Messages in this thread Patch in this message | | | From | Ravi Bangoria <> | Subject | [PATCH v2 2/2] perf annotate: Add fusion logic for AMD microarchs | Date | Sat, 11 Sep 2021 10:08:54 +0530 |
| |
AMD family 15h and above microarchs fuse a subset of cmp/test/ALU instructions with branch instructions[1][2]. Add perf annotate fused instruction support for these microarchs.
Before: │ testb $0x80,0x51(%rax) │ ┌──jne 5b3 0.78 │ │ mov %r13,%rdi │ │→ callq mark_page_accessed 1.08 │5b3:└─→mov 0x8(%r13),%rax
After: │ ┌──testb $0x80,0x51(%rax) │ ├──jne 5b3 0.78 │ │ mov %r13,%rdi │ │→ callq mark_page_accessed 1.08 │5b3:└─→mov 0x8(%r13),%rax
[1] https://bugzilla.kernel.org/attachment.cgi?id=298553 [2] https://bugzilla.kernel.org/attachment.cgi?id=298555
Reported-by: Kim Phillips <kim.phillips@amd.com> Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com> --- v1->v2: - Don't store vendor id. Instead, directly assign function pointer based on verndor id. (acme)
tools/perf/arch/x86/annotate/instructions.c | 28 ++++++++++++++++++++- tools/perf/util/annotate.c | 1 - 2 files changed, 27 insertions(+), 2 deletions(-)
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index 24ea12ec7e02..305872692bfd 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -144,8 +144,31 @@ static struct ins x86__instructions[] = { { .name = "xorps", .ops = &mov_ops, }, }; -static bool x86__ins_is_fused(struct arch *arch, const char *ins1, +static bool amd__ins_is_fused(struct arch *arch, const char *ins1, const char *ins2) +{ + if (strstr(ins2, "jmp")) + return false; + + /* Family >= 15h supports cmp/test + branch fusion */ + if (arch->family >= 0x15 && (strstarts(ins1, "test") || + (strstarts(ins1, "cmp") && !strstr(ins1, "xchg")))) { + return true; + } + + /* Family >= 19h supports some ALU + branch fusion */ + if (arch->family >= 0x19 && (strstarts(ins1, "add") || + strstarts(ins1, "sub") || strstarts(ins1, "and") || + strstarts(ins1, "inc") || strstarts(ins1, "dec") || + strstarts(ins1, "or") || strstarts(ins1, "xor"))) { + return true; + } + + return false; +} + +static bool intel__ins_is_fused(struct arch *arch, const char *ins1, + const char *ins2) { if (arch->family != 6 || arch->model < 0x1e || strstr(ins2, "jmp")) return false; @@ -184,6 +207,9 @@ static int x86__cpuid_parse(struct arch *arch, char *cpuid) if (ret == 3) { arch->family = family; arch->model = model; + arch->ins_is_fused = strstarts(cpuid, "AuthenticAMD") ? + amd__ins_is_fused : + intel__ins_is_fused; return 0; } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 0bae061b2d6d..b55f35485e43 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -183,7 +183,6 @@ static struct arch architectures[] = { .init = x86__annotate_init, .instructions = x86__instructions, .nr_instructions = ARRAY_SIZE(x86__instructions), - .ins_is_fused = x86__ins_is_fused, .objdump = { .comment_char = '#', }, -- 2.27.0
| |