[PATCH v5 3/5] lib/gpgpu_shader: add inline support for iga64 assembly

Andrzej Hajda andrzej.hajda at intel.com
Wed Jun 5 12:55:20 UTC 2024



On 29.05.2024 11:36, Kamil Konieczny wrote:
> Hi Andrzej,
> On 2024-05-28 at 16:04:49 +0200, Andrzej Hajda wrote:
>> With this patch adding iga64 assembly should be similar to
>> adding x86 assembly inline. Simple example:
>>      emit_iga64_code(shdr, set_exception, R"ASM(
>>          or (1|M0) cr0.1<1>:ud cr0.1<0;1,0>:ud ARG(0):ud
>>      )ASM", value);
>> Note presence of 'ARG(0)', it will be replaced by 'value' argument,
>> multiple arguments are possible.
>> More sophisticated examples in following patches.
>> How does it works:
>> 1. Raw string literals (C++ feature available in gcc as extension):
>>     R"ASM(...)ASM" allows to use multiline/unescaped string literals.
>>     If for some reason they cannot be used we could always fallback to
>>     old ugly way of handling multiline strings with escape characters:
>>      emit_iga64_code(shdr, set_exception, "\n\
>>          or (1|M0) cr0.1<1>:ud cr0.1<0;1,0>:ud ARG(0):ud\n\
>>      ", value);
>> 2. emit_iga64_code puts the assembly string into special linker section,
>>     and calls __emit_iga64_code with pointer to external variable
>>     which will contain code templates generated from the assembly for all
>>     supported platforms, remaining arguments are put to temporal array
>>     to eventually patch the code with positional arguments.
>> 3. During build phase the linker section is scanned for assemblies.
>>     Every assembly is preprocessed with cpp, to replace ARG(x) macros with
>>     magic numbers, and to provide different code for different platforms
>>     if needed. Then output file is compiled with iga64, and then .c file
>>     is generated with global variables pointing to hexified iga64 codes.
>>
>> v2:
>>   - fixed meson paths to script,
>>   - added check if compiler supports all platforms,
>>   - include assembly names in MD5 calculations,
>>   - use more specific name for MD5 sum
>> v3:
>>   - bump minimal meson version to kill "ERROR:  Expecting eol got id." bug
>> v4:
>>   - set minimal meson to 0.49.2 - builder uses it
>> v5:
>>   - revert back minimal version of meson, instead use old syntax a.contains(b)
>>
>> Signed-off-by: Andrzej Hajda<andrzej.hajda at intel.com>
>> ---
>>   lib/generate_iga64_codes    | 115 ++++++++++++++++++++++++++++++++++++++++++++
>>   lib/gpgpu_shader.c          |  39 +++++++++++++++
>>   lib/gpgpu_shader.h          |  25 ++++++++++
>>   lib/iga64_generated_codes.c |   6 +++
>>   lib/iga64_macros.h          |  11 +++++
>>   lib/meson.build             |  18 +++++++
>>   6 files changed, 214 insertions(+)
>>
>> diff --git a/lib/generate_iga64_codes b/lib/generate_iga64_codes
>> new file mode 100755
>> index 000000000000..4bea6c2382c9
>> --- /dev/null
>> +++ b/lib/generate_iga64_codes
> imho better place is in ../scripts
>
>> @@ -0,0 +1,115 @@
>> +#!/bin/bash
>> +# SPDX-License-Identifier: MIT
>> +# Copyright © 2024 Intel Corporation
>> +# Author: Andrzej Hajda<andrzej.hajda at intel.com>
>> +
>> +# List of supported platforms, in format gen100:platform, where gen100 equals
>> +# to minimal GPU generation supported by platform multiplied by 100 and platform
>> +# is one of platforms supported by -p switch of iga64.
>> +#
>> +# Must be in decreasing order, the last one must have gen100 equal 0"
>> +GEN_VERSIONS="2000:2 1272:12p72 1250:12p5 0:12p1"
>> +
>> +warn() {
>> +    echo -e "$1" >/dev/stderr
>> +}
>> +
>> +die() {
>> +    warn "DIE: $1"
>> +    exit 1
>> +}
>> +
>> +# parse args
>> +while getopts ':i:o:' opt; do
