Commit e32bfc16 by Venkataramanan Kumar Committed by Venkataramanan Kumar

AMD btver2 enablement

From-SVN: r189838
parent 92345349
2012-7-25 Venkataramanan Kumar <venkataramanan.kumar@amd.com>
btver2 Enablement
* config.gcc (i[34567]86-*-linux* | ...): Add btver2.
(case ${target}): Add btver2.
* config/i386/driver-i386.c (host_detect_local_cpu): Let
-march=native recognize btver2 processors.
* config/i386/i386-c.c (ix86_target_macros_internal): Add
btver2 def_and_undef
* config/i386/i386.c (struct processor_costs btver2_cost): New
btver2 cost table.
(m_BTVER2): New definition.
(m_AMD_MULTIPLE): Includes m_BTVER2.
(initial_ix86_tune_features): Add btver2 tune.
(processor_target_table): Add btver2 entry.
(static const char *const cpu_names): Add btver2 entry.
(software_prefetching_beneficial_p): Add btver2.
(ix86_option_override_internal): Add btver2 instruction sets.
(ix86_issue_rate): Add btver2.
(ix86_adjust_cost): Add btver2.
* config/i386/i386.h (TARGET_BTVER2): New definition.
(enum target_cpu_default): Add TARGET_CPU_DEFAULT_btver2.
(enum processor_type): Add PROCESSOR_BTVER2.
* config/i386/i386.md (define_attr "cpu"): Add btver2.
2012-07-24 Bill Schmidt <wschmidt@linux.ibm.com>
* doc/tm.texi: Regenerate.
......
......@@ -1214,7 +1214,7 @@ i[34567]86-*-linux* | i[34567]86-*-kfreebsd*-gnu | i[34567]86-*-knetbsd*-gnu | i
TM_MULTILIB_CONFIG=`echo $TM_MULTILIB_CONFIG | sed 's/^,//'`
need_64bit_isa=yes
case X"${with_cpu}" in
Xgeneric|Xatom|Xcore2|Xcorei7|Xcorei7-avx|Xnocona|Xx86-64|Xbdver2|Xbdver1|Xbtver1|Xamdfam10|Xbarcelona|Xk8|Xopteron|Xathlon64|Xathlon-fx|Xathlon64-sse3|Xk8-sse3|Xopteron-sse3)
Xgeneric|Xatom|Xcore2|Xcorei7|Xcorei7-avx|Xnocona|Xx86-64|Xbdver2|Xbdver1|Xbtver2|Xbtver1|Xamdfam10|Xbarcelona|Xk8|Xopteron|Xathlon64|Xathlon-fx|Xathlon64-sse3|Xk8-sse3|Xopteron-sse3)
;;
X)
if test x$with_cpu_64 = x; then
......@@ -1223,7 +1223,7 @@ i[34567]86-*-linux* | i[34567]86-*-kfreebsd*-gnu | i[34567]86-*-knetbsd*-gnu | i
;;
*)
echo "Unsupported CPU used in --with-cpu=$with_cpu, supported values:" 1>&2
echo "generic atom core2 corei7 corei7-avx nocona x86-64 bdver2 bdver1 btver1 amdfam10 barcelona k8 opteron athlon64 athlon-fx athlon64-sse3 k8-sse3 opteron-sse3" 1>&2
echo "generic atom core2 corei7 corei7-avx nocona x86-64 bdver2 bdver1 btver2 btver1 amdfam10 barcelona k8 opteron athlon64 athlon-fx athlon64-sse3 k8-sse3 opteron-sse3" 1>&2
exit 1
;;
esac
......@@ -1335,7 +1335,7 @@ i[34567]86-*-solaris2* | x86_64-*-solaris2.1[0-9]*)
tmake_file="$tmake_file i386/t-sol2-64"
need_64bit_isa=yes
case X"${with_cpu}" in
