Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add AMD PMC/U support #222

Merged
merged 5 commits into from
Aug 9, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions src/data.rs
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,9 @@ cfg_if::cfg_if! {
pub mod intel_perf_events;
pub mod intel_icelake_perf_events;
pub mod intel_sapphire_rapids_perf_events;
pub mod amd_perf_events;
pub mod amd_genoa_perf_events;
pub mod amd_milan_perf_events;
}
}
pub mod interrupts;
Expand Down
24 changes: 24 additions & 0 deletions src/data/amd_genoa_perf_events.rs
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
use crate::data::perf_stat::{NamedCtr, NamedTypeCtr, PerfType};

static STALL_BACKEND: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "Backend-Stalls",
config: 0x100001ea0,
};
static CYCLES: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "Cycles",
config: 0x0076,
};

lazy_static! {
pub static ref GENOA_CTRS: Vec<NamedCtr<'static>> = [
NamedCtr {
name: "stall_backend_pkc",
nrs: vec![STALL_BACKEND],
drs: vec![CYCLES],
scale: 167 //~= 1000/6
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

That is really weird, why this value instead of just 1000? The ones below for milan are just 1000.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not sure, I think its from each cycle being able to dispatch 6 instructions? This scale was from our documentation and AMD documentation.

},
]
.to_vec();
}
27 changes: 27 additions & 0 deletions src/data/amd_milan_perf_events.rs
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
use crate::data::perf_stat::{NamedCtr, NamedTypeCtr, PerfType};

static STALL_BACKEND_1: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "Backend-Stalls-1",
config: 0xf7ae,
};
static STALL_BACKEND_2: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "Backend-Stalls-2",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Are there any better specifiers for these besides just -1 and -2?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not sure, each one counts several backend stall types.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If it's not documented what exactly each one counts, perhaps the better thing to do is add them together. That assumes there's not overlap in what each one counts.

Copy link
Contributor Author

@lancelui-amzn lancelui-amzn Aug 7, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Talked with Geoff, the sum of the two is the total backend stalls. Pushed changes

config: 0x27af,
};
static CYCLES: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "Cycles",
config: 0x0076,
};

lazy_static! {
pub static ref MILAN_CTRS: Vec<NamedCtr<'static>> = [NamedCtr {
name: "stall_backend_pkc",
nrs: vec![STALL_BACKEND_1, STALL_BACKEND_2],
drs: vec![CYCLES],
scale: 1000
}]
.to_vec();
}
136 changes: 136 additions & 0 deletions src/data/amd_perf_events.rs
Original file line number Diff line number Diff line change
@@ -0,0 +1,136 @@
use crate::data::perf_stat::{NamedCtr, NamedTypeCtr, PerfType};

// amd events
static INSTRUCTIONS: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "Instructions",
config: 0x00c0,
};
static CYCLES: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "Cycles",
config: 0x0076,
};
static BRANCH_MISPRED: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "Branch-Mispredictions",
config: 0x00c3,
};
static L1_DATA_FILL: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "L1-Data-Fills",
config: 0xff44,
};
static L1_INSTRUCTION_MISS: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "L1-Instruction-Misses",
config: 0x1060,
};
static L2_DEMAND_MISS: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "L2-Demand-Misses",
config: 0x0964,
};
static L1_ANY_FILLS_DRAM: NamedTypeCtr = NamedTypeCtr {
// Approximately L3 Misses
perf_type: PerfType::RAW,
name: "L1-Any-Fills-DRAM",
config: 0x0844,
};
static STALL_FRONTEND: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "Frontend-Stalls",
config: 0x00a9,
};
static INSTRUCTION_TLB_MISS: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "Instruction-TLB-Misses",
config: 0x0084,
};
static INSTRUCTION_TLB_TW_MISS: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "Instruction-TLB-TW-Misses",
config: 0x0f85,
};
static DATA_TLB_MISS: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "Data-TLB-Misses",
config: 0xff45,
};
static DATA_TLB_TW_MISS: NamedTypeCtr = NamedTypeCtr {
perf_type: PerfType::RAW,
name: "Data-TLB-TW-Misses",
config: 0xf045,
};