>> +    case $opt in
>> +    i) INPUT=$OPTARG;;
>> +    o) OUTPUT=$OPTARG;;
>> +    ?) die "Usage: $0 -i pre-generated-iga64-file -o generated-iga64-file libs-with-iga64-assembly [...]"
>> +    esac
>> +done
>> +LIBS=${@:OPTIND}
>> +
>> +# read all assemblies into ASMS array
>> +ASMS=()
>> +while  read -d $'\0' asm; do
>> +    test -z "$asm" && continue
>> +    ASMS+=( "$asm" )
>> +done < <(for f in $LIBS; do objcopy --dump-section .iga64_assembly=/dev/stdout $f.p/*.o; done)
>> +
>> +# check if we need to recompile - checksum difference and compiler present
>> +MD5_ASMS="$(md5sum <<< "${ASMS[@]}" | cut -b1-32)"
>> +MD5_PRE="$(grep -Po '(?<=^#define MD5_SUM_IGA64_ASMS )\S{32,32}' $INPUT 2>/dev/null)"
>> +
>> +if [ "$MD5_ASMS" = "$MD5_PRE" ]; then
>> +    echo "iga64 assemblies not changed, reusing pre-compiled file $INPUT."
>> +    cp $INPUT $OUTPUT
>> +    exit 0
>> +fi
>> +
>> +type iga64 >/dev/null || {
>> +    warn "WARNING: iga64 assemblies changed, but iga64 compiler not present, CHANGES will have no effect. Install iga64 (libigc-tools package) to re-compile code."
>> +    cp $INPUT $OUTPUT
>> +    exit 0
>> +}
>> +
>> +# generate code file
>> +WD=$OUTPUT.d
>> +mkdir -p $WD
>> +
>> +# check if all required platforms are supported
>> +touch $WD/empty
>> +for gen in $GEN_VERSIONS; do
>> +    gen_name="${gen#*:}"
>> +    iga64 -p=$gen_name -d $WD/empty 2>/dev/null || {
>> +        warn "WARNING: iga64 assemblies changed, but iga64 compiler does not support platform '$gen_name', CHANGES will have no effect. Update iga64 (libigc-tools package) to re-compile code."
>> +        cp $INPUT $OUTPUT
>> +        exit 0
>> +    }
>> +done
>> +
>> +# returns count of numbers in strings of format "0x1234, 0x23434, ..."
>> +dword_count() {
>> +    n=${1//[^x]}
>> +    echo ${#n}
>> +}
>> +
>> +echo "Generating new $OUTPUT"
>> +
>> +cat <<-EOF >$OUTPUT
>> +/* SPDX-License-Identifier: MIT */
>> +/* Generated using $(iga64 |& head -1) */
>> +
>> +#include "gpgpu_shader.h"
>> +
>> +#define MD5_SUM_IGA64_ASMS $MD5_ASMS
>> +EOF
>> +
>> +for asm in "${ASMS[@]}"; do
>> +    asm_name="${asm%%:*}"
>> +    asm_code="${asm_name/assembly/code}"
>> +    asm_body="${asm#*:}"
>> +    cur_code=""
>> +    cur_ver=""
>> +    echo -e "\nstruct iga64_template const $asm_code[] = {" >>$OUTPUT
>> +    for gen in $GEN_VERSIONS; do
>> +        gen_ver="${gen%%:*}"
>> +        gen_name="${gen#*:}"
>> +        warn "Generating $asm_code for platform $gen_name"
>> +        cmd="cpp -P - -o $WD/$asm_name.$gen_name.asm"
>> +        cmd+=" -DGEN_VER=$gen_ver -imacros ../lib/iga64_macros.h"
>> +        eval "$cmd" <<<"$asm_body" || die "cpp error for $asm_name.$gen_name\ncmd: $cmd"
>> +        cmd="iga64 -Xauto-deps -Wall -p=$gen_name"
>> +        cmd+=" $WD/$asm_name.$gen_name.asm -o $WD/$asm_name.$gen_name.bin"
>> +        eval "$cmd" || die "iga64 error for $asm_name.$gen_name\ncmd: $cmd"
>> +        code="$(hexdump -e '"\t\t" 4/4 "0x%08x, " "\n"' $WD/$asm_name.$gen_name.bin)"
>> +        [ -z "$cur_code" ] && cur_code="$code"
>> +        [ "$cur_code" != "$code" ] && {
>> +            echo -e "\t{ .gen_ver = $cur_ver, .size = $(dword_count "$cur_code"), .code = (const uint32_t []) {\n$cur_code\n\t}}," >>$OUTPUT
>> +            cur_code="$code"
>> +        }
>> +        cur_ver=$gen_ver
>> +    done
>> +    echo -e "\t{ .gen_ver = $cur_ver, .size = $(dword_count "$cur_code"), .code = (const uint32_t []) {\n$cur_code\n\t}}\n};" >>$OUTPUT
>> +done
>> +
>> +cp $OUTPUT $INPUT
>> diff --git a/lib/gpgpu_shader.c b/lib/gpgpu_shader.c
>> index d14301789421..3317e9e35c91 100644
>> --- a/lib/gpgpu_shader.c
