On Tue, Oct 6, 2015 at 9:09 AM, Kirill Yukhin <kirill.yuk...@gmail.com> wrote:
> Hello Uroš,
>
> I've merged two patches together and rebased it
> on top of gcc-5-branch. The only change I made compared
> to trunk version is scheduling set to CPU_NEHALEM since
> CPU_HASWELL is not supported in gcc-5.
>
> Bootstrapped.
>
> Is it ok for gcc-5-branch?
>
> gcc/
> * config.gcc: Support "skylake-avx512".
> * config/i386/i386-c.c (ix86_target_macros_internal): Handle
> PROCESSOR_SKYLAKE_AVX512.
> * config/i386/i386.c (m_SKYLAKE_AVX512): Define.
> (processor_target_table): Add "skylake-avx512".
> (PTA_SKYLAKE): Define.
> (ix86_option_override_internal): Add "skylake-avx512".
> (fold_builtin_cpu): Handle "skylake-avx512".
> * config/i386/i386.h (TARGET_SKYLAKE_AVX512): Define.
> (processor_type): Add PROCESSOR_SKYLAKE_AVX512.
> * doc/invoke.texi (skylake-avx512): New.
>
> libgcc/
> * libgcc/config/i386/cpuinfo.c (get_intel_cpu): Detect
> "skylake-avx512",
> AES, PCLMUL, AVX-512VL, AVX-512BW, AVX-512DQ, AVX-512PF,
> AVX-512ER, AVX-512CD.
>
> gcc/testsuite/
> * gcc.target/i386/builtin_target.c: Add check for "skylake-avx512",
> "aes"
> and "pclmul".
> * gcc.target/i386/funcspec-5.c: Test avx512vl, avx512bw,
> avx512dq, avx512cd, avx512er, avx512pf and skylake-avx512.
OK together with a followup testsuite patch.
Thanks,
Uros.
> --
> Thanks, K
>
> diff --git a/gcc/config.gcc b/gcc/config.gcc
> index c835734..207fc65 100644
> --- a/gcc/config.gcc
> +++ b/gcc/config.gcc
> @@ -589,8 +589,8 @@ pentium4 pentium4m pentiumpro prescott"
> x86_64_archs="amdfam10 athlon64 athlon64-sse3 barcelona bdver1 bdver2 \
> bdver3 bdver4 btver1 btver2 k8 k8-sse3 opteron opteron-sse3 nocona \
> core2 corei7 corei7-avx core-avx-i core-avx2 atom slm nehalem westmere \
> -sandybridge ivybridge haswell broadwell bonnell silvermont knl x86-64 \
> -native"
> +sandybridge ivybridge haswell broadwell bonnell silvermont knl \
> +skylake-avx512 x86-64 native"
>
> # Additional x86 processors supported by --with-cpu=. Each processor
> # MUST be separated by exactly one space.
> diff --git a/gcc/config/i386/i386-c.c b/gcc/config/i386/i386-c.c
> index f3f90df..4f20e14 100644
> --- a/gcc/config/i386/i386-c.c
> +++ b/gcc/config/i386/i386-c.c
> @@ -185,6 +185,10 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
> def_or_undef (parse_in, "__knl");
> def_or_undef (parse_in, "__knl__");
> break;
> + case PROCESSOR_SKYLAKE_AVX512:
> + def_or_undef (parse_in, "__skylake_avx512");
> + def_or_undef (parse_in, "__skylake_avx512__");
> + break;
> /* use PROCESSOR_max to not set/unset the arch macro. */
> case PROCESSOR_max:
> break;
> @@ -294,6 +298,9 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
> case PROCESSOR_KNL:
> def_or_undef (parse_in, "__tune_knl__");
> break;
> + case PROCESSOR_SKYLAKE_AVX512:
> + def_or_undef (parse_in, "__tune_skylake_avx512__");