Xgeneric|Xatom|Xcore2|Xcorei7|Xcorei7-avx|Xnocona|Xx86-64|Xbdver2|Xbdver1|Xbtver1|Xamdfam10|Xbarcelona|Xk8|Xopteron|Xathlon64|Xathlon-fx|Xathlon64-sse3|Xk8-sse3|Xopteron-sse3)
Xgeneric|Xatom|Xcore2|Xcorei7|Xcorei7-avx|Xnocona|Xx86-64|Xbdver2|Xbdver1|Xbtver2|Xbtver1|Xamdfam10|Xbarcelona|Xk8|Xopteron|Xathlon64|Xathlon-fx|Xathlon64-sse3|Xk8-sse3|Xopteron-sse3)
;;
X)
if test x$with_cpu_64 = x; then
......@@ -1344,7 +1344,7 @@ i[34567]86-*-solaris2* | x86_64-*-solaris2.1[0-9]*)
;;
*)
echo "Unsupported CPU used in --with-cpu=$with_cpu, supported values:" 1>&2
echo "generic atom core2 corei7 corei7-avx nocona x86-64 bdver2 bdver1 btver1 amdfam10 barcelona k8 opteron athlon64 athlon-fx athlon64-sse3 k8-sse3 opteron-sse3" 1>&2
echo "generic atom core2 corei7 corei7-avx nocona x86-64 bdver2 bdver1 btver2 btver1 amdfam10 barcelona k8 opteron athlon64 athlon-fx athlon64-sse3 k8-sse3 opteron-sse3" 1>&2
exit 1
;;
esac
......@@ -1401,7 +1401,7 @@ i[34567]86-*-mingw* | x86_64-*-mingw*)
if test x$enable_targets = xall; then
tm_defines="${tm_defines} TARGET_BI_ARCH=1"
case X"${with_cpu}" in
Xgeneric|Xatom|Xcore2|Xcorei7|Xcorei7-avx|Xnocona|Xx86-64|Xbdver2|Xbdver1|Xbtver1|Xamdfam10|Xbarcelona|Xk8|Xopteron|Xathlon64|Xathlon-fx|Xathlon64-sse3|Xk8-sse3|Xopteron-sse3)
Xgeneric|Xatom|Xcore2|Xcorei7|Xcorei7-avx|Xnocona|Xx86-64|Xbdver2|Xbdver1|Xbtver2|Xbtver1|Xamdfam10|Xbarcelona|Xk8|Xopteron|Xathlon64|Xathlon-fx|Xathlon64-sse3|Xk8-sse3|Xopteron-sse3)
;;
X)
if test x$with_cpu_64 = x; then
......@@ -1410,7 +1410,7 @@ i[34567]86-*-mingw* | x86_64-*-mingw*)
;;
*)
echo "Unsupported CPU used in --with-cpu=$with_cpu, supported values:" 1>&2
echo "generic atom core2 corei7 Xcorei7-avx nocona x86-64 bdver2 bdver1 btver1 amdfam10 barcelona k8 opteron athlon64 athlon-fx athlon64-sse3 k8-sse3 opteron-sse3" 1>&2
echo "generic atom core2 corei7 Xcorei7-avx nocona x86-64 bdver2 bdver1 btver2 btver1 amdfam10 barcelona k8 opteron athlon64 athlon-fx athlon64-sse3 k8-sse3 opteron-sse3" 1>&2
exit 1
;;
esac
......@@ -2640,6 +2640,10 @@ case ${target} in
arch=btver1
cpu=btver1
;;
btver2-*)
arch=btver2
cpu=btver2
;;
amdfam10-*|barcelona-*)
arch=amdfam10
cpu=amdfam10
......@@ -2737,6 +2741,10 @@ case ${target} in
arch=btver1
cpu=btver1
;;
btver2-*)
arch=btver2
cpu=btver2
;;
amdfam10-*|barcelona-*)
arch=amdfam10
cpu=amdfam10
......@@ -3171,7 +3179,7 @@ case "${target}" in
;;
"" | x86-64 | generic | native \
| k8 | k8-sse3 | athlon64 | athlon64-sse3 | opteron \
| opteron-sse3 | athlon-fx | bdver2 | bdver1 | btver1 \
| opteron-sse3 | athlon-fx | bdver2 | bdver1 | btver2 | btver1 \
| amdfam10 | barcelona | nocona | core2 | corei7 \
| corei7-avx | core-avx-i | core-avx2 | atom)
# OK
......