lazy_static! {
pub static ref PERF_LIST: Vec<NamedCtr<'static>> = [
NamedCtr {
name: "ipc",
nrs: vec![INSTRUCTIONS],
drs: vec![CYCLES],
scale: 1
},
NamedCtr {
name: "branch-mpki",
nrs: vec![BRANCH_MISPRED],
drs: vec![INSTRUCTIONS],
scale: 1000
},
NamedCtr {
name: "data-l1-mpki",
nrs: vec![L1_DATA_FILL],
drs: vec![INSTRUCTIONS],
scale: 1000
},
NamedCtr {
name: "inst-l1-mpki",
nrs: vec![L1_INSTRUCTION_MISS],
drs: vec![INSTRUCTIONS],
scale: 1000
},
NamedCtr {
name: "l2-mpki",
nrs: vec![L2_DEMAND_MISS],
drs: vec![INSTRUCTIONS],
scale: 1000
},
NamedCtr {
name: "l3-mpki",
nrs: vec![L1_ANY_FILLS_DRAM],
drs: vec![INSTRUCTIONS],
scale: 1000
},
NamedCtr {
name: "stall_frontend_pkc",
nrs: vec![STALL_FRONTEND],
drs: vec![CYCLES],
scale: 1000
},
NamedCtr {
name: "inst-tlb-mpki",
nrs: vec![INSTRUCTION_TLB_MISS],
drs: vec![INSTRUCTIONS],
scale: 1000
},
NamedCtr {
name: "inst-tlb-tw-mpki",
nrs: vec![INSTRUCTION_TLB_TW_MISS],
drs: vec![INSTRUCTIONS],
scale: 1000
},
NamedCtr {
name: "data-tlb-mpki",
nrs: vec![DATA_TLB_MISS],
drs: vec![INSTRUCTIONS],
scale: 1000
},
NamedCtr {
name: "data-tlb-tw-pki",
nrs: vec![DATA_TLB_TW_MISS],
drs: vec![INSTRUCTIONS],
scale: 1000
},
]
.to_vec();
}
17 changes: 14 additions & 3 deletions src/data/perf_stat.rs
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,10 @@ use std::sync::Mutex;
use crate::data::grv_perf_events;
#[cfg(any(target_arch = "x86", target_arch = "x86_64"))]
use {
crate::data::intel_icelake_perf_events::ICX_CTRS, crate::data::intel_perf_events,
crate::data::intel_sapphire_rapids_perf_events::SPR_CTRS, crate::data::utils::get_cpu_info,
indexmap::IndexMap,
crate::data::amd_genoa_perf_events::GENOA_CTRS, crate::data::amd_milan_perf_events::MILAN_CTRS,
crate::data::amd_perf_events, crate::data::intel_icelake_perf_events::ICX_CTRS,
crate::data::intel_perf_events, crate::data::intel_sapphire_rapids_perf_events::SPR_CTRS,
crate::data::utils::get_cpu_info, indexmap::IndexMap,
};

pub static PERF_STAT_FILE_NAME: &str = "perf_stat";
Expand Down Expand Up @@ -140,6 +141,16 @@ impl CollectData for PerfStatRaw {
"Intel(R) Xeon(R) Platinum 8488C" => SPR_CTRS.to_vec(),
_ => Vec::new(),
};
} else if cpu_info.vendor == "AuthenticAMD" {
warn!("Event multiplexing may result in bad PMU data."); //TODO: mitigate bad PMU data on AMD instances
perf_list = amd_perf_events::PERF_LIST.to_vec();

/* Get Model specific events */
platform_specific_counter = match cpu_info.model_name.get(..13).unwrap_or_default() {
"AMD EPYC 9R14" => GENOA_CTRS.to_vec(),
"AMD EPYC 7R13" => MILAN_CTRS.to_vec(),
_ => Vec::new(),
};
} else {
return Err(PDError::CollectorPerfUnsupportedCPU.into());
}
Expand Down
Loading