[PATCH 2/2] lib/gpgpu_shader: simplify load/store shaders
Zbigniew Kempczyński
zbigniew.kempczynski at intel.com
Thu Nov 14 11:28:46 UTC 2024
On Thu, Nov 14, 2024 at 11:31:39AM +0100, Andrzej Hajda wrote:
> There is lot of redundancy in shaders code regarding load/store messages.
> It makes the code barely readable. Simplify it by using macros in iga64
> assembler.
> Every load/store operation is split into two phases:
> 1. Load address/descriptor (from) where data should be stored/loaded.
> 2. Issue load/store instruction.
> Shader threads needs two types of memory access:
> 3. Private area per thread.
> 4. Area shared per all threads.
> Different platforms access surface in different ways:
> 5. Using media block messages.
> 6. Using untyped 2d block messages.
> 7. Future platforms will use different messages.
>
> All this is simplified to two macros per message in shader:
> load_(shared|thread)_space_addr(dst,y,width)
> (load|store)_space_dw(dst, src)
>
> Signed-off-by: Andrzej Hajda <andrzej.hajda at intel.com>
> ---
> lib/gpgpu_shader.c | 160 +++------------------
> lib/iga64_generated_codes.c | 338 ++++++++++++++++++++++----------------------
> lib/iga64_macros.h | 43 ++++++
> 3 files changed, 230 insertions(+), 311 deletions(-)
>
> diff --git a/lib/gpgpu_shader.c b/lib/gpgpu_shader.c
> index 4e1b8d5e9009..7728f96bf305 100644
> --- a/lib/gpgpu_shader.c
> +++ b/lib/gpgpu_shader.c
> @@ -431,22 +431,8 @@ void gpgpu_shader__jump_neq(struct gpgpu_shader *shdr, int label_id,
>
> size = emit_iga64_code(shdr, jump_dw_neq, " \n\
> L0: \n\
> -(W) mov (16|M0) r30.0<1>:ud 0x0:ud \n\
> -#if GEN_VER < 2000 // Media Block Write \n\
This comment seems is incorrect,
> - // Y offset of the block in rows := thread group id Y \n\
> -(W) mov (1|M0) r30.1<1>:ud ARG(0):ud \n\
> - // block width [0,63] representing 1 to 64 bytes, we want dword \n\
> -(W) mov (1|M0) r30.2<1>:ud 0x3:ud \n\
> - // FFTID := FFTID from R0 header \n\
> -(W) mov (1|M0) r30.4<1>:ud r0.5<0;1,0>:ud \n\
> -(W) send.dc1 (16|M0) r31 r30 null 0x0 0x2190000 \n\
> -#else // Typed 2D Block Store \n\
this as well...
> - // Store X and Y block start (160:191 and 192:223) \n\
> -(W) mov (1|M0) r30.6<1>:ud ARG(0):ud \n\
> - // Store X and Y block size (224:231 and 232:239) \n\
> -(W) mov (1|M0) r30.7<1>:ud 0x3:ud \n\
> -(W) send.tgm (16|M0) r31 r30 null:0 0x0 0x62100003 \n\
> -#endif \n\
> + load_shared_space_addr(r30, ARG(0):ud, 4) \n\
Shouldn't above be named set_shared_space_addr()? Load is ambiguous for
me in this context.
> +(W) load_space_dw(r31, r30) \n\
Ok, we're loading dw, not store (wrong comment was removed, great).
> // clear the flag register \n\
> (W) mov (1|M0) f0.0<1>:ud 0x0:ud \n\
> (W) cmp (1|M0) (ne)f0.0 null<1>:ud r31.0<0;1,0>:ud ARG(1):ud \n\
> @@ -511,28 +497,13 @@ void gpgpu_shader__common_target_write(struct gpgpu_shader *shdr,
> uint32_t y_offset, const uint32_t value[4])
> {
> emit_iga64_code(shdr, common_target_write, " \n\
> -(W) mov (16|M0) r30.0<1>:ud 0x0:ud \n\
> (W) mov (16|M0) r31.0<1>:ud 0x0:ud \n\
> (W) mov (1|M0) r31.0<1>:ud ARG(1):ud \n\
> (W) mov (1|M0) r31.1<1>:ud ARG(2):ud \n\
> (W) mov (1|M0) r31.2<1>:ud ARG(3):ud \n\
> (W) mov (1|M0) r31.3<1>:ud ARG(4):ud \n\
> -#if GEN_VER < 2000 // Media Block Write \n\
> - // Y offset of the block in rows \n\
> -(W) mov (1|M0) r30.1<1>:ud ARG(0):ud \n\
> - // block width [0,63] representing 1 to 64 bytes \n\
> -(W) mov (1|M0) r30.2<1>:ud 0xf:ud \n\
> - // FFTID := FFTID from R0 header \n\
> -(W) mov (1|M0) r30.4<1>:ud r0.5<0;1,0>:ud \n\
> - // written value \n\
> -(W) send.dc1 (16|M0) null r30 src1_null 0x0 0x40A8000 \n\
> -#else // Typed 2D Block Store \n\
> - // Store X and Y block start (160:191 and 192:223) \n\
> -(W) mov (1|M0) r30.6<1>:ud ARG(0):ud \n\
> - // Store X and Y block size (224:231 and 232:239) \n\
> -(W) mov (1|M0) r30.7<1>:ud 0xf:ud \n\
> -(W) send.tgm (16|M0) null r30 null:0 0x0 0x64000007 \n\
> -#endif \n\
> + load_shared_space_addr(r30, ARG(0):ud, 16) \n\
> +(W) store_space_dw(r30, r31) \n\
> ", y_offset, value[0], value[1], value[2], value[3]);
> }
>
