +		0x80000061, 0x04454220, 0x00000000, 0xc0ded003,
>>   		0x80000061, 0x04850220, 0x000000a4, 0x00000000,
>> -		0x80000965, 0x03058220, 0x02008020, 0xc0ded004,
>> +		0x80000965, 0x03058220, 0x02008020, 0xc0ded005,
>>   		0x80000961, 0x30014220, 0x00000000, 0x00000000,
>> -		0x80001a70, 0x00018220, 0x12000304, 0xc0ded005,
>> +		0x80001a70, 0x00018220, 0x12000304, 0xc0ded006,
>>   		0x80001a01, 0x00010000, 0x00000000, 0x00000000,
>>   		0x81044031, 0x00000000, 0xc0000414, 0x02a00000,
>>   		0x80000001, 0x00010000, 0x20000000, 0x00000000,
>>   		0x80000001, 0x00010000, 0x30000000, 0x00000000,
>>   		0x80000901, 0x00010000, 0x00000000, 0x00000000,
>>   	}},
>> -	{ .gen_ver = 1260, .size = 56, .code = (const uint32_t []) {
>> +	{ .gen_ver = 1260, .size = 60, .code = (const uint32_t []) {
>>   		0x80100061, 0x04054220, 0x00000000, 0x00000000,
>> -		0x80000061, 0x05054220, 0x00000000, 0xc0ded003,
>> -		0x80000069, 0x04058220, 0x02000014, 0xc0ded000,
>> +		0x80000061, 0x05054220, 0x00000000, 0xc0ded004,
>> +		0x80000040, 0x04058220, 0x02000014, 0xc0ded001,
>> +		0x80001969, 0x04058220, 0x02000404, 0xc0ded000,
>>   		0x80000061, 0x04150220, 0x00000064, 0x00000000,
>> -		0x80001940, 0x04158220, 0x02000414, 0xc0ded001,
>> -		0x80000061, 0x04254220, 0x00000000, 0xc0ded002,
>> +		0x80001940, 0x04158220, 0x02000414, 0xc0ded002,
>> +		0x80000061, 0x04254220, 0x00000000, 0xc0ded003,
>>   		0x80000061, 0x04450220, 0x00000054, 0x00000000,
>> -		0x80000965, 0x03058220, 0x02008010, 0xc0ded004,
>> +		0x80000965, 0x03058220, 0x02008010, 0xc0ded005,
>>   		0x80000961, 0x30014220, 0x00000000, 0x00000000,
>> -		0x80001a70, 0x00018220, 0x12000304, 0xc0ded005,
>> +		0x80001a70, 0x00018220, 0x12000304, 0xc0ded006,
>>   		0x84134031, 0x00000000, 0xc0000414, 0x02a00000,
>>   		0x80000001, 0x00010000, 0x20000000, 0x00000000,
>>   		0x80000001, 0x00010000, 0x30000000, 0x00000000,
>>   		0x80000901, 0x00010000, 0x00000000, 0x00000000,
>>   	}},
>> -	{ .gen_ver = 1250, .size = 60, .code = (const uint32_t []) {
>> +	{ .gen_ver = 1250, .size = 64, .code = (const uint32_t []) {
>>   		0x80040061, 0x04054220, 0x00000000, 0x00000000,
>> -		0x80000061, 0x05054220, 0x00000000, 0xc0ded003,
>> -		0x80000069, 0x04058220, 0x02000024, 0xc0ded000,
>> +		0x80000061, 0x05054220, 0x00000000, 0xc0ded004,
>> +		0x80000040, 0x04058220, 0x02000024, 0xc0ded001,
>> +		0x80001969, 0x04058220, 0x02000404, 0xc0ded000,
>>   		0x80000061, 0x04250220, 0x000000c4, 0x00000000,
>> -		0x80001940, 0x04258220, 0x02000424, 0xc0ded001,
>> -		0x80000061, 0x04454220, 0x00000000, 0xc0ded002,
>> +		0x80001940, 0x04258220, 0x02000424, 0xc0ded002,
>> +		0x80000061, 0x04454220, 0x00000000, 0xc0ded003,
>>   		0x80000061, 0x04850220, 0x000000a4, 0x00000000,
>> -		0x80000965, 0x03058220, 0x02008020, 0xc0ded004,
>> +		0x80000965, 0x03058220, 0x02008020, 0xc0ded005,
>>   		0x80000961, 0x30014220, 0x00000000, 0x00000000,
>> -		0x80001a70, 0x00018220, 0x12000304, 0xc0ded005,
>> +		0x80001a70, 0x00018220, 0x12000304, 0xc0ded006,