> + break;
> case PROCESSOR_INTEL:
> case PROCESSOR_GENERIC:
> break;
> diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
> index 9b17256..43e6f91 100644
> --- a/gcc/config/i386/i386.c
> +++ b/gcc/config/i386/i386.c
> @@ -2054,6 +2054,7 @@ const struct processor_costs *ix86_cost = &pentium_cost;
> #define m_BONNELL (1<<PROCESSOR_BONNELL)
> #define m_SILVERMONT (1<<PROCESSOR_SILVERMONT)
> #define m_KNL (1<<PROCESSOR_KNL)
> +#define m_SKYLAKE_AVX512 (1<<PROCESSOT_SKYLAKE_AVX512)
> #define m_INTEL (1<<PROCESSOR_INTEL)
>
> #define m_GEODE (1<<PROCESSOR_GEODE)
> @@ -2522,6 +2523,7 @@ static const struct ptt
> processor_target_table[PROCESSOR_max] =
> {"bonnell", &atom_cost, 16, 15, 16, 7, 16},
> {"silvermont", &slm_cost, 16, 15, 16, 7, 16},
> {"knl", &slm_cost, 16, 15, 16, 7, 16},
> + {"skylake-avx512", &core_cost, 16, 10, 16, 10, 16},
> {"intel", &intel_cost, 16, 15, 16, 7, 16},
> {"geode", &geode_cost, 0, 0, 0, 0, 0},
> {"k6", &k6_cost, 32, 7, 32, 7, 32},
> @@ -3210,6 +3212,10 @@ ix86_option_override_internal (bool main_args_p,
> | PTA_FMA | PTA_MOVBE | PTA_HLE)
> #define PTA_BROADWELL \
> (PTA_HASWELL | PTA_ADX | PTA_PRFCHW | PTA_RDSEED)
> +#define PTA_SKYLAKE_AVX512 \
> + (PTA_BROADWELL | PTA_CLFLUSHOPT | PTA_XSAVEC | PTA_XSAVES \
> + | PTA_AVX512F | PTA_AVX512CD | PTA_AVX512VL \
> + | PTA_AVX512BW | PTA_AVX512DQ)
> #define PTA_KNL \
> (PTA_BROADWELL | PTA_AVX512PF | PTA_AVX512ER | PTA_AVX512F | PTA_AVX512CD)
> #define PTA_BONNELL \
> @@ -3271,6 +3277,7 @@ ix86_option_override_internal (bool main_args_p,
> {"haswell", PROCESSOR_HASWELL, CPU_NEHALEM, PTA_HASWELL},
> {"core-avx2", PROCESSOR_HASWELL, CPU_NEHALEM, PTA_HASWELL},
> {"broadwell", PROCESSOR_HASWELL, CPU_NEHALEM, PTA_BROADWELL},
> + {"skylake-avx512", PROCESSOR_SKYLAKE_AVX512, CPU_NEHALEM,
> PTA_SKYLAKE_AVX512},
> {"bonnell", PROCESSOR_BONNELL, CPU_ATOM, PTA_BONNELL},
> {"atom", PROCESSOR_BONNELL, CPU_ATOM, PTA_BONNELL},
> {"silvermont", PROCESSOR_SILVERMONT, CPU_SLM, PTA_SILVERMONT},
> @@ -35556,6 +35563,14 @@ fold_builtin_cpu (tree fndecl, tree *args)
> F_AVX512F,
> F_BMI,
> F_BMI2,
> + F_AES,
> + F_PCLMUL,
> + F_AVX512VL,
> + F_AVX512BW,
> + F_AVX512DQ,
> + F_AVX512CD,
> + F_AVX512ER,
> + F_AVX512PF,
> F_MAX
> };
>
> @@ -35589,7 +35604,9 @@ fold_builtin_cpu (tree fndecl, tree *args)
> M_AMDFAM15H_BDVER4,
> M_INTEL_COREI7_IVYBRIDGE,
> M_INTEL_COREI7_HASWELL,
> - M_INTEL_COREI7_BROADWELL
> + M_INTEL_COREI7_BROADWELL,
> + M_INTEL_COREI7_SKYLAKE,
> + M_INTEL_COREI7_SKYLAKE_AVX512
> };
>
> static struct _arch_names_table
> @@ -35611,6 +35628,8 @@ fold_builtin_cpu (tree fndecl, tree *args)
> {"ivybridge", M_INTEL_COREI7_IVYBRIDGE},
> {"haswell", M_INTEL_COREI7_HASWELL},
> {"broadwell", M_INTEL_COREI7_BROADWELL},
> + {"skylake", M_INTEL_COREI7_SKYLAKE},
> + {"skylake-avx512", M_INTEL_COREI7_SKYLAKE_AVX512},
> {"bonnell", M_INTEL_BONNELL},