> @@ -565,31 +536,8 @@ void gpgpu_shader__write_aip(struct gpgpu_shader *shdr, uint32_t y_offset)
> emit_iga64_code(shdr, media_block_write_aip, " \n\
> // Payload \n\
> (W) mov (1|M0) r5.0<1>:ud cr0.2:ud \n\
> -#if GEN_VER < 2000 // 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 0x2: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(0):ud \n\
> - // block width [0,63] representing 1 to 64 bytes \n\
> -(W) mov (1|M0) r4.2<1>:ud 0x3:ud \n\
> - // FFTID := FFTID from R0 header \n\
> -(W) mov (1|M0) r4.4<1>:ud r0.5<0;1,0>:ud \n\
> -(W) send.dc1 (16|M0) null r4 src1_null 0 0x40A8000 \n\
> -#else // 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 0x2: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(0):ud \n\
> - // payload setup \n\
> -(W) mov (16|M0) r4.0<1>:ud 0x0: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 0x3:ud \n\
> -(W) send.tgm (16|M0) null r4 null:0 0 0x64000007 \n\
> -#endif \n\
> + load_thread_space_addr(r4, 0, ARG(0):ud, 4) \n\
> +(W) store_space_dw(r4, r5) \n\
> ", y_offset);
> }
>
> @@ -618,38 +566,11 @@ void gpgpu_shader__increase_aip(struct gpgpu_shader *shdr, uint32_t value)
> void gpgpu_shader__write_dword(struct gpgpu_shader *shdr, uint32_t value,
> uint32_t y_offset)
> {
> - emit_iga64_code(shdr, media_block_write, " \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\
> -#if GEN_VER < 2000 // 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\
> -(W) send.dc1 (16|M0) null r4 src1_null 0 0x40A8000 \n\
> -#else // 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\
> -(W) send.tgm (16|M0) null r4 null:0 0 0x64000007 \n\
> -#endif \n\
> - ", 2, y_offset, 3, value, value, value, value);
> + emit_iga64_code(shdr, media_block_write, " \n\
> +(W) mov (1) r5.0<1>:ud ARG(1):ud \n\
> + load_thread_space_addr(r4, 0, ARG(0):ud, 4) \n\
> +(W) store_space_dw(r4, r5) \n\
> + ", y_offset, value);
> }
>
> /**
> @@ -697,41 +618,14 @@ 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(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) 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) add (1|M0) r4.1<1>:ud r0.6<0;1,0>:ud ARG(2):ud \n\
> - // block width [0,63] representing 1 to 64 bytes \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 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) add (1|M0) r2.1<1>:ud r0.6<0;1,0>:ud ARG(2):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(3):ud \n\
> -#endif \n\
> +(W) mov (1|M0) r5.0<1>:ud ARG(2):ud \n\
> + load_thread_space_addr(r4, ARG(0), ARG(1):ud, 4) \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(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(6):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, x_offset, y_offset, 3, value, mask, expected);
> +(W) and (1|M0) r3.0<1>:ud cr0.1<0;1,0>:ud ARG(3):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(4):ud \n\
> +(W&f0.0) store_space_dw(r4, r5) \n\
> + ", 4 * x_offset, y_offset, value, mask, expected);
> }
>
> /**
> @@ -778,22 +672,8 @@ void gpgpu_shader__end_system_routine_step_if_eq(struct gpgpu_shader *shdr,
> emit_iga64_code(shdr, end_system_routine_step_if_eq, " \n\
> (W) or (1|M0) cr0.0<1>:ud cr0.0<0;1,0>:ud 0x8000:ud \n\
> (W) and (1|M0) cr0.1<1>:ud cr0.1<0;1,0>:ud ARG(0):ud \n\
> -(W) mov (16|M0) r30.0<1>:ud 0x0:ud \n\
> -#if GEN_VER < 2000 // Media Block Write \n\
> - // Y offset of the block in rows := thread group id Y \n\
> -(W) mov (1|M0) r30.1<1>:ud ARG(1):ud \n\
> - // block width [0,63] representing 1 to 64 bytes, we want dword \n\
> -(W) mov (1|M0) r30.2<1>:ud 0x3:ud \n\
> - // FFTID := FFTID from R0 header \n\
> -(W) mov (1|M0) r30.4<1>:ud r0.5<0;1,0>:ud \n\
> -(W) send.dc1 (16|M0) r31 r30 null 0x0 0x2190000 \n\
> -#else // Typed 2D Block Store \n\
> - // Store X and Y block start (160:191 and 192:223) \n\
> -(W) mov (1|M0) r30.6<1>:ud ARG(1):ud \n\
> - // Store X and Y block size (224:231 and 232:239) \n\
> -(W) mov (1|M0) r30.7<1>:ud 0x3:ud \n\
> -(W) send.tgm (16|M0) r31 r30 null:0 0x0 0x62100003 \n\
> -#endif \n\
> + load_thread_space_addr(r30, 0, ARG(0):ud, 4) \n\
Shouldn't this be load_shared_space_addr()?
