commit 18371383f2c6c866ec10dbf7e7e48aaa61a11e3e Author: Kirill Yukhin Date: Tue Jun 21 14:43:32 2011 +0400 AVX2 supported in driver. diff --git a/gcc/ChangeLog.avx2 b/gcc/ChangeLog.avx2 index 9c01fb6..1ee229e 100644 --- a/gcc/ChangeLog.avx2 +++ b/gcc/ChangeLog.avx2 @@ -1,3 +1,9 @@ +2011-06-21 Yukhin Kirill + + * gcc/config/i386/driver-i386.c (host_detect_local_cpu): Define + and set has_avx2. + * gcc/doc/invoke.texi: Document -mavx2 and -mno-avx2. + 2011-06-20 Yukhin Kirill * gcc/config/i386/i386.c (ix86_expand_args_builtin): Improved diff --git a/gcc/config/i386/driver-i386.c b/gcc/config/i386/driver-i386.c index efd4372..2bacba9 100644 --- a/gcc/config/i386/driver-i386.c +++ b/gcc/config/i386/driver-i386.c @@ -393,7 +393,7 @@ const char *host_detect_local_cpu (int argc, const char **argv) unsigned int has_lahf_lm = 0, has_sse4a = 0; unsigned int has_longmode = 0, has_3dnowp = 0, has_3dnow = 0; unsigned int has_movbe = 0, has_sse4_1 = 0, has_sse4_2 = 0; - unsigned int has_popcnt = 0, has_aes = 0, has_avx = 0; + unsigned int has_popcnt = 0, has_aes = 0, has_avx = 0, has_avx2 = 0; unsigned int has_pclmul = 0, has_abm = 0, has_lwp = 0; unsigned int has_fma = 0, has_fma4 = 0, has_xop = 0; unsigned int has_bmi = 0, has_tbm = 0; @@ -473,6 +473,7 @@ const char *host_detect_local_cpu (int argc, const char **argv) __cpuid (0x7, eax, ebx, ecx, edx); has_bmi = ebx & bit_BMI; + has_avx2 = ebx & bit_AVX2; } if (!arch) @@ -710,12 +711,13 @@ const char *host_detect_local_cpu (int argc, const char **argv) const char *bmi = has_bmi ? " -mbmi" : " -mno-bmi"; const char *tbm = has_tbm ? " -mtbm" : " -mno-tbm"; const char *avx = has_avx ? " -mavx" : " -mno-avx"; + const char *avx2 = has_avx2 ? " -mavx2" : " -mno-avx2"; const char *sse4_2 = has_sse4_2 ? " -msse4.2" : " -mno-sse4.2"; const char *sse4_1 = has_sse4_1 ? " -msse4.1" : " -mno-sse4.1"; options = concat (options, cx16, sahf, movbe, ase, pclmul, popcnt, abm, lwp, fma, fma4, xop, bmi, tbm, - avx, sse4_2, sse4_1, NULL); + avx2, avx, sse4_2, sse4_1, NULL); } done: diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi index e747f1d..ee1f2ab 100644 --- a/gcc/doc/invoke.texi +++ b/gcc/doc/invoke.texi @@ -600,7 +600,7 @@ Objective-C and Objective-C++ Dialects}. -mincoming-stack-boundary=@var{num} @gol -mcld -mcx16 -msahf -mmovbe -mcrc32 -mrecip -mvzeroupper @gol -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4 -mavx @gol --maes -mpclmul -mfsgsbase -mrdrnd -mf16c -mfused-madd @gol +-mavx2 -maes -mpclmul -mfsgsbase -mrdrnd -mf16c -mfused-madd @gol -msse4a -m3dnow -mpopcnt -mabm -mbmi -mtbm -mfma4 -mxop -mlwp @gol -mthreads -mno-align-stringops -minline-all-stringops @gol -minline-stringops-dynamically -mstringop-strategy=@var{alg} @gol @@ -12560,6 +12560,8 @@ preferred alignment to @option{-mpreferred-stack-boundary=2}. @itemx -mno-sse4 @itemx -mavx @itemx -mno-avx +@itemx -mavx2 +@itemx -mno-avx2 @itemx -maes @itemx -mno-aes @itemx -mpclmul @@ -12597,7 +12599,7 @@ preferred alignment to @option{-mpreferred-stack-boundary=2}. @opindex m3dnow @opindex mno-3dnow These switches enable or disable the use of instructions in the MMX, -SSE, SSE2, SSE3, SSSE3, SSE4.1, AVX, AES, PCLMUL, FSGSBASE, RDRND, +SSE, SSE2, SSE3, SSSE3, SSE4.1, AVX, AVX2, AES, PCLMUL, FSGSBASE, RDRND, F16C, SSE4A, FMA4, XOP, LWP, ABM, BMI, or 3DNow!