> {"silvermont", M_INTEL_SILVERMONT},
> {"knl", M_INTEL_KNL},
> @@ -35634,24 +35653,32 @@ fold_builtin_cpu (tree fndecl, tree *args)
> }
> const isa_names_table[] =
> {
> - {"cmov", F_CMOV},
> - {"mmx", F_MMX},
> - {"popcnt", F_POPCNT},
> - {"sse", F_SSE},
> - {"sse2", F_SSE2},
> - {"sse3", F_SSE3},
> - {"ssse3", F_SSSE3},
> - {"sse4a", F_SSE4_A},
> - {"sse4.1", F_SSE4_1},
> - {"sse4.2", F_SSE4_2},
> - {"avx", F_AVX},
> - {"fma4", F_FMA4},
> - {"xop", F_XOP},
> - {"fma", F_FMA},
> - {"avx2", F_AVX2},
> - {"avx512f",F_AVX512F},
> - {"bmi", F_BMI},
> - {"bmi2", F_BMI2}
> + {"cmov", F_CMOV},
> + {"mmx", F_MMX},
> + {"popcnt", F_POPCNT},
> + {"sse", F_SSE},
> + {"sse2", F_SSE2},
> + {"sse3", F_SSE3},
> + {"ssse3", F_SSSE3},
> + {"sse4a", F_SSE4_A},
> + {"sse4.1", F_SSE4_1},
> + {"sse4.2", F_SSE4_2},
> + {"avx", F_AVX},
> + {"fma4", F_FMA4},
> + {"xop", F_XOP},
> + {"fma", F_FMA},
> + {"avx2", F_AVX2},
> + {"avx512f", F_AVX512F},
> + {"bmi", F_BMI},
> + {"bmi2", F_BMI2},
> + {"aes", F_AES},
> + {"pclmul", F_PCLMUL},
> + {"avx512vl",F_AVX512VL},
> + {"avx512bw",F_AVX512BW},
> + {"avx512dq",F_AVX512DQ},
> + {"avx512cd",F_AVX512CD},
> + {"avx512er",F_AVX512ER},
> + {"avx512pf",F_AVX512PF},
> };
>
> tree __processor_model_type = build_processor_model_struct ();
> diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
> index de43f06..f913348 100644
> --- a/gcc/config/i386/i386.h
> +++ b/gcc/config/i386/i386.h
> @@ -340,6 +340,7 @@ extern const struct processor_costs ix86_size_cost;
> #define TARGET_BONNELL (ix86_tune == PROCESSOR_BONNELL)
> #define TARGET_SILVERMONT (ix86_tune == PROCESSOR_SILVERMONT)
> #define TARGET_KNL (ix86_tune == PROCESSOR_KNL)
> +#define TARGET_SKYLAKE_AVX512 (ix86_tune == PROCESSOR_SKYLAKE_AVX512)
> #define TARGET_INTEL (ix86_tune == PROCESSOR_INTEL)
> #define TARGET_GENERIC (ix86_tune == PROCESSOR_GENERIC)
> #define TARGET_AMDFAM10 (ix86_tune == PROCESSOR_AMDFAM10)
> @@ -2278,6 +2279,7 @@ enum processor_type
> PROCESSOR_BONNELL,
> PROCESSOR_SILVERMONT,
> PROCESSOR_KNL,
> + PROCESSOR_SKYLAKE_AVX512,
> PROCESSOR_INTEL,
> PROCESSOR_GEODE,
> PROCESSOR_K6,
> diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
> index d3be589..99a9027 100644
> --- a/gcc/doc/invoke.texi
> +++ b/gcc/doc/invoke.texi
> @@ -22060,6 +22060,12 @@ SSSE3, SSE4.1, SSE4.2, POPCNT, AVX, AVX2, AES,
> PCLMUL, FSGSBASE, RDRND, FMA,
> BMI, BMI2, F16C, RDSEED, ADCX, PREFETCHW, AVX512F, AVX512PF, AVX512ER and
> AVX512CD instruction set support.
>
> +@item skylake-avx512
> +Intel Skylake Server CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3,
> +SSSE3, SSE4.1, SSE4.2, POPCNT, AVX, AVX2, AES, PCLMUL, FSGSBASE, RDRND, FMA,
> +BMI, BMI2, F16C, RDSEED, ADCX, PREFETCHW, CLFLUSHOPT, XSAVEC, XSAVES,
> AVX512F,
> +AVX512VL, AVX512BW, AVX512DQ and AVX512CD instruction set support.
> +
> @item k6
> AMD K6 CPU with MMX instruction set support.