--
Zbigniew
> +(W) load_space_dw(r31, r30) \n\
> // clear the flag register \n\
> (W) mov (1|M0) f0.0<1>:ud 0x0:ud \n\
> (W) cmp (1|M0) (ne)f0.0 null<1>:ud r31.0<0;1,0>:ud ARG(2):ud \n\
> diff --git a/lib/iga64_generated_codes.c b/lib/iga64_generated_codes.c
> index 0bd92b8c4dc9..017adefce400 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 e2d97ef45d5f322200793a0aa76872d7
> +#define MD5_SUM_IGA64_ASMS fa1b0aa75c3ee1cd13300ad1324737b4
>
> struct iga64_template const iga64_code_gpgpu_fill[] = {
> { .gen_ver = 2000, .size = 44, .code = (const uint32_t []) {
> @@ -80,71 +80,81 @@ struct iga64_template const iga64_code_gpgpu_fill[] = {
> };
>
> struct iga64_template const iga64_code_end_system_routine_step_if_eq[] = {
> - { .gen_ver = 2000, .size = 44, .code = (const uint32_t []) {
> + { .gen_ver = 2000, .size = 52, .code = (const uint32_t []) {
> 0x80000966, 0x80018220, 0x02008000, 0x00008000,
> 0x80000965, 0x80118220, 0x02008010, 0xc0ded000,
> - 0x80100961, 0x1e054220, 0x00000000, 0x00000000,
> - 0x80000061, 0x1e654220, 0x00000000, 0xc0ded001,
> + 0x800c0961, 0x1e054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x1e558220, 0x02000014, 0x00000002,
> + 0x80001940, 0x1e558220, 0x02001e54, 0x00000000,
> + 0x80000040, 0x1e658220, 0x02000064, 0xc0ded000,
> 0x80000061, 0x1e754220, 0x00000000, 0x00000003,
> - 0x80132031, 0x1f0c0000, 0xd0061e8c, 0x04000000,
> + 0x80032031, 0x1f0c0000, 0xd0061e8c, 0x04000000,
> 0x80000061, 0x30014220, 0x00000000, 0x00000000,
> 0x80008070, 0x00018220, 0x22001f04, 0xc0ded002,
> 0x84000965, 0x80118220, 0x02008010, 0xc0ded003,
> 0x80000965, 0x80018220, 0x02008000, 0x7ffffffd,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> - { .gen_ver = 1270, .size = 52, .code = (const uint32_t []) {
> + { .gen_ver = 1270, .size = 60, .code = (const uint32_t []) {
> 0x80000966, 0x80018220, 0x02008000, 0x00008000,
> 0x80000965, 0x80218220, 0x02008020, 0xc0ded000,
> - 0x80040961, 0x1e054220, 0x00000000, 0x00000000,
> - 0x80000061, 0x1e254220, 0x00000000, 0xc0ded001,
> + 0x80030961, 0x1e054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x1e058220, 0x02000024, 0x00000002,
> + 0x80001940, 0x1e058220, 0x02001e04, 0x00000000,
> + 0x80000040, 0x1e258220, 0x020000c4, 0xc0ded000,
> 0x80000061, 0x1e454220, 0x00000000, 0x00000003,
> 0x80000061, 0x1e850220, 0x000000a4, 0x00000000,
> 0x80001901, 0x00010000, 0x00000000, 0x00000000,
> - 0x80044031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> + 0x80004031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> 0x80000061, 0x30014220, 0x00000000, 0x00000000,
> 0x80002070, 0x00018220, 0x22001f04, 0xc0ded002,
> 0x81000965, 0x80218220, 0x02008020, 0xc0ded003,
> 0x80000965, 0x80018220, 0x02008000, 0x7ffffffd,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> - { .gen_ver = 1260, .size = 48, .code = (const uint32_t []) {
> + { .gen_ver = 1260, .size = 56, .code = (const uint32_t []) {
> 0x80000966, 0x80018220, 0x02008000, 0x00008000,
> 0x80000965, 0x80118220, 0x02008010, 0xc0ded000,
> - 0x80100961, 0x1e054220, 0x00000000, 0x00000000,
> - 0x80000061, 0x1e154220, 0x00000000, 0xc0ded001,
> + 0x800c0961, 0x1e054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x1e058220, 0x02000014, 0x00000002,
> + 0x80001940, 0x1e058220, 0x02001e04, 0x00000000,
> + 0x80000040, 0x1e158220, 0x02000064, 0xc0ded000,
> 0x80000061, 0x1e254220, 0x00000000, 0x00000003,
> 0x80000061, 0x1e450220, 0x00000054, 0x00000000,
> - 0x80132031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> + 0x80032031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> 0x80000061, 0x30014220, 0x00000000, 0x00000000,
> 0x80008070, 0x00018220, 0x22001f04, 0xc0ded002,
> 0x84000965, 0x80118220, 0x02008010, 0xc0ded003,
> 0x80000965, 0x80018220, 0x02008000, 0x7ffffffd,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> - { .gen_ver = 1250, .size = 52, .code = (const uint32_t []) {
> + { .gen_ver = 1250, .size = 60, .code = (const uint32_t []) {
> 0x80000966, 0x80018220, 0x02008000, 0x00008000,
> 0x80000965, 0x80218220, 0x02008020, 0xc0ded000,
> - 0x80040961, 0x1e054220, 0x00000000, 0x00000000,
> - 0x80000061, 0x1e254220, 0x00000000, 0xc0ded001,
> + 0x80030961, 0x1e054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x1e058220, 0x02000024, 0x00000002,
> + 0x80001940, 0x1e058220, 0x02001e04, 0x00000000,
> + 0x80000040, 0x1e258220, 0x020000c4, 0xc0ded000,
> 0x80000061, 0x1e454220, 0x00000000, 0x00000003,
> 0x80000061, 0x1e850220, 0x000000a4, 0x00000000,
> 0x80001901, 0x00010000, 0x00000000, 0x00000000,
> - 0x80044031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> + 0x80004031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> 0x80000061, 0x30014220, 0x00000000, 0x00000000,
> 0x80002070, 0x00018220, 0x22001f04, 0xc0ded002,
> 0x81000965, 0x80218220, 0x02008020, 0xc0ded003,