@: extended instruction sets. These extensions are also available as built-in functions: see @ref{X86 Built-in Functions}, for details of the functions enabled and diff --git a/gcc/testsuite/ChangeLog.avx2 b/gcc/testsuite/ChangeLog.avx2 index a211b3f..0be13ce 100644 --- a/gcc/testsuite/ChangeLog.avx2 +++ b/gcc/testsuite/ChangeLog.avx2 @@ -1,5 +1,11 @@ 2011-06-20 Yukhin Kirill + * gcc.target/i386/funcspec-5.c: Add avx2 and no-avx2 targets. + * gcc.target/i386/funcspec-6.c: Likewise. + * gcc.target/i386/sse-12.c: Likewise. + +2011-06-10 Yukhin Kirill + * gcc.target/i386/avx2-mpsadbw-3.c: New test to check error diagnostic while passing wrong immediate. * gcc.target/i386/avx2-vextracti128-3.c: Likewise. diff --git a/gcc/testsuite/gcc.target/i386/funcspec-5.c b/gcc/testsuite/gcc.target/i386/funcspec-5.c index 1e18dcf..b7febab 100644 --- a/gcc/testsuite/gcc.target/i386/funcspec-5.c +++ b/gcc/testsuite/gcc.target/i386/funcspec-5.c @@ -20,6 +20,8 @@ extern void test_sse4a (void) __attribute__((__target__("sse4a"))); extern void test_fma4 (void) __attribute__((__target__("fma4"))); extern void test_ssse3 (void) __attribute__((__target__("ssse3"))); 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_no_abm (void) __attribute__((__target__("no-abm"))); extern void test_no_aes (void) __attribute__((__target__("no-aes"))); @@ -38,6 +40,8 @@ extern void test_no_sse4a (void) __attribute__((__target__("no-sse4a"))); extern void test_no_fma4 (void) __attribute__((__target__("no-fma4"))); extern void test_no_ssse3 (void) __attribute__((__target__("no-ssse3"))); 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_arch_i386 (void) __attribute__((__target__("arch=i386"))); extern void test_arch_i486 (void) __attribute__((__target__("arch=i486"))); diff --git a/gcc/testsuite/gcc.target/i386/funcspec-6.c b/gcc/testsuite/gcc.target/i386/funcspec-6.c index 92a3cb5..709be29 100644 --- a/gcc/testsuite/gcc.target/i386/funcspec-6.c +++ b/gcc/testsuite/gcc.target/i386/funcspec-6.c @@ -20,6 +20,8 @@ extern void test_sse4a (void) __attribute__((__target__("sse4a"))); extern void test_fma4 (void) __attribute__((__target__("fma4"))); extern void test_ssse3 (void) __attribute__((__target__("ssse3"))); 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_no_abm (void) __attribute__((__target__("no-abm"))); extern void test_no_aes (void) __attribute__((__target__("no-aes"))); @@ -38,6 +40,8 @@ extern void test_no_sse4a (void) __attribute__((__target__("no-sse4a"))); extern void test_no_fma4 (void) __attribute__((__target__("no-fma4"))); extern void test_no_ssse3 (void) __attribute__((__target__("no-ssse3"))); 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_arch_nocona (void) __attribute__((__target__("arch=nocona"))); extern void test_arch_core2 (void) __attribute__((__target__("arch=core2"))); diff --git a/gcc/testsuite/gcc.target/i386/sse-12.c b/gcc/testsuite/gcc.target/i386/sse-12.c index 4f8aaec..c12aa36 100644 --- a/gcc/testsuite/gcc.target/i386/sse-12.c +++ b/gcc/testsuite/gcc.target/i386/sse-12.c @@ -3,7 +3,7 @@ popcntintrin.h and mm_malloc.h are usable with -O -std=c89 -pedantic-errors. */ /* { dg-do compile } */ -/* { dg-options "-O -std=c89 -pedantic-errors -march=k8 -msse4a -m3dnow -mavx -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mbmi -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c" } */ +/* { dg-options "-O -std=c89 -pedantic-errors -march=k8 -msse4a -m3dnow -mavx -mavx2 -mfma4 -mxop -maes -mpclmul -mpopcnt -mabm -mbmi -mtbm -mlwp -mfsgsbase -mrdrnd -mf16c" } */ #include