>
> diff --git a/gcc/testsuite/gcc.target/i386/builtin_target.c
> b/gcc/testsuite/gcc.target/i386/builtin_target.c
> index 10c0568..591d1c7 100644
> --- a/gcc/testsuite/gcc.target/i386/builtin_target.c
> +++ b/gcc/testsuite/gcc.target/i386/builtin_target.c
> @@ -80,6 +80,11 @@ check_intel_cpu_model (unsigned int family, unsigned int
> model,
> assert (__builtin_cpu_is ("corei7"));
> assert (__builtin_cpu_is ("broadwell"));
> break;
> + case 0x55:
> + /* Skylake with AVX-512 support. */
> + assert (__builtin_cpu_is ("corei7"));
> + assert (__builtin_cpu_is ("skylake-avx512"));
> + break;
> case 0x17:
> case 0x1d:
> /* Penryn. */
> @@ -177,6 +182,18 @@ check_features (unsigned int ecx, unsigned int edx,
> assert (__builtin_cpu_supports ("avx2"));
> if (ebx & bit_AVX512F)
> assert (__builtin_cpu_supports ("avx512f"));
> + if (ebx & bit_AVX512VL)
> + assert (__builtin_cpu_supports ("avx512vl"));
> + if (ebx & bit_AVX512CD)
> + assert (__builtin_cpu_supports ("avx512cd"));
> + if (ebx & bit_AVX512PF)
> + assert (__builtin_cpu_supports ("avx512pf"));
> + if (ebx & bit_AVX512ER)
> + assert (__builtin_cpu_supports ("avx512er"));
> + if (ebx & bit_AVX512BW)
> + assert (__builtin_cpu_supports ("avx512bw"));
> + if (ebx & bit_AVX512DQ)
> + assert (__builtin_cpu_supports ("avx512dq"));
> }
> }
>
> diff --git a/gcc/testsuite/gcc.target/i386/funcspec-5.c
> b/gcc/testsuite/gcc.target/i386/funcspec-5.c
> index 7185b5c..c43bc76 100644
> --- a/gcc/testsuite/gcc.target/i386/funcspec-5.c
> +++ b/gcc/testsuite/gcc.target/i386/funcspec-5.c
> @@ -25,6 +25,12 @@ extern void test_tbm (void)
> __attribute__((__target__("tbm")));
> extern void test_avx (void)
> __attribute__((__target__("avx")));
> extern void test_avx2 (void)
> __attribute__((__target__("avx2")));
> extern void test_avx512f (void)
> __attribute__((__target__("avx512f")));
> +extern void test_avx512vl(void)
> __attribute__((__target__("avx512vl")));
> +extern void test_avx512bw(void)
> __attribute__((__target__("avx512bw")));
> +extern void test_avx512dq(void)
> __attribute__((__target__("avx512dq")));
> +extern void test_avx512er(void)
> __attribute__((__target__("avx512er")));
> +extern void test_avx512pf(void)
> __attribute__((__target__("avx512pf")));
> +extern void test_avx512cd(void)
> __attribute__((__target__("avx512cd")));
> extern void test_bmi (void)
> __attribute__((__target__("bmi")));
> extern void test_bmi2 (void)
> __attribute__((__target__("bmi2")));
>
> @@ -50,6 +56,12 @@ extern void test_no_tbm (void)
> __attribute__((__target__("no-tbm")));
> extern void test_no_avx (void)
> __attribute__((__target__("no-avx")));
> extern void test_no_avx2 (void)
> __attribute__((__target__("no-avx2")));
> extern void test_no_avx512f (void)
> __attribute__((__target__("no-avx512f")));
> +extern void test_no_avx512vl(void)
> __attribute__((__target__("no-avx512vl")));
> +extern void test_no_avx512bw(void)
> __attribute__((__target__("no-avx512bw")));
> +extern void test_no_avx512dq(void)
> __attribute__((__target__("no-avx512dq")));
> +extern void test_no_avx512er(void)
> __attribute__((__target__("no-avx512er")));
> +extern void test_bo_avx512pf(void)
> __attribute__((__target__("no-avx512pf")));
> +extern void test_no_avx512cd(void)
> __attribute__((__target__("no-avx512cd")));
> extern void test_no_bmi (void)
> __attribute__((__target__("no-bmi")));
> extern void test_no_bmi2 (void)
> __attribute__((__target__("no-bmi2")));
>
> @@ -77,6 +89,7 @@ extern void test_arch_corei7 (void)
> __attribute__((__target__("arch=corei7")));
> extern void test_arch_corei7_avx (void)
> __attribute__((__target__("arch=corei7-avx")));
> extern void test_arch_core_avx2 (void)
> __attribute__((__target__("arch=core-avx2")));
> extern void test_arch_knl (void)
> __attribute__((__target__("arch=knl")));
> +extern void test_arch_skylake_avx512 (void)
> __attribute__((__target__("arch=skylake-avx512")));
> extern void test_arch_geode (void)
> __attribute__((__target__("arch=geode")));
> extern void test_arch_k6 (void)
> __attribute__((__target__("arch=k6")));
> extern void test_arch_k6_2 (void)
> __attribute__((__target__("arch=k6-2")));
> diff --git a/libgcc/config/i386/cpuinfo.c b/libgcc/config/i386/cpuinfo.c
> index eaf2f10..3abf04f 100644
> --- a/libgcc/config/i386/cpuinfo.c
> +++ b/libgcc/config/i386/cpuinfo.c
> @@ -36,7 +36,7 @@ see the files COPYING3 and COPYING.RUNTIME respectively.
