Lerking/nanoBench
1
0
Fork 0
mirror of https://github.com/andreas-abel/nanoBench.git synced 2025-12-16 11:30:07 +01:00
Code Issues Packages Projects Releases Wiki Activity

cycle-by-cycle measurements

Browse Source
This commit is contained in:
Andreas Abel
2022-01-21 00:12:50 +01:00
parent 7f7a7eb53a
commit d3d4060be3
6 changed files with 655 additions and 83 deletions
Download Patch File Download Diff File Expand all files Collapse all files

66
common/nanoBench.c
View File

@@ -571,16 +571,6 @@ void create_runtime_code(char* measurement_template, long local_unroll_count, lo
*(int32_t*)(&runtime_code[rcI]) = (int32_t)local_loop_count; rcI += 4; // mov R15, local_loop_count
}
if (drain_frontend) {
strcpy(&runtime_code[rcI], "\x0F\xAE\xE8"); rcI += 3; // lfence
for (int i=0; i<192; i++) {
strcpy(&runtime_code[rcI], NOPS[1]); rcI += 1;
}
for (int i=0; i<64; i++) {
strcpy(&runtime_code[rcI], NOPS[15]); rcI += 15;
}
}
int dist = get_distance_to_code(measurement_template, templateI) + code_late_init_length;
int n_fill = (64 - ((uintptr_t)&runtime_code[rcI+dist] % 64)) % 64;
n_fill += alignment_offset;
@@ -589,6 +579,16 @@ void create_runtime_code(char* measurement_template, long local_unroll_count, lo
strcpy(&runtime_code[rcI], NOPS[nop_len]); rcI += nop_len;
n_fill -= nop_len;
}
if (drain_frontend) {
strcpy(&runtime_code[rcI], "\x0F\xAE\xE8"); rcI += 3; // lfence
for (int i=0; i<189; i++) {
strcpy(&runtime_code[rcI], NOPS[1]); rcI += 1;
}
for (int i=0; i<64; i++) {
strcpy(&runtime_code[rcI], NOPS[15]); rcI += 15;
}
}
} else if (starts_with_magic_bytes(&measurement_template[templateI], MAGIC_BYTES_PFC_START)) {
magic_bytes_pfc_start_I = templateI;
templateI += 8;
@@ -1567,6 +1567,52 @@ void measurement_RDMSR_template_noMem() {
asm(".quad "STRINGIFY(MAGIC_BYTES_TEMPLATE_END));
}
void measurement_cycleByCycle_template_Intel() {
SAVE_REGS_FLAGS();
asm(".intel_syntax noprefix \n"
".quad "STRINGIFY(MAGIC_BYTES_INIT) " \n"
"push rax \n"
"push rcx \n"
"push rdx \n"
"mov rcx, 0x38F \n"
"mov rax, 0xF \n"
"mov rdx, 0x7 \n"
"wrmsr \n"
"pop rdx \n"
"pop rcx \n"
"pop rax \n"
"lfence \n"
".quad "STRINGIFY(MAGIC_BYTES_CODE) " \n"
"lfence \n"
"mov rcx, 0x38F \n"
"mov rax, 0x0 \n"
"mov rdx, 0x0 \n"
"wrmsr \n"
".att_syntax prefix \n");
RESTORE_REGS_FLAGS();
asm(".quad " STRINGIFY(MAGIC_BYTES_TEMPLATE_END));
}
void measurement_cycleByCycle_template_Intel_noMem() {
SAVE_REGS_FLAGS();
asm(".intel_syntax noprefix \n"
".quad "STRINGIFY(MAGIC_BYTES_INIT) " \n"
"mov rcx, 0x38F \n"
"mov rax, 0xF \n"
"mov rdx, 0x7 \n"
"wrmsr \n"
"lfence \n"
".quad "STRINGIFY(MAGIC_BYTES_CODE) " \n"
"lfence \n"
"mov rcx, 0x38F \n"
"mov rax, 0x0 \n"
"mov rdx, 0x0 \n"
"wrmsr \n"
".att_syntax prefix \n");
RESTORE_REGS_FLAGS();
asm(".quad " STRINGIFY(MAGIC_BYTES_TEMPLATE_END));
}
void one_time_init_template() {
SAVE_REGS_FLAGS();
asm(".quad "STRINGIFY(MAGIC_BYTES_INIT));

8
common/nanoBench.h
View File

@@ -80,6 +80,10 @@
#define CORE_X86_MSR_PERF_CTR 0xC0010201
#endif
#define FIXED_CTR_INST_RETIRED 0
#define FIXED_CTR_CORE_CYCLES 1
#define FIXED_CTR_REF_CYCLES 2
// How often the measurement will be repeated.
extern long n_measurements;
@@ -311,6 +315,8 @@ void measurement_RDTSC_template(void);
void measurement_RDTSC_template_noMem(void);
void measurement_RDMSR_template(void);
void measurement_RDMSR_template_noMem(void);
void measurement_cycleByCycle_template_Intel(void);
void measurement_cycleByCycle_template_Intel_noMem(void);
void one_time_init_template(void);
void initial_warm_up_template(void);
@@ -357,4 +363,4 @@ void initial_warm_up_template(void);
"pop rbx\n" \
".att_syntax noprefix");
#endif
#endif