......@@ -514,6 +514,8 @@ const char *host_detect_local_cpu (int argc, const char **argv)
if (name == SIG_GEODE)
processor = PROCESSOR_GEODE;
else if (has_movbe)
processor = PROCESSOR_BTVER2;
else if (has_bmi)
processor = PROCESSOR_BDVER2;
else if (has_xop)
......@@ -687,6 +689,9 @@ const char *host_detect_local_cpu (int argc, const char **argv)
case PROCESSOR_BTVER1:
cpu = "btver1";
break;
case PROCESSOR_BTVER2:
cpu = "btver2";
break;
default:
/* Use something reasonable. */
......
......@@ -118,6 +118,10 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
def_or_undef (parse_in, "__btver1");
def_or_undef (parse_in, "__btver1__");
break;
case PROCESSOR_BTVER2:
def_or_undef (parse_in, "__btver2");
def_or_undef (parse_in, "__btver2__");
break;
case PROCESSOR_PENTIUM4:
def_or_undef (parse_in, "__pentium4");
def_or_undef (parse_in, "__pentium4__");
......@@ -208,6 +212,9 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
case PROCESSOR_BTVER1:
def_or_undef (parse_in, "__tune_btver1__");
break;
case PROCESSOR_BTVER2:
def_or_undef (parse_in, "__tune_btver2__");
break;
case PROCESSOR_PENTIUM4:
def_or_undef (parse_in, "__tune_pentium4__");
break;
......
......@@ -1509,6 +1509,85 @@ struct processor_costs btver1_cost = {
1, /* cond_not_taken_branch_cost. */
};
struct processor_costs btver2_cost = {
COSTS_N_INSNS (1), /* cost of an add instruction */
COSTS_N_INSNS (2), /* cost of a lea instruction */
COSTS_N_INSNS (1), /* variable shift costs */
COSTS_N_INSNS (1), /* constant shift costs */
{COSTS_N_INSNS (3), /* cost of starting multiply for QI */
COSTS_N_INSNS (4), /* HI */
COSTS_N_INSNS (3), /* SI */
COSTS_N_INSNS (4), /* DI */
COSTS_N_INSNS (5)}, /* other */
0, /* cost of multiply per each bit set */
{COSTS_N_INSNS (19), /* cost of a divide/mod for QI */
COSTS_N_INSNS (35), /* HI */
COSTS_N_INSNS (51), /* SI */
COSTS_N_INSNS (83), /* DI */
COSTS_N_INSNS (83)}, /* other */
COSTS_N_INSNS (1), /* cost of movsx */
COSTS_N_INSNS (1), /* cost of movzx */
8, /* "large" insn */
9, /* MOVE_RATIO */
4, /* cost for loading QImode using movzbl */
{3, 4, 3}, /* cost of loading integer registers
in QImode, HImode and SImode.
Relative to reg-reg move (2). */
{3, 4, 3}, /* cost of storing integer registers */
4, /* cost of reg,reg fld/fst */
{4, 4, 12}, /* cost of loading fp registers
in SFmode, DFmode and XFmode */
{6, 6, 8}, /* cost of storing fp registers
in SFmode, DFmode and XFmode */
2, /* cost of moving MMX register */
{3, 3}, /* cost of loading MMX registers
in SImode and DImode */
{4, 4}, /* cost of storing MMX registers
in SImode and DImode */
2, /* cost of moving SSE register */
{4, 4, 3}, /* cost of loading SSE registers
in SImode, DImode and TImode */
{4, 4, 5}, /* cost of storing SSE registers
in SImode, DImode and TImode */
3, /* MMX or SSE register to integer */
/* On K8:
MOVD reg64, xmmreg Double FSTORE 4
MOVD reg32, xmmreg Double FSTORE 4
On AMDFAM10:
MOVD reg64, xmmreg Double FADD 3