> If not, see
> int __cpu_indicator_init (void)
> __attribute__ ((constructor CONSTRUCTOR_PRIORITY));
>
> -/* Processor Vendor and Models. */
> +/* Processor Vendor and Models. */
>
> enum processor_vendor
> {
> @@ -46,7 +46,7 @@ enum processor_vendor
> VENDOR_MAX
> };
>
> -/* Any new types or subtypes have to be inserted at the end. */
> +/* Any new types or subtypes have to be inserted at the end. */
>
> enum processor_types
> {
> @@ -76,10 +76,11 @@ enum processor_subtypes
> INTEL_COREI7_IVYBRIDGE,
> INTEL_COREI7_HASWELL,
> INTEL_COREI7_BROADWELL,
> + INTEL_COREI7_SKYLAKE_AVX512,
> CPU_SUBTYPE_MAX
> };
>
> -/* ISA Features supported. */
> +/* ISA Features supported. New features have to be inserted at the end. */
>
> enum processor_features
> {
> @@ -100,7 +101,15 @@ enum processor_features
> FEATURE_FMA,
> FEATURE_AVX512F,
> FEATURE_BMI,
> - FEATURE_BMI2
> + FEATURE_BMI2,
> + FEATURE_AES,
> + FEATURE_PCLMUL,
> + FEATURE_AVX512VL,
> + FEATURE_AVX512BW,
> + FEATURE_AVX512DQ,
> + FEATURE_AVX512CD,
> + FEATURE_AVX512ER,
> + FEATURE_AVX512PF
> };
>
> struct __processor_model
> @@ -171,7 +180,7 @@ get_amd_cpu (unsigned int family, unsigned int model)
> static void
> get_intel_cpu (unsigned int family, unsigned int model, unsigned int
> brand_id)
> {
> - /* Parse family and model only if brand ID is 0. */
> + /* Parse family and model only if brand ID is 0. */
> if (brand_id == 0)
> {
> switch (family)
> @@ -237,6 +246,11 @@ get_intel_cpu (unsigned int family, unsigned int model,
> unsigned int brand_id)
> __cpu_model.__cpu_type = INTEL_COREI7;
> __cpu_model.__cpu_subtype = INTEL_COREI7_BROADWELL;
> break;
> + case 0x55:
> + /* Skylake with AVX-512 support. */
> + __cpu_model.__cpu_type = INTEL_COREI7;
> + __cpu_model.__cpu_subtype = INTEL_COREI7_SKYLAKE_AVX512;
> + break;
> case 0x17:
> case 0x1d:
> /* Penryn. */
> @@ -273,6 +287,10 @@ get_available_features (unsigned int ecx, unsigned int
> edx,
> features |= (1 << FEATURE_SSE2);
> if (ecx & bit_POPCNT)
> features |= (1 << FEATURE_POPCNT);
> + if (ecx & bit_AES)
> + features |= (1 << FEATURE_AES);
> + if (ecx & bit_PCLMUL)
> + features |= (1 << FEATURE_PCLMUL);
> if (ecx & bit_SSE3)
> features |= (1 << FEATURE_SSE3);
> if (ecx & bit_SSSE3)
> @@ -299,6 +317,18 @@ get_available_features (unsigned int ecx, unsigned int
> edx,
> features |= (1 << FEATURE_BMI2);
> if (ebx & bit_AVX512F)
> features |= (1 << FEATURE_AVX512F);
> + if (ebx & bit_AVX512VL)
> + features |= (1 << FEATURE_AVX512VL);
> + if (ebx & bit_AVX512BW)
> + features |= (1 << FEATURE_AVX512BW);
> + if (ebx & bit_AVX512DQ)
> + features |= (1 << FEATURE_AVX512DQ);
> + if (ebx & bit_AVX512CD)
> + features |= (1 << FEATURE_AVX512CD);
> + if (ebx & bit_AVX512PF)
> + features |= (1 << FEATURE_AVX512PF);
> + if (ebx & bit_AVX512ER)
> + features |= (1 << FEATURE_AVX512ER);
> }
>
> unsigned int ext_level;
