[Patch v11 10/10] perf tests: Add SIMD registers sampling test
From: Dapeng Mi
Date: Sun Sep 13 2026 - 21:49:02 EST
Validate that SIMD registers (XMM/YMM/ZMM/OPMASK on x86) can be sampled
correctly with hardware support.
Signed-off-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
---
tools/perf/tests/shell/record.sh | 138 +++++++++++++++++++++++++++++++
1 file changed, 138 insertions(+)
diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index 770a546f8d45..4a4931cb5ba9 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -249,6 +249,143 @@ test_extd_register_capture() {
echo "Extended register capture test [Success]"
}
+extract_x86_advertised_simd_classes() {
+ local regs_output="$1"
+
+ echo "${regs_output}" \
+ | grep -oE '(ZMM|YMM|XMM|OPMASK)[0-9]+-[0-9]+' \
+ | sed -E 's/[0-9]+-[0-9]+$//' \
+ | tr '[:upper:]' '[:lower:]' \
+ | sort -u
+}
+
+ordered_x86_simd_classes() {
+ local advertised_classes="$1"
+ local simd_classes=""
+
+ if echo "${advertised_classes}" | grep -qw zmm
+ then
+ simd_classes="${simd_classes} zmm"
+ fi
+ if echo "${advertised_classes}" | grep -qw ymm
+ then
+ simd_classes="${simd_classes} ymm"
+ fi
+ if echo "${advertised_classes}" | grep -qw xmm
+ then
+ simd_classes="${simd_classes} xmm"
+ fi
+ if echo "${advertised_classes}" | grep -qw opmask
+ then
+ simd_classes="${simd_classes} opmask"
+ fi
+
+ echo "${simd_classes}" | xargs
+}
+
+check_simd_reg_capture() {
+ local script_field="$1"
+ local simd_reg="$2"
+
+ perf script -F ip,sym,"${script_field}" -i "${perfdata}" 2>/dev/null | \
+ grep -q -i "${simd_reg}\["
+}
+
+validate_simd_regs_sampling() {
+ local regs_opt="$1"
+ local simd_classes="$2"
+ local script_field="$3"
+ local simd_class
+ local ret=0
+
+ for simd_class in ${simd_classes}
+ do
+ perf_record_with_retry "${perfdata}" \
+ "check_simd_reg_capture ${script_field} ${simd_class}" "perf test -w thloop" \
+ -e br_inst_retired.near_call ${regs_opt}=${simd_class} -c 1000 \
+ --per-thread || ret=$?
+
+ if [ $ret -ne 0 ]
+ then
+ echo "SIMD register capture test [Failed record ${regs_opt}=${simd_class}]"
+ return 1
+ fi
+ done
+
+ return 0
+}
+
+test_simd_register_capture() {
+ local arch
+ local intr_regs
+ local user_regs
+ local simd_classes
+ local user_simd_classes
+ local advertised_intr_classes
+ local advertised_user_classes
+ local tested=0
+
+ echo "SIMD register capture test"
+ if ! perf list pmu | grep -q 'br_inst_retired.near_call'
+ then
+ echo "SIMD register capture test [Skipped missing event]"
+ return
+ fi
+
+ intr_regs=$(perf record --intr-regs=\? 2>&1 || true)
+ user_regs=$(perf record --user-regs=\? 2>&1 || true)
+
+ simd_classes=""
+ user_simd_classes=""
+
+ arch=$(uname -m)
+ case ${arch} in
+ x86_64|i386)
+ advertised_intr_classes=$(extract_x86_advertised_simd_classes "${intr_regs}")
+ advertised_user_classes=$(extract_x86_advertised_simd_classes "${user_regs}")
+
+ simd_classes=$(ordered_x86_simd_classes "${advertised_intr_classes}")
+ user_simd_classes=$(ordered_x86_simd_classes "${advertised_user_classes}")
+ ;;
+ *)
+ echo "SIMD register capture test [Skipped non-x86 platform]"
+ return
+ ;;
+ esac
+
+ if [ -z "${simd_classes}" ]
+ then
+ echo "SIMD register capture test [Skipped missing intr SIMD registers]"
+ elif ! validate_simd_regs_sampling "--intr-regs" "${simd_classes}" "iregs"
+ then
+ echo "SIMD register capture test [Failed intr SIMD register sampling]"
+ err=1
+ return
+ else
+ tested=1
+ fi
+
+ if [ -z "${user_simd_classes}" ]
+ then
+ echo "SIMD register capture test [Skipped missing user SIMD registers]"
+ elif ! validate_simd_regs_sampling "--user-regs" "${user_simd_classes}" "uregs"
+ then
+ echo "SIMD register capture test [Failed user SIMD register sampling]"
+ err=1
+ return
+ else
+ tested=1
+ fi
+
+ if [ ${tested} -eq 0 ]
+ then
+ echo "SIMD register capture test [Skipped missing SIMD registers]"
+ return
+ fi
+
+ echo "SIMD register capture test [Success]"
+}
+
test_system_wide() {
echo "Basic --system-wide mode test"
local ret=0
@@ -610,6 +747,7 @@ fi
test_per_thread
test_register_capture
test_extd_register_capture
+test_simd_register_capture
test_system_wide
test_workload
test_branch_counter
--
2.34.1