>> +++ b/lib/gpgpu_shader.c
>> @@ -11,6 +11,9 @@
>>   #include "gpgpu_shader.h"
>>   #include "gpu_cmds.h"
>>   
>> +#define IGA64_ARG0 0xc0ded000
>> +#define IGA64_ARG_MASK 0xffffff00
>> +
>>   #define SUPPORTED_GEN_VER 1200 /* Support TGL and up */
>>   
>>   #define PAGE_SIZE 4096
>> @@ -22,6 +25,42 @@
>>   #define GPGPU_CURBE_SIZE 0
>>   #define GEN7_VFE_STATE_GPGPU_MODE 1
>>   
>> +static void gpgpu_shader_extend(struct gpgpu_shader *shdr)
>> +{
>> +	shdr->max_size <<= 1;
>> +	shdr->code = realloc(shdr->code, 4 * shdr->max_size);
>> +}
>> +
>> +void
>> +__emit_iga64_code(struct gpgpu_shader *shdr, struct iga64_template const *tpls,
>> +		  int argc, uint32_t *argv)
>> +{
>> +	uint32_t *ptr;
>> +
>> +	igt_require_f(shdr->gen_ver >= SUPPORTED_GEN_VER,
>> +		      "No available shader templates for platforms older than XeLP\n");
>> +
>> +	while (shdr->gen_ver < tpls->gen_ver)
>> +		tpls++;
>> +
>> +	while (shdr->max_size < shdr->size + tpls->size)
>> +		gpgpu_shader_extend(shdr);
>> +
>> +	ptr = shdr->code + shdr->size;
>> +	memcpy(ptr, tpls->code, 4 * tpls->size);
>> +
>> +	/* patch the template */
>> +	for (int n, i = 0; i < tpls->size; ++i) {
>> +		if ((ptr[i] & IGA64_ARG_MASK) != IGA64_ARG0)
>> +			continue;
>> +		n = ptr[i] - IGA64_ARG0;
>> +		igt_assert(n < argc);
>> +		ptr[i] = argv[n];
>> +	}
>> +
>> +	shdr->size += tpls->size;
>> +}
>> +
>>   static uint32_t fill_sip(struct intel_bb *ibb,
>>   			 const uint32_t sip[][4],
>>   			 const size_t size)
>> diff --git a/lib/gpgpu_shader.h b/lib/gpgpu_shader.h
>> index 02f6f1aad1e3..0b997deba8bb 100644
>> --- a/lib/gpgpu_shader.h
>> +++ b/lib/gpgpu_shader.h
>> @@ -23,6 +23,27 @@ struct gpgpu_shader {
>>   	};
>>   };
>>   
>> +struct iga64_template {
>> +	uint32_t gen_ver;
>> +	uint32_t size;
>> +	const uint32_t *code;
>> +};
>> +
>> +#pragma GCC diagnostic ignored "-Wnested-externs"
>> +
>> +void
>> +__emit_iga64_code(struct gpgpu_shader *shdr, const struct iga64_template *tpls,
>> +		  int argc, uint32_t *argv);
>> +
>> +#define emit_iga64_code(__shdr, __name, __txt, __args...) \
>> +({ \
>> +	static const char t[] __attribute__ ((section(".iga64_assembly"),used)) \
>> +		="iga64_assembly_" #__name ":" __txt "\n"; \
>> +	extern struct iga64_template const iga64_code_ ## __name[]; \
>> +	u32 args[] = { __args }; \
>> +	__emit_iga64_code(__shdr, iga64_code_ ## __name, ARRAY_SIZE(args), args); \
>> +})
>> +
>>   struct gpgpu_shader *gpgpu_shader_create(int fd);
>>   void gpgpu_shader_destroy(struct gpgpu_shader *shdr);
>>   
>> @@ -35,4 +56,8 @@ void gpgpu_shader_exec(struct intel_bb *ibb,
>>   		       struct gpgpu_shader *sip,
>>   		       uint64_t ring, bool explicit_engine);
>>   
>> +void gpgpu_shader__eot(struct gpgpu_shader *shdr);
>> +void gpgpu_shader__write_dword(struct gpgpu_shader *shdr, uint32_t value,
>> +			       uint32_t y_offset);
>> +
>>   #endif /* GPGPU_SHADER_H */
>> diff --git a/lib/iga64_generated_codes.c b/lib/iga64_generated_codes.c
>> new file mode 100644
>> index 000000000000..219436983585
>> --- /dev/null
>> +++ b/lib/iga64_generated_codes.c
>> @@ -0,0 +1,6 @@
>> +/* SPDX-License-Identifier: MIT */
>> +/* Generated using Intel Graphics Assembler 1.1.0-int */
>> +
>> +#include "gpgpu_shader.h"
>> +
>> +#define MD5_SUM_IGA64_ASMS 68b329da9893e34099c7d8ad5cb9c940
>> diff --git a/lib/iga64_macros.h b/lib/iga64_macros.h
>> new file mode 100644
>> index 000000000000..008ef795d2ce
>> --- /dev/null
>> +++ b/lib/iga64_macros.h
>> @@ -0,0 +1,11 @@
>> +/* SPDX-License-Identifier: MIT */
>> +/* Copyright © 2024 Intel Corporation */
>> +
> Add standard #ifndef/define/undef IGA64_MACROS_H
> here.