>>   		0x80001a01, 0x00010000, 0x00000000, 0x00000000,
>>   		0x81044031, 0x00000000, 0xc0000414, 0x02a00000,
>>   		0x80000001, 0x00010000, 0x20000000, 0x00000000,
>>   		0x80000001, 0x00010000, 0x30000000, 0x00000000,
>>   		0x80000901, 0x00010000, 0x00000000, 0x00000000,
>>   	}},
>> -	{ .gen_ver = 0, .size = 56, .code = (const uint32_t []) {
>> +	{ .gen_ver = 0, .size = 60, .code = (const uint32_t []) {
>>   		0x80040061, 0x04054220, 0x00000000, 0x00000000,
>> -		0x80000061, 0x05054220, 0x00000000, 0xc0ded003,
>> -		0x80000069, 0x04058220, 0x02000024, 0xc0ded000,
>> +		0x80000061, 0x05054220, 0x00000000, 0xc0ded004,
>> +		0x80000040, 0x04058220, 0x02000024, 0xc0ded001,
>> +		0x80000169, 0x04058220, 0x02000404, 0xc0ded000,
>>   		0x80000061, 0x04250220, 0x000000c4, 0x00000000,
>> -		0x80000140, 0x04258220, 0x02000424, 0xc0ded001,
>> -		0x80000061, 0x04454220, 0x00000000, 0xc0ded002,
>> +		0x80000140, 0x04258220, 0x02000424, 0xc0ded002,
>> +		0x80000061, 0x04454220, 0x00000000, 0xc0ded003,
>>   		0x80000061, 0x04850220, 0x000000a4, 0x00000000,
>> -		0x80000165, 0x03058220, 0x02008020, 0xc0ded004,
>> +		0x80000165, 0x03058220, 0x02008020, 0xc0ded005,
>>   		0x80000161, 0x30014220, 0x00000000, 0x00000000,
>> -		0x80000270, 0x00018220, 0x12000304, 0xc0ded005,
>> +		0x80000270, 0x00018220, 0x12000304, 0xc0ded006,
>>   		0x8104a031, 0x00000000, 0xc0000414, 0x02a00000,
>>   		0x80000001, 0x00010000, 0x20000000, 0x00000000,
>>   		0x80000001, 0x00010000, 0x30000000, 0x00000000,
>> diff --git a/tests/intel/xe_exec_sip.c b/tests/intel/xe_exec_sip.c
>> index ee4787d61..ed27d9c32 100644
>> --- a/tests/intel/xe_exec_sip.c
>> +++ b/tests/intel/xe_exec_sip.c
>> @@ -93,14 +93,14 @@ static struct gpgpu_shader *get_shader(int fd, enum shader_type shader_type)
>>   	case SHADER_INV_INSTR_DISABLED:
>>   	case SHADER_INV_INSTR_WALKER_ENABLED:
>>   		bad = (shader_type == SHADER_INV_INSTR_DISABLED) ? ILLEGAL_OPCODE_ENABLE : 0;
>> -		gpgpu_shader__write_on_exception(shader, 1, 0, ILLEGAL_OPCODE_ENABLE, bad);
>> +		gpgpu_shader__write_on_exception(shader, 1, 0, 0, ILLEGAL_OPCODE_ENABLE, bad);
>>   		gpgpu_shader__nop(shader);
>>   		gpgpu_shader__nop(shader);
>>   		/* modify second nop, set only opcode bits[6:0] */
>>   		shader->instr[gpgpu_shader_last_instr(shader)][0] = 0x7f;
>>   		/* SIP should clear exception bit */
>>   		bad = ILLEGAL_OPCODE_STATUS;
>> -		gpgpu_shader__write_on_exception(shader, 2, 0, ILLEGAL_OPCODE_STATUS, bad);
>> +		gpgpu_shader__write_on_exception(shader, 2, 0, 0, ILLEGAL_OPCODE_STATUS, bad);
>>   		break;
>>   	}
>>   
>> @@ -120,7 +120,7 @@ static struct gpgpu_shader *get_sip(int fd, enum sip_type sip_type, unsigned int
>>   
>>   	switch (sip_type) {
>>   	case SIP_INV_INSTR:
>> -		gpgpu_shader__write_on_exception(sip, 1, y_offset, ILLEGAL_OPCODE_STATUS, 0);
>> +		gpgpu_shader__write_on_exception(sip, 1, 0, y_offset, ILLEGAL_OPCODE_STATUS, 0);
>>   		break;
>>   	default:
>>   		break;
>> -- 
>> 2.34.1
>>


More information about the igt-dev mailing list