| #
2079f7aa |
|
18-Mar-2020 |
Vijay Thakkar <vijaythakkar@me.com> |
perf vendor events amd: Add Zen2 events
This patch adds PMU events for AMD Zen2 core based processors, namely,
Matisse (model 71h), Castle Peak (model 31h) and Rome (model 2xh), as
documented in the AMD Processor Programming Reference for Matisse [1].
The model number regex has been set to detect all the models under
family 17 that do not match those of Zen1, as the range is larger for
zen2.
Zen2 adds some additional counters that are not present in Zen1 and
events for them have been added in this patch. Some counters have also
been removed for Zen2 thatwere previously present in Zen1 and have been
confirmed to always sample zero on zen2. These added/removed counters
have been omitted for brevity but can be found here:
https://gist.github.com/thakkarV/5b12ca5fd7488eb2c42e451e40bdd5f3
Note that PPR for Zen2 [1] does not include some counters that were
documented in the PPR for Zen1 based processors [2]. After having tested
these counters, some of them that still work for zen2 systems have been
preserved in the events for zen2. The counters that are omitted in [1]
but are still measurable and non-zero on zen2 (tested on a Ryzen 3900X
system) are the following:
PMC 0x000 fpu_pipe_assignment.{total|total0|total1|total2|total3}
PMC 0x004 fp_num_mov_elim_scal_op.*
PMC 0x046 ls_tablewalker.*
PMC 0x062 l2_latency.l2_cycles_waiting_on_fills
PMC 0x063 l2_wcb_req.*
PMC 0x06D l2_fill_pending.l2_fill_busy
PMC 0x080 ic_fw32
PMC 0x081 ic_fw32_miss
PMC 0x086 bp_snp_re_sync
PMC 0x087 ic_fetch_stall.*
PMC 0x08C ic_cache_inval.*
PMC 0x099 bp_tlb_rel
PMC 0x0C7 ex_ret_brn_resync
PMC 0x28A ic_oc_mode_switch.*
L3PMC 0x001 l3_request_g1.*
L3PMC 0x006 l3_comb_clstr_state.*
[1]: Processor Programming Reference (PPR) for AMD Family 17h Model 71h,
Revision B0 Processors, 56176 Rev 3.06 - Jul 17, 2019
[2]: Processor Programming Reference (PPR) for AMD Family 17h Models
01h,08h, Revision B2 Processors, 54945 Rev 3.03 - Jun 14, 2019
All of the PPRs can be found at:
https://bugzilla.kernel.org/show_bug.cgi?id=206537
Here are the results of running "fpu_pipe_assignment.total" events on my
Ryzen 3900X family 17h model 71h system:
Before this patch:
$> perf list *fpu_pipe_assignment*
List of pre-defined events (to be used in -e):
After:
$> perf list *fpu_pipe_assignment*
floating point:
fpu_pipe_assignment.total
[Total number of fp uOps]
fpu_pipe_assignment.total0
[Total number uOps assigned to pipe 0]
fpu_pipe_assignment.total1
[Total number uOps assigned to pipe 1]
fpu_pipe_assignment.total2
[Total number uOps assigned to pipe 2]
fpu_pipe_assignment.total3
[Total number uOps assigned to pipe 3]
Metric Groups:
$> perf stat -e fpu_pipe_assignment.total sleep 1
Performance counter stats for 'sleep 1':
25,883 fpu_pipe_assignment.total
1.004145868 seconds time elapsed
0.001805000 seconds user
0.000000000 seconds sys
Usage tests while running Linpackin the background:
$> perf stat -I1000 -e fpu_pipe_assignment.total
1.000266796 79,313,191,516 fpu_pipe_assignment.total
2.000809630 68,091,474,430 fpu_pipe_assignment.total
3.001028115 52,925,023,174 fpu_pipe_assignment.total
$> perf record -e fpu_pipe_assignment.total,fpu_pipe_assignment.total0 -a sleep 1
[ perf record: Woken up 9 times to write data ]
[ perf record: Captured and wrote 4.031 MB perf.data (64764 samples) ]
$> perf report --stdio --no-header | head -30
98.33% xhpl xhpl [.] dgemm_kernel
0.28% xhpl xhpl [.] dtrsm_kernel_LT
0.10% xhpl [kernel.kallsyms] [k] entry_SYSCALL_64
0.08% xhpl xhpl [.] idamax_k
0.07% baloo_file_extr liblmdb.so [.] mdb_mid2l_insert
0.06% xhpl xhpl [.] dgemm_itcopy
0.06% xhpl xhpl [.] dgemm_oncopy