> 0x80000965, 0x80018220, 0x02008000, 0x7ffffffd,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> - { .gen_ver = 0, .size = 48, .code = (const uint32_t []) {
> + { .gen_ver = 0, .size = 56, .code = (const uint32_t []) {
> 0x80000166, 0x80018220, 0x02008000, 0x00008000,
> 0x80000165, 0x80218220, 0x02008020, 0xc0ded000,
> - 0x80040161, 0x1e054220, 0x00000000, 0x00000000,
> - 0x80000061, 0x1e254220, 0x00000000, 0xc0ded001,
> + 0x80030161, 0x1e054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x1e058220, 0x02000024, 0x00000002,
> + 0x80000140, 0x1e058220, 0x02001e04, 0x00000000,
> + 0x80000040, 0x1e258220, 0x020000c4, 0xc0ded000,
> 0x80000061, 0x1e454220, 0x00000000, 0x00000003,
> 0x80000061, 0x1e850220, 0x000000a4, 0x00000000,
> - 0x80049031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> + 0x80009031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> 0x80000061, 0x30014220, 0x00000000, 0x00000000,
> 0x80002070, 0x00018220, 0x22001f04, 0xc0ded002,
> 0x81000165, 0x80218220, 0x02008020, 0xc0ded003,
> @@ -193,84 +203,83 @@ 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 []) {
> - 0x80100061, 0x04054220, 0x00000000, 0x00000000,
> - 0x80000061, 0x05054220, 0x00000000, 0xc0ded004,
> - 0x80000040, 0x02058220, 0x02000014, 0xc0ded001,
> - 0x80001969, 0x02058220, 0x02000204, 0xc0ded000,
> - 0x80000040, 0x02158220, 0x02000064, 0xc0ded002,
> - 0x80041961, 0x04550220, 0x00220205, 0x00000000,
> - 0x80000061, 0x04754220, 0x00000000, 0xc0ded003,
> - 0x80000965, 0x03058220, 0x02008010, 0xc0ded005,
> + { .gen_ver = 2000, .size = 52, .code = (const uint32_t []) {
> + 0x80000061, 0x05054220, 0x00000000, 0xc0ded002,
> + 0x800c0061, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04558220, 0x02000014, 0x00000002,
> + 0x80001940, 0x04558220, 0x02000454, 0xc0ded000,
> + 0x80000040, 0x04658220, 0x02000064, 0xc0ded001,
> + 0x80000061, 0x04754220, 0x00000000, 0x00000003,
> + 0x80000965, 0x03058220, 0x02008010, 0xc0ded003,
> 0x80000961, 0x30014220, 0x00000000, 0x00000000,
> - 0x80001a70, 0x00018220, 0x12000304, 0xc0ded006,
> - 0x84132031, 0x00000000, 0xd00e0494, 0x04000000,
> + 0x80001a70, 0x00018220, 0x12000304, 0xc0ded004,
> + 0x84032031, 0x00000000, 0xd00e0494, 0x04000000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> { .gen_ver = 1270, .size = 60, .code = (const uint32_t []) {
> - 0x80040061, 0x04054220, 0x00000000, 0x00000000,
> - 0x80000061, 0x05054220, 0x00000000, 0xc0ded004,
> - 0x80000040, 0x04058220, 0x02000024, 0xc0ded001,
> - 0x80001969, 0x04058220, 0x02000404, 0xc0ded000,
> - 0x80000040, 0x04258220, 0x020000c4, 0xc0ded002,
> - 0x80000061, 0x04454220, 0x00000000, 0xc0ded003,
> + 0x80000061, 0x05054220, 0x00000000, 0xc0ded002,
> + 0x80030061, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04058220, 0x02000024, 0x00000002,
> + 0x80001940, 0x04058220, 0x02000404, 0xc0ded000,
> + 0x80000040, 0x04258220, 0x020000c4, 0xc0ded001,
> + 0x80000061, 0x04454220, 0x00000000, 0x00000003,
> 0x80000061, 0x04850220, 0x000000a4, 0x00000000,
> - 0x80000965, 0x03058220, 0x02008020, 0xc0ded005,
> + 0x80000965, 0x03058220, 0x02008020, 0xc0ded003,
> 0x80000961, 0x30014220, 0x00000000, 0x00000000,
> - 0x80001a70, 0x00018220, 0x12000304, 0xc0ded006,
> + 0x80001a70, 0x00018220, 0x12000304, 0xc0ded004,
> 0x80001901, 0x00010000, 0x00000000, 0x00000000,
> - 0x81044031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x81004031, 0x00000000, 0xc0000414, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> { .gen_ver = 1260, .size = 56, .code = (const uint32_t []) {
> - 0x80100061, 0x04054220, 0x00000000, 0x00000000,
> - 0x80000061, 0x05054220, 0x00000000, 0xc0ded004,
> - 0x80000040, 0x04058220, 0x02000014, 0xc0ded001,
> - 0x80001969, 0x04058220, 0x02000404, 0xc0ded000,
> - 0x80000040, 0x04158220, 0x02000064, 0xc0ded002,
> - 0x80000061, 0x04254220, 0x00000000, 0xc0ded003,
> + 0x80000061, 0x05054220, 0x00000000, 0xc0ded002,
> + 0x800c0061, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04058220, 0x02000014, 0x00000002,
> + 0x80001940, 0x04058220, 0x02000404, 0xc0ded000,
> + 0x80000040, 0x04158220, 0x02000064, 0xc0ded001,
> + 0x80000061, 0x04254220, 0x00000000, 0x00000003,
> 0x80000061, 0x04450220, 0x00000054, 0x00000000,
> - 0x80000965, 0x03058220, 0x02008010, 0xc0ded005,
> + 0x80000965, 0x03058220, 0x02008010, 0xc0ded003,
> 0x80000961, 0x30014220, 0x00000000, 0x00000000,
> - 0x80001a70, 0x00018220, 0x12000304, 0xc0ded006,
> - 0x84132031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x80001a70, 0x00018220, 0x12000304, 0xc0ded004,
> + 0x84032031, 0x00000000, 0xc0000414, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> { .gen_ver = 1250, .size = 60, .code = (const uint32_t []) {
> - 0x80040061, 0x04054220, 0x00000000, 0x00000000,
> - 0x80000061, 0x05054220, 0x00000000, 0xc0ded004,
> - 0x80000040, 0x04058220, 0x02000024, 0xc0ded001,
> - 0x80001969, 0x04058220, 0x02000404, 0xc0ded000,
> - 0x80000040, 0x04258220, 0x020000c4, 0xc0ded002,