Thanks for reviewing.

This header is for inclusion in iga64 assembly, so I did not bother, but 
it should not harm.

>
>> +#define ARG(n) (0xc0ded000 + n)
> ---------- ^^^
>
> A little too short name for macro.

Regarding this macro I would prefer to keep it short as it is the basic 
macro used
in inline assembly. Like %0 in CPU assembly:

asm ("mov %1, %0\n\t"
     "add $1, %0"
     : "=r" (dst)
     : "r" (src));

iga64 example:

emit_iga64_code(shdr, sample, "                              \n\
     mov (1|M0)               r5.0<1>:ud    ARG(0):ud
", 42);


Regards
Andrzej

>
> Regards,
> Kamil
>
>> +
>> +/* send instruction for DG2+ requires 0 length in case src1 is null, BSpec: 47443 */
>> +#if GEN_VER < 1271
>> +#define src1_null null
>> +#else
>> +#define src1_null null:0
>> +#endif
>> diff --git a/lib/meson.build b/lib/meson.build
>> index 0a3084f8aea2..46594062e019 100644
>> --- a/lib/meson.build
>> +++ b/lib/meson.build
>> @@ -216,7 +216,10 @@ lib_version = vcs_tag(input : 'version.h.in', output : 'version.h',
>>   		      fallback : 'NO-GIT',
>>   		      command : vcs_command )
>>   
>> +iga64_assembly_sources = [ 'gpgpu_shader.c' ]
>> +
>>   lib_intermediates = []
>> +iga64_assembly_libs = []
>>   foreach f: lib_sources
>>       name = f.underscorify()
>>       lib = static_library('igt-' + name,
>> @@ -230,8 +233,23 @@ foreach f: lib_sources
>>   	])
>>   
>>       lib_intermediates += lib
>> +    if iga64_assembly_sources.contains(f)
>> +	iga64_assembly_libs += lib
>> +    endif
>>   endforeach
>>   
>> +generate_iga64_codes = find_program('generate_iga64_codes')
>> +iga64_generated_codes = custom_target(
>> +    'iga64_generated_codes.c',
>> +    input : [ 'iga64_generated_codes.c' ] + iga64_assembly_libs,
>> +    output : 'iga64_generated_codes.c',
>> +    command : [ generate_iga64_codes, '-o', '@OUTPUT@', '-i', '@INPUT@' ]
>> +)
>> +
>> +lib_intermediates += static_library('igt-iga64_generated_codes.c',
>> +			[ iga64_generated_codes, lib_version ]
>> +		     )
>> +
>>   lib_igt_build = shared_library('igt',
>>       ['dummy.c'],
>>       link_whole: lib_intermediates,
>>
>> -- 
>> 2.34.1
>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/igt-dev/attachments/20240605/4ab71120/attachment-0001.htm>


More information about the igt-dev mailing list