0.06% xhpl [kernel.kallsyms] [k] __schedule
0.06% xhpl [kernel.kallsyms] [k] syscall_trace_enter
0.06% xhpl [kernel.kallsyms] [k] native_sched_clock
0.06% xhpl [kernel.kallsyms] [k] pick_next_task_fair
0.05% xhpl xhpl [.] blas_thread_server.llvm.15009391670273914865
0.04% xhpl [kernel.kallsyms] [k] do_syscall_64
0.04% xhpl [kernel.kallsyms] [k] yield_task_fair
0.04% xhpl libpthread-2.31.so [.] __pthread_mutex_unlock_usercnt
0.03% xhpl [kernel.kallsyms] [k] cpuacct_charge
0.03% xhpl [kernel.kallsyms] [k] syscall_return_via_sysret
0.03% xhpl libc-2.31.so [.] __sched_yield
0.03% xhpl [kernel.kallsyms] [k] __calc_delta
$> perf annotate --stdio2 dgemm_kernel | egrep '^ {0,2}[0-9]+' -B2 -A2
sub $0x60,%rsp
mov %rbx,(%rsp)
0.00 mov %rbp,0x8(%rsp)
mov %r12,0x10(%rsp)
0.00 mov %r13,0x18(%rsp)
mov %r14,0x20(%rsp)
mov %r15,0x28(%rsp)
--
mov %rdi,%r13
mov %rsi,0x28(%rsp)
0.00 mov %rdx,%r12
vmovsd %xmm0,0x30(%rsp)
shl $0x3,%r10
mov 0x28(%rsp),%rax
0.00 xor %rdx,%rdx
mov $0x18,%rdi
div %rdi
--
nop
a0: mov %r12,%rax
0.00 shl $0x3,%rax
mov %r8,%rdi
lea (%r8,%rax,8),%r15
--
mov %r12,%rax
nop
0.00 c0: vmovups (%rdi),%ymm1
0.09 vmovups 0x20(%rdi),%ymm2
0.02 vmovups (%r15),%ymm3
0.10 vmovups %ymm1,(%rsi)
0.07 vmovups %ymm2,0x20(%rsi)
0.07 vmovups %ymm3,0x40(%rsi)
0.06 add $0x40,%rdi
add $0x40,%r15
add $0x60,%rsi
0.00 dec %rax
↑ jne c0
mov %r9,%r15
--
nop
110: lea 0x80(%rsp),%rsi
0.01 add $0x60,%rsi
0.03 mov %r12,%rax
0.00 sar $0x3,%rax
cmp $0x2,%rax
↓ jl d26
prefetcht0 0x200(%rdi)
0.01 vmovups -0x60(%rsi),%ymm1
0.02 prefetcht0 0xa0(%rsi)
0.00 vbroadcastsd -0x80(%rdi),%ymm0
0.00 prefetcht0 0xe0(%rsi)
0.03 vmovups -0x40(%rsi),%ymm2
0.00 prefetcht0 0x120(%rsi)
vmovups -0x20(%rsi),%ymm3
vmulpd %ymm0,%ymm1,%ymm4
0.01 prefetcht0 0x160(%rsi)
vmulpd %ymm0,%ymm2,%ymm8
0.01 vmulpd %ymm0,%ymm3,%ymm12
0.02 prefetcht0 0x1a0(%rsi)
0.01 vbroadcastsd -0x78(%rdi),%ymm0
vmulpd %ymm0,%ymm1,%ymm5
0.01 vmulpd %ymm0,%ymm2,%ymm9
vmulpd %ymm0,%ymm3,%ymm13
0.01 vbroadcastsd -0x70(%rdi),%ymm0
vmulpd %ymm0,%ymm1,%ymm6
0.00 vmulpd %ymm0,%ymm2,%ymm10
0.00 add $0x60,%rsi
... snip ...
nop
65e0: vmovddup -0x60(%rsi),%xmm2
0.00 vmovups -0x80(%rdi),%xmm0
vmovups -0x70(%rdi),%xmm1
0.00 vmovddup -0x58(%rsi),%xmm3
vfmadd231pd %xmm0,%xmm2,%xmm4
0.00 vfmadd231pd %xmm1,%xmm2,%xmm5
0.00 vfmadd231pd %xmm0,%xmm3,%xmm6
0.00 vfmadd231pd %xmm1,%xmm3,%xmm7
0.00 add $0x10,%rsi
add $0x20,%rdi
0.00 dec %rax
↑ jne 65e0
nop
nop
6620: vmovddup 0x30(%rsp),%xmm0
0.00 vmulpd %xmm0,%xmm4,%xmm4
0.00 vmulpd %xmm0,%xmm5,%xmm5
vmulpd %xmm0,%xmm6,%xmm6
vmulpd %xmm0,%xmm7,%xmm7
vaddpd (%r15),%xmm4,%xmm4
vaddpd 0x10(%r15),%xmm5,%xmm5
0.00 vaddpd (%r15,%r10,1),%xmm6,%xmm6
0.00 vaddpd 0x10(%r15,%r10,1),%xmm7,%xmm7
0.00 vmovups %xmm4,(%r15)
vmovups %xmm5,0x10(%r15)
0.00 vmovups %xmm6,(%r15,%r10,1)
vmovups %xmm7,0x10(%r15,%r10,1)
add $0x20,%r15
--
lea (%r8,%rax,8),%r8
69d8: mov 0x20(%rsp),%r14
0.00 test $0x1,%r14
↓ je 6d84
mov %r9,%r15
--
vbroadcastsd -0x28(%rsi),%ymm3
vfmadd231pd (%rdi),%ymm0,%ymm4
0.00 vfmadd231pd 0x20(%rdi),%ymm1,%ymm5
vfmadd231pd 0x40(%rdi),%ymm2,%ymm6
vfmadd231pd 0x60(%rdi),%ymm3,%ymm7
--
vmulpd %ymm0,%ymm4,%ymm4
vaddpd (%r15),%ymm4,%ymm4
0.00 vmovups %ymm4,(%r15)
add $0x20,%r15
dec %r11
--
mov %rbx,%rsp
mov (%rsp),%rbx
0.01 mov 0x8(%rsp),%rbp
mov 0x10(%rsp),%r12
mov 0x18(%rsp),%r13
Signed-off-by: Vijay Thakkar <vijaythakkar@me.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Kim Phillips <kim.phillips@amd.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Jon Grimm <jon.grimm@amd.com>
Cc: Martin Liška <mliska@suse.cz>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20200318190002.307290-3-vijaythakkar@me.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|