> - 0x80000061, 0x04454220, 0x00000000, 0xc0ded003,
> + 0x80000061, 0x05054220, 0x00000000, 0xc0ded002,
> + 0x80030061, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04058220, 0x02000024, 0x00000002,
> + 0x80001940, 0x04058220, 0x02000404, 0xc0ded000,
> + 0x80000040, 0x04258220, 0x020000c4, 0xc0ded001,
> + 0x80000061, 0x04454220, 0x00000000, 0x00000003,
> 0x80000061, 0x04850220, 0x000000a4, 0x00000000,
> - 0x80000965, 0x03058220, 0x02008020, 0xc0ded005,
> + 0x80000965, 0x03058220, 0x02008020, 0xc0ded003,
> 0x80000961, 0x30014220, 0x00000000, 0x00000000,
> - 0x80001a70, 0x00018220, 0x12000304, 0xc0ded006,
> + 0x80001a70, 0x00018220, 0x12000304, 0xc0ded004,
> 0x80001901, 0x00010000, 0x00000000, 0x00000000,
> - 0x81044031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x81004031, 0x00000000, 0xc0000414, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> { .gen_ver = 0, .size = 56, .code = (const uint32_t []) {
> - 0x80040061, 0x04054220, 0x00000000, 0x00000000,
> - 0x80000061, 0x05054220, 0x00000000, 0xc0ded004,
> - 0x80000040, 0x04058220, 0x02000024, 0xc0ded001,
> - 0x80000169, 0x04058220, 0x02000404, 0xc0ded000,
> - 0x80000040, 0x04258220, 0x020000c4, 0xc0ded002,
> - 0x80000061, 0x04454220, 0x00000000, 0xc0ded003,
> + 0x80000061, 0x05054220, 0x00000000, 0xc0ded002,
> + 0x80030061, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04058220, 0x02000024, 0x00000002,
> + 0x80000140, 0x04058220, 0x02000404, 0xc0ded000,
> + 0x80000040, 0x04258220, 0x020000c4, 0xc0ded001,
> + 0x80000061, 0x04454220, 0x00000000, 0x00000003,
> 0x80000061, 0x04850220, 0x000000a4, 0x00000000,
> - 0x80000165, 0x03058220, 0x02008020, 0xc0ded005,
> + 0x80000165, 0x03058220, 0x02008020, 0xc0ded003,
> 0x80000161, 0x30014220, 0x00000000, 0x00000000,
> - 0x80000270, 0x00018220, 0x12000304, 0xc0ded006,
> - 0x81049031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x80000270, 0x00018220, 0x12000304, 0xc0ded004,
> + 0x81009031, 0x00000000, 0xc0000414, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000101, 0x00010000, 0x00000000, 0x00000000,
> @@ -324,84 +333,68 @@ struct iga64_template const iga64_code_clear_exception[] = {
> };
>
> struct iga64_template const iga64_code_media_block_write[] = {
> - { .gen_ver = 2000, .size = 56, .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,
> - 0x80132031, 0x00000000, 0xd00e0494, 0x04000000,
> + { .gen_ver = 2000, .size = 40, .code = (const uint32_t []) {
> + 0x80000061, 0x05054220, 0x00000000, 0xc0ded001,
> + 0x800c0061, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04558220, 0x02000014, 0x00000002,
> + 0x80001940, 0x04558220, 0x02000454, 0x00000000,
> + 0x80000040, 0x04658220, 0x02000064, 0xc0ded000,
> + 0x80000061, 0x04754220, 0x00000000, 0x00000003,
> + 0x80032031, 0x00000000, 0xd00e0494, 0x04000000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> - { .gen_ver = 1270, .size = 60, .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,
> + { .gen_ver = 1270, .size = 48, .code = (const uint32_t []) {
> + 0x80000061, 0x05054220, 0x00000000, 0xc0ded001,
> + 0x80030061, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04058220, 0x02000024, 0x00000002,
> + 0x80001940, 0x04058220, 0x02000404, 0x00000000,
> + 0x80000040, 0x04258220, 0x020000c4, 0xc0ded000,
> + 0x80000061, 0x04454220, 0x00000000, 0x00000003,
> 0x80000061, 0x04850220, 0x000000a4, 0x00000000,
> 0x80001901, 0x00010000, 0x00000000, 0x00000000,
> - 0x80044031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x80004031, 0x00000000, 0xc0000414, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> - { .gen_ver = 1260, .size = 56, .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,
> + { .gen_ver = 1260, .size = 44, .code = (const uint32_t []) {
> + 0x80000061, 0x05054220, 0x00000000, 0xc0ded001,
> + 0x800c0061, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04058220, 0x02000014, 0x00000002,
> + 0x80001940, 0x04058220, 0x02000404, 0x00000000,
> + 0x80000040, 0x04158220, 0x02000064, 0xc0ded000,
> + 0x80000061, 0x04254220, 0x00000000, 0x00000003,
> 0x80000061, 0x04450220, 0x00000054, 0x00000000,
> - 0x80132031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x80032031, 0x00000000, 0xc0000414, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> - { .gen_ver = 1250, .size = 60, .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,
> + { .gen_ver = 1250, .size = 48, .code = (const uint32_t []) {
> + 0x80000061, 0x05054220, 0x00000000, 0xc0ded001,
> + 0x80030061, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04058220, 0x02000024, 0x00000002,
> + 0x80001940, 0x04058220, 0x02000404, 0x00000000,
> + 0x80000040, 0x04258220, 0x020000c4, 0xc0ded000,
> + 0x80000061, 0x04454220, 0x00000000, 0x00000003,
> 0x80000061, 0x04850220, 0x000000a4, 0x00000000,
> 0x80001901, 0x00010000, 0x00000000, 0x00000000,
