Giovanni Lenzi Baraldi
ea56f79495
* Enabling codeobj and thread trace samples
* Updating aqlprofile_v2 header
* Codeobj and thread trace samples with output log files
* Fixing clang format
* Cmake formatting
* Adding coverage to codeobj
* Comment trace sample
* Adding ATT Parser API
* Fixing forwarding to aqlprofile
* Clang formatting
* Clang tidy
* Adding option to print memory kernels
* Clang format
* Remove default from switch case
* Separating client/main on codeobj sample for ASAn
* Formatting
* Gbaraldi/att tool rebase (#801)
* Enabling codeobj and thread trace samples
* Updating aqlprofile_v2 header
* Codeobj and thread trace samples with output log files
* Fixing clang format
* Cmake formatting
* Adding coverage to codeobj
* Comment trace sample
* Removing python from workflow
* Adding ATT Parser API
* Fixing forwarding to aqlprofile
* Clang formatting
* Clang tidy
* Adding option to print memory kernels
* Clang format
* Remove default from switch case
* Separating client/main on codeobj sample for ASAn
* Formatting
* Enabling codeobj and thread trace samples
* Updating aqlprofile_v2 header
* Codeobj and thread trace samples with output log files
* Fixing clang format
* Cmake formatting
* Adding coverage to codeobj
* Comment trace sample
* Adding ATT Parser API
* Fixing forwarding to aqlprofile
* Clang formatting
* Clang tidy
* Adding option to print memory kernels
* Clang format
* Remove default from switch case
* Separating client/main on codeobj sample for ASAn
* Formatting
* Fix codeobj library
* Allow thread trace in parallel with other service
* Zeroing the HSA signals
* Adding exception wrappers in ATT sample
* Removed force configure
* Remove force configure from ISA decode
* Removing codecov flag
* Gbaraldi/att tool tests (#828)
* Adding tests for codeobj ISA decode
* Adding ATT tests
* Adding ATT integration tests
* Formatting
* Changing codeobj binary extension
* Renaming codeobj library spaces
* Fixing samples
* Formatting
* Formatting
* Fixing int test
* Fixing linker error
* Fixing memory fault
* Moving kernel ot inside namespace
* ASAN linking fix
* Removing unecessary headers
* Formatting
* Fixing target_cu
* Remove codeobj binary
* Revert "Remove codeobj binary"
This reverts commit 7d286f89d8096bc36925cd79cd742a5e6d10d179.
* Enable memory snapshot
* adding comgr
---------
Co-authored-by: Ammar ELWazir <ammar.elwazir@amd.com>
[ROCm/rocprofiler-sdk commit: 099ac7c72d]
18 righe
519 B
ArmAsm
18 righe
519 B
ArmAsm
s_load_b64 s[0:1], s[0:1], 0x0
|
|
s_getreg_b32 s2, hwreg(HW_REG_SHADER_CYCLES, 0, 20)
|
|
s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
s_waitcnt_vscnt null, 0x0
|
|
s_barrier
|
|
s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
s_waitcnt_vscnt null, 0x0
|
|
buffer_gl0_inv
|
|
s_getreg_b32 s3, hwreg(HW_REG_SHADER_CYCLES, 0, 20)
|
|
s_delay_alu instid0(SALU_CYCLE_1) | instskip(SKIP_1) | instid1(SALU_CYCLE_1)
|
|
s_sub_u32 s4, s3, s2
|
|
s_subb_u32 s5, 0, 0
|
|
v_cmp_lt_i64_e64 s3, s[4:5], s[0:1]
|
|
s_delay_alu instid0(VALU_DEP_1)
|
|
s_and_b32 vcc_lo, exec_lo, s3
|
|
s_cbranch_vccnz 65520
|
|
s_endpgm
|