1/1 1/1
MOVD reg32, xmmreg Double FADD 3
1/1 1/1 */
32, /* size of l1 cache. */
2048, /* size of l2 cache. */
64, /* size of prefetch block */
100, /* number of parallel prefetches */
2, /* Branch cost */
COSTS_N_INSNS (4), /* cost of FADD and FSUB insns. */
COSTS_N_INSNS (4), /* cost of FMUL instruction. */
COSTS_N_INSNS (19), /* cost of FDIV instruction. */
COSTS_N_INSNS (2), /* cost of FABS instruction. */
COSTS_N_INSNS (2), /* cost of FCHS instruction. */
COSTS_N_INSNS (35), /* cost of FSQRT instruction. */
{{libcall, {{6, loop}, {14, unrolled_loop}, {-1, rep_prefix_4_byte}}},
{libcall, {{16, loop}, {8192, rep_prefix_8_byte}, {-1, libcall}}}},
{{libcall, {{8, loop}, {24, unrolled_loop},
{2048, rep_prefix_4_byte}, {-1, libcall}}},
{libcall, {{48, unrolled_loop}, {8192, rep_prefix_8_byte}, {-1, libcall}}}},
4, /* scalar_stmt_cost. */
2, /* scalar load_cost. */
2, /* scalar_store_cost. */
6, /* vec_stmt_cost. */
0, /* vec_to_scalar_cost. */
2, /* scalar_to_vec_cost. */
2, /* vec_align_load_cost. */
2, /* vec_unalign_load_cost. */
2, /* vec_store_cost. */
2, /* cond_taken_branch_cost. */
1, /* cond_not_taken_branch_cost. */
};
static const
struct processor_costs pentium4_cost = {
COSTS_N_INSNS (1), /* cost of an add instruction */
......@@ -1909,8 +1988,10 @@ const struct processor_costs *ix86_cost = &pentium_cost;
#define m_BDVER1 (1<<PROCESSOR_BDVER1)
#define m_BDVER2 (1<<PROCESSOR_BDVER2)
#define m_BDVER (m_BDVER1 | m_BDVER2)
#define m_BTVER (m_BTVER1 | m_BTVER2)
#define m_BTVER1 (1<<PROCESSOR_BTVER1)
#define m_AMD_MULTIPLE (m_ATHLON_K8 | m_AMDFAM10 | m_BDVER | m_BTVER1)
#define m_BTVER2 (1<<PROCESSOR_BTVER2)
#define m_AMD_MULTIPLE (m_ATHLON_K8 | m_AMDFAM10 | m_BDVER | m_BTVER)
#define m_GENERIC32 (1<<PROCESSOR_GENERIC32)
#define m_GENERIC64 (1<<PROCESSOR_GENERIC64)
......@@ -1950,7 +2031,7 @@ static unsigned int initial_ix86_tune_features[X86_TUNE_LAST] = {
~m_386,
/* X86_TUNE_USE_SAHF */
m_PPRO | m_P4_NOCONA | m_CORE2I7 | m_ATOM | m_K6_GEODE | m_K8 | m_AMDFAM10 | m_BDVER | m_BTVER1 | m_GENERIC,
m_PPRO | m_P4_NOCONA | m_CORE2I7 | m_ATOM | m_K6_GEODE | m_K8 | m_AMDFAM10 | m_BDVER | m_BTVER | m_GENERIC,
/* X86_TUNE_MOVX: Enable to zero extend integer registers to avoid
partial dependencies. */
......@@ -2056,7 +2137,7 @@ static unsigned int initial_ix86_tune_features[X86_TUNE_LAST] = {
m_PPRO | m_P4_NOCONA | m_CORE2I7 | m_ATOM | m_AMDFAM10 | m_BDVER | m_GENERIC,
/* X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL */
m_COREI7 | m_AMDFAM10 | m_BDVER | m_BTVER1,
m_COREI7 | m_AMDFAM10 | m_BDVER | m_BTVER,
/* X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL */
m_COREI7 | m_BDVER,
......@@ -2131,11 +2212,11 @@ static unsigned int initial_ix86_tune_features[X86_TUNE_LAST] = {
/* X86_TUNE_SLOW_IMUL_IMM32_MEM: Imul of 32-bit constant and memory is
vector path on AMD machines. */
m_CORE2I7_64 | m_K8 | m_AMDFAM10 | m_BDVER | m_BTVER1 | m_GENERIC64,
m_CORE2I7_64 | m_K8 | m_AMDFAM10 | m_BDVER | m_BTVER | m_GENERIC64,