> - 0x80044031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x80004031, 0x00000000, 0xc0000414, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> - { .gen_ver = 0, .size = 56, .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,
> + { .gen_ver = 0, .size = 44, .code = (const uint32_t []) {
> + 0x80000061, 0x05054220, 0x00000000, 0xc0ded001,
> + 0x80030061, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04058220, 0x02000024, 0x00000002,
> + 0x80000140, 0x04058220, 0x02000404, 0x00000000,
> + 0x80000040, 0x04258220, 0x020000c4, 0xc0ded000,
> + 0x80000061, 0x04454220, 0x00000000, 0x00000003,
> 0x80000061, 0x04850220, 0x000000a4, 0x00000000,
> - 0x80049031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x80009031, 0x00000000, 0xc0000414, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000101, 0x00010000, 0x00000000, 0x00000000,
> @@ -432,65 +425,68 @@ struct iga64_template const iga64_code_write_aip[] = {
> };
>
> struct iga64_template const iga64_code_media_block_write_aip[] = {
> - { .gen_ver = 2000, .size = 44, .code = (const uint32_t []) {
> + { .gen_ver = 2000, .size = 40, .code = (const uint32_t []) {
> 0x80000961, 0x05050220, 0x00008020, 0x00000000,
> - 0x80000969, 0x02058220, 0x02000014, 0x00000002,
> - 0x80000061, 0x02150220, 0x00000064, 0x00000000,
> - 0x80001940, 0x02158220, 0x02000214, 0xc0ded000,
> - 0x80100061, 0x04054220, 0x00000000, 0x00000000,
> - 0x80041a61, 0x04550220, 0x00220205, 0x00000000,
> + 0x800c0961, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04558220, 0x02000014, 0x00000002,
> + 0x80001940, 0x04558220, 0x02000454, 0x00000000,
> + 0x80000040, 0x04658220, 0x02000064, 0xc0ded000,
> 0x80000061, 0x04754220, 0x00000000, 0x00000003,
> - 0x80132031, 0x00000000, 0xd00e0494, 0x04000000,
> + 0x80032031, 0x00000000, 0xd00e0494, 0x04000000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> - { .gen_ver = 1270, .size = 44, .code = (const uint32_t []) {
> + { .gen_ver = 1270, .size = 48, .code = (const uint32_t []) {
> 0x80000961, 0x05050220, 0x00008040, 0x00000000,
> - 0x80000969, 0x04058220, 0x02000024, 0x00000002,
> - 0x80000061, 0x04250220, 0x000000c4, 0x00000000,
> - 0x80001940, 0x04258220, 0x02000424, 0xc0ded000,
> + 0x80030961, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04058220, 0x02000024, 0x00000002,
> + 0x80001940, 0x04058220, 0x02000404, 0x00000000,
> + 0x80000040, 0x04258220, 0x020000c4, 0xc0ded000,
> 0x80000061, 0x04454220, 0x00000000, 0x00000003,
> 0x80000061, 0x04850220, 0x000000a4, 0x00000000,
> 0x80001901, 0x00010000, 0x00000000, 0x00000000,
> - 0x80044031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x80004031, 0x00000000, 0xc0000414, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> - { .gen_ver = 1260, .size = 40, .code = (const uint32_t []) {
> + { .gen_ver = 1260, .size = 44, .code = (const uint32_t []) {
> 0x80000961, 0x05050220, 0x00008020, 0x00000000,
> - 0x80000969, 0x04058220, 0x02000014, 0x00000002,
> - 0x80000061, 0x04150220, 0x00000064, 0x00000000,
> - 0x80001940, 0x04158220, 0x02000414, 0xc0ded000,
> + 0x800c0961, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04058220, 0x02000014, 0x00000002,
> + 0x80001940, 0x04058220, 0x02000404, 0x00000000,
> + 0x80000040, 0x04158220, 0x02000064, 0xc0ded000,
> 0x80000061, 0x04254220, 0x00000000, 0x00000003,
> 0x80000061, 0x04450220, 0x00000054, 0x00000000,
> - 0x80132031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x80032031, 0x00000000, 0xc0000414, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> - { .gen_ver = 1250, .size = 44, .code = (const uint32_t []) {
> + { .gen_ver = 1250, .size = 48, .code = (const uint32_t []) {
> 0x80000961, 0x05050220, 0x00008040, 0x00000000,
> - 0x80000969, 0x04058220, 0x02000024, 0x00000002,
> - 0x80000061, 0x04250220, 0x000000c4, 0x00000000,
> - 0x80001940, 0x04258220, 0x02000424, 0xc0ded000,
> + 0x80030961, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04058220, 0x02000024, 0x00000002,
> + 0x80001940, 0x04058220, 0x02000404, 0x00000000,
> + 0x80000040, 0x04258220, 0x020000c4, 0xc0ded000,
> 0x80000061, 0x04454220, 0x00000000, 0x00000003,
> 0x80000061, 0x04850220, 0x000000a4, 0x00000000,
> 0x80001901, 0x00010000, 0x00000000, 0x00000000,
> - 0x80044031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x80004031, 0x00000000, 0xc0000414, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> - { .gen_ver = 0, .size = 40, .code = (const uint32_t []) {
> + { .gen_ver = 0, .size = 44, .code = (const uint32_t []) {
> 0x80000161, 0x05050220, 0x00008040, 0x00000000,
> - 0x80000169, 0x04058220, 0x02000024, 0x00000002,
> - 0x80000061, 0x04250220, 0x000000c4, 0x00000000,
> - 0x80000140, 0x04258220, 0x02000424, 0xc0ded000,
> + 0x80030161, 0x04054220, 0x00000000, 0x00000000,
> + 0x80000069, 0x04058220, 0x02000024, 0x00000002,
> + 0x80000140, 0x04058220, 0x02000404, 0x00000000,
> + 0x80000040, 0x04258220, 0x020000c4, 0xc0ded000,
> 0x80000061, 0x04454220, 0x00000000, 0x00000003,
> 0x80000061, 0x04850220, 0x000000a4, 0x00000000,
> - 0x80049031, 0x00000000, 0xc0000414, 0x02a00000,
> + 0x80009031, 0x00000000, 0xc0000414, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000101, 0x00010000, 0x00000000, 0x00000000,
> @@ -499,77 +495,77 @@ struct iga64_template const iga64_code_media_block_write_aip[] = {
>
> struct iga64_template const iga64_code_common_target_write[] = {
> { .gen_ver = 2000, .size = 48, .code = (const uint32_t []) {
> - 0x80100061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80100061, 0x1f054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1f054220, 0x00000000, 0xc0ded001,
> 0x80000061, 0x1f154220, 0x00000000, 0xc0ded002,
> 0x80000061, 0x1f254220, 0x00000000, 0xc0ded003,
> 0x80000061, 0x1f354220, 0x00000000, 0xc0ded004,
> + 0x800c0061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1e654220, 0x00000000, 0xc0ded000,
> 0x80000061, 0x1e754220, 0x00000000, 0x0000000f,
> - 0x80132031, 0x00000000, 0xd00e1e94, 0x04000000,
> + 0x80032031, 0x00000000, 0xd00e1e94, 0x04000000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> { .gen_ver = 1270, .size = 56, .code = (const uint32_t []) {
> - 0x80040061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80040061, 0x1f054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1f054220, 0x00000000, 0xc0ded001,
> 0x80000061, 0x1f254220, 0x00000000, 0xc0ded002,
> 0x80000061, 0x1f454220, 0x00000000, 0xc0ded003,
> 0x80000061, 0x1f654220, 0x00000000, 0xc0ded004,
> + 0x80030061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1e254220, 0x00000000, 0xc0ded000,
> 0x80000061, 0x1e454220, 0x00000000, 0x0000000f,
> 0x80000061, 0x1e850220, 0x000000a4, 0x00000000,
> 0x80001901, 0x00010000, 0x00000000, 0x00000000,
> - 0x80044031, 0x00000000, 0xc0001e14, 0x02a00000,
> + 0x80004031, 0x00000000, 0xc0001e14, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> { .gen_ver = 1260, .size = 52, .code = (const uint32_t []) {
> - 0x80100061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80100061, 0x1f054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1f054220, 0x00000000, 0xc0ded001,
> 0x80000061, 0x1f154220, 0x00000000, 0xc0ded002,
> 0x80000061, 0x1f254220, 0x00000000, 0xc0ded003,
> 0x80000061, 0x1f354220, 0x00000000, 0xc0ded004,
> + 0x800c0061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1e154220, 0x00000000, 0xc0ded000,
> 0x80000061, 0x1e254220, 0x00000000, 0x0000000f,
> 0x80000061, 0x1e450220, 0x00000054, 0x00000000,
> - 0x80132031, 0x00000000, 0xc0001e14, 0x02a00000,
> + 0x80032031, 0x00000000, 0xc0001e14, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> { .gen_ver = 1250, .size = 56, .code = (const uint32_t []) {
> - 0x80040061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80040061, 0x1f054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1f054220, 0x00000000, 0xc0ded001,
> 0x80000061, 0x1f254220, 0x00000000, 0xc0ded002,
> 0x80000061, 0x1f454220, 0x00000000, 0xc0ded003,
> 0x80000061, 0x1f654220, 0x00000000, 0xc0ded004,
> + 0x80030061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1e254220, 0x00000000, 0xc0ded000,
> 0x80000061, 0x1e454220, 0x00000000, 0x0000000f,
> 0x80000061, 0x1e850220, 0x000000a4, 0x00000000,
> 0x80001901, 0x00010000, 0x00000000, 0x00000000,
> - 0x80044031, 0x00000000, 0xc0001e14, 0x02a00000,
> + 0x80004031, 0x00000000, 0xc0001e14, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> { .gen_ver = 0, .size = 52, .code = (const uint32_t []) {
> - 0x80040061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80040061, 0x1f054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1f054220, 0x00000000, 0xc0ded001,
> 0x80000061, 0x1f254220, 0x00000000, 0xc0ded002,
> 0x80000061, 0x1f454220, 0x00000000, 0xc0ded003,
> 0x80000061, 0x1f654220, 0x00000000, 0xc0ded004,
> + 0x80030061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1e254220, 0x00000000, 0xc0ded000,
> 0x80000061, 0x1e454220, 0x00000000, 0x0000000f,
> 0x80000061, 0x1e850220, 0x000000a4, 0x00000000,
> - 0x80049031, 0x00000000, 0xc0001e14, 0x02a00000,
> + 0x80009031, 0x00000000, 0xc0001e14, 0x02a00000,
> 0x80000001, 0x00010000, 0x20000000, 0x00000000,
> 0x80000001, 0x00010000, 0x30000000, 0x00000000,
> 0x80000101, 0x00010000, 0x00000000, 0x00000000,
> @@ -627,56 +623,56 @@ struct iga64_template const iga64_code_clear_r40[] = {
>
> struct iga64_template const iga64_code_jump_dw_neq[] = {
> { .gen_ver = 2000, .size = 32, .code = (const uint32_t []) {
> - 0x80100061, 0x1e054220, 0x00000000, 0x00000000,
> + 0x800c0061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1e654220, 0x00000000, 0xc0ded000,
> 0x80000061, 0x1e754220, 0x00000000, 0x00000003,
> - 0x80132031, 0x1f0c0000, 0xd0061e8c, 0x04000000,
> + 0x80032031, 0x1f0c0000, 0xd0061e8c, 0x04000000,
> 0x80000061, 0x30014220, 0x00000000, 0x00000000,
> 0x80008070, 0x00018220, 0x22001f04, 0xc0ded001,
> 0x84000020, 0x00004000, 0x00000000, 0xffffffa0,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> { .gen_ver = 1270, .size = 40, .code = (const uint32_t []) {
> - 0x80040061, 0x1e054220, 0x00000000, 0x00000000,
> + 0x80030061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1e254220, 0x00000000, 0xc0ded000,
> 0x80000061, 0x1e454220, 0x00000000, 0x00000003,
> 0x80000061, 0x1e850220, 0x000000a4, 0x00000000,
> 0x80001901, 0x00010000, 0x00000000, 0x00000000,
> - 0x80044031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> + 0x80004031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> 0x80000061, 0x30014220, 0x00000000, 0x00000000,
> 0x80002070, 0x00018220, 0x22001f04, 0xc0ded001,
> 0x81000020, 0x00004000, 0x00000000, 0xffffff80,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> { .gen_ver = 1260, .size = 36, .code = (const uint32_t []) {
> - 0x80100061, 0x1e054220, 0x00000000, 0x00000000,
> + 0x800c0061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1e154220, 0x00000000, 0xc0ded000,
> 0x80000061, 0x1e254220, 0x00000000, 0x00000003,
> 0x80000061, 0x1e450220, 0x00000054, 0x00000000,
> - 0x80132031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> + 0x80032031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> 0x80000061, 0x30014220, 0x00000000, 0x00000000,
> 0x80008070, 0x00018220, 0x22001f04, 0xc0ded001,
> 0x84000020, 0x00004000, 0x00000000, 0xffffff90,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> { .gen_ver = 1250, .size = 40, .code = (const uint32_t []) {
> - 0x80040061, 0x1e054220, 0x00000000, 0x00000000,
> + 0x80030061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1e254220, 0x00000000, 0xc0ded000,
> 0x80000061, 0x1e454220, 0x00000000, 0x00000003,
> 0x80000061, 0x1e850220, 0x000000a4, 0x00000000,
> 0x80001901, 0x00010000, 0x00000000, 0x00000000,
> - 0x80044031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> + 0x80004031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> 0x80000061, 0x30014220, 0x00000000, 0x00000000,
> 0x80002070, 0x00018220, 0x22001f04, 0xc0ded001,
> 0x81000020, 0x00004000, 0x00000000, 0xffffff80,
> 0x80000901, 0x00010000, 0x00000000, 0x00000000,
> }},
> { .gen_ver = 0, .size = 36, .code = (const uint32_t []) {
> - 0x80040061, 0x1e054220, 0x00000000, 0x00000000,
> + 0x80030061, 0x1e054220, 0x00000000, 0x00000000,
> 0x80000061, 0x1e254220, 0x00000000, 0xc0ded000,
> 0x80000061, 0x1e454220, 0x00000000, 0x00000003,
> 0x80000061, 0x1e850220, 0x000000a4, 0x00000000,
> - 0x80049031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> + 0x80009031, 0x1f0c0000, 0xc0001e0c, 0x02400000,
> 0x80000061, 0x30014220, 0x00000000, 0x00000000,
> 0x80002070, 0x00018220, 0x22001f04, 0xc0ded001,
> 0x81000120, 0x00004000, 0x00000000, 0xffffff90,
> diff --git a/lib/iga64_macros.h b/lib/iga64_macros.h
> index 03cc726d48c2..0fd5e268d957 100644
> --- a/lib/iga64_macros.h
> +++ b/lib/iga64_macros.h
> @@ -13,4 +13,47 @@
> #define src1_null null:0
> #endif
>
> +/* GPGPU_R0Payload fields, Bspec: 55396, 56587 */
> +#define r0_tgidx r0.1<0;1,0>:ud
> +#define r0_tgidy r0.6<0;1,0>:ud
> +#define r0_fftid r0.5<0;1,0>:ud
> +
> +#define load_shared_media_block_msg_hdr(dst, y, width) \
> +(W) mov (8) dst.0<1>:ud 0x0:ud ;\
> +(W) mov (1) dst.1<1>:ud y ;\
> +(W) mov (1) dst.2<1>:ud (width - 1):ud ;\
> +(W) mov (1) dst.4<1>:ud r0_fftid
> +
> +#define load_thread_media_block_msg_hdr(dst, x, y, width) \
> +(W) mov (8) dst.0<1>:ud 0x0:ud ;\
> +(W) shl (1) dst.0<1>:ud r0_tgidx 0x2:ud ;\
> +(W) add (1) dst.0<1>:ud dst.0<0;1,0>:ud x:ud ;\
> +(W) add (1) dst.1<1>:ud r0_tgidy y ;\
> +(W) mov (1) dst.2<1>:ud (width - 1):ud ;\
> +(W) mov (1) dst.4<1>:ud r0_fftid
> +
> +#define load_shared_a2dblock_payload(dst, y, width) \
> +(W) mov (8) dst.0<1>:ud 0x0:ud ;\
> +(W) mov (1) dst.6<1>:ud y ;\
> +(W) mov (1) dst.7<1>:ud (width - 1):ud
> +
> +#define load_thread_a2dblock_payload(dst, x, y, width) \
> +(W) mov (8) dst.0<1>:ud 0x0:ud ;\
> +(W) shl (1) dst.5<1>:ud r0_tgidx 0x2:ud ;\
> +(W) add (1) dst.5<1>:ud dst.5<0;1,0>:ud x:ud ;\
> +(W) add (1) dst.6<1>:ud r0_tgidy y ;\
> +(W) mov (1) dst.7<1>:ud (width - 1):ud ;\
> +
> +#if GEN_VER < 2000
> +#define load_shared_space_addr(dst, y, width) load_shared_media_block_msg_hdr(dst, y, width)
> +#define load_thread_space_addr(dst, x, y, width) load_thread_media_block_msg_hdr(dst, x, y, width)
> +#define load_space_dw(dst, src) send.dc1 (1) dst src src1_null 0x0 0x2190000
> +#define store_space_dw(dst, src) send.dc1 (1) null dst null 0x0 0x40A8000
> +#else
> +#define load_shared_space_addr(dst, y, width) load_shared_a2dblock_payload(dst, y, width)
> +#define load_thread_space_addr(dst, x, y, width) load_thread_a2dblock_payload(dst, x, y, width)
> +#define load_space_dw(dst, src) send.tgm (1) dst src null:0 0x0 0x62100003
> +#define store_space_dw(dst, src) send.tgm (1) null dst null:0 0x0 0x64000007
> +#endif
> +
> #endif
>
> --
> 2.34.1
>
More information about the igt-dev
mailing list