/* X86_TUNE_SLOW_IMUL_IMM8: Imul of 8-bit constant is vector path on AMD
machines. */
m_CORE2I7_64 | m_K8 | m_AMDFAM10 | m_BDVER | m_BTVER1 | m_GENERIC64,
m_CORE2I7_64 | m_K8 | m_AMDFAM10 | m_BDVER | m_BTVER | m_GENERIC64,
/* X86_TUNE_MOVE_M1_VIA_OR: On pentiums, it is faster to load -1 via OR
than a MOV. */
......@@ -2606,6 +2687,7 @@ static const struct ptt processor_target_table[PROCESSOR_max] =
{&bdver1_cost, 32, 24, 32, 7, 32},
{&bdver2_cost, 32, 24, 32, 7, 32},
{&btver1_cost, 32, 24, 32, 7, 32},
{&btver2_cost, 32, 24, 32, 7, 32},
{&atom_cost, 16, 15, 16, 7, 16}
};
......@@ -2636,7 +2718,8 @@ static const char *const cpu_names[TARGET_CPU_DEFAULT_max] =
"amdfam10",
"bdver1",
"bdver2",
"btver1"
"btver1",
"btver2"
};
/* Return true if a red-zone is in use. */
......@@ -3082,6 +3165,11 @@ ix86_option_override_internal (bool main_args_p)
| PTA_SSSE3 | PTA_SSE4A |PTA_ABM | PTA_CX16},
{"generic32", PROCESSOR_GENERIC32, CPU_PENTIUMPRO,
PTA_HLE /* flags are only used for -march switch. */ },
{"btver2", PROCESSOR_BTVER2, CPU_GENERIC64,
PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3
| PTA_SSSE3 | PTA_SSE4A |PTA_ABM | PTA_CX16 | PTA_SSE4_1
| PTA_SSE4_2 | PTA_AES | PTA_PCLMUL | PTA_AVX
| PTA_BMI | PTA_F16C | PTA_MOVBE},
{"generic64", PROCESSOR_GENERIC64, CPU_GENERIC64,
PTA_64BIT
| PTA_HLE /* flags are only used for -march switch. */ },
......@@ -23692,6 +23780,7 @@ ix86_issue_rate (void)
case PROCESSOR_PENTIUM:
case PROCESSOR_ATOM:
case PROCESSOR_K6:
case PROCESSOR_BTVER2:
return 2;
case PROCESSOR_PENTIUMPRO:
......@@ -23898,6 +23987,7 @@ ix86_adjust_cost (rtx insn, rtx link, rtx dep_insn, int cost)
case PROCESSOR_BDVER1:
case PROCESSOR_BDVER2:
case PROCESSOR_BTVER1:
case PROCESSOR_BTVER2:
case PROCESSOR_ATOM:
case PROCESSOR_GENERIC32:
case PROCESSOR_GENERIC64:
......@@ -249,6 +249,7 @@ extern const struct processor_costs ix86_size_cost;
#define TARGET_BDVER1 (ix86_tune == PROCESSOR_BDVER1)
#define TARGET_BDVER2 (ix86_tune == PROCESSOR_BDVER2)
#define TARGET_BTVER1 (ix86_tune == PROCESSOR_BTVER1)
#define TARGET_BTVER2 (ix86_tune == PROCESSOR_BTVER2)
#define TARGET_ATOM (ix86_tune == PROCESSOR_ATOM)
/* Feature tests against the various tunings. */
......@@ -608,6 +609,7 @@ enum target_cpu_default
TARGET_CPU_DEFAULT_bdver1,
TARGET_CPU_DEFAULT_bdver2,
TARGET_CPU_DEFAULT_btver1,
TARGET_CPU_DEFAULT_btver2,
TARGET_CPU_DEFAULT_max
};
......@@ -2067,6 +2069,7 @@ enum processor_type
PROCESSOR_BDVER1,
PROCESSOR_BDVER2,
PROCESSOR_BTVER1,
PROCESSOR_BTVER2,
PROCESSOR_ATOM,
PROCESSOR_max
};
......
......@@ -310,7 +310,7 @@
;; Processor type.
(define_attr "cpu" "none,pentium,pentiumpro,geode,k6,athlon,k8,core2,corei7,
atom,generic64,amdfam10,bdver1,bdver2,btver1"
atom,generic64,amdfam10,bdver1,bdver2,btver1,btver2"
(const (symbol_ref "ix86_schedule")))
;; A basic instruction type. Refinements due to arguments to be
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment