public inbox for intel-gfx@lists.freedesktop.org
 help / color / mirror / Atom feed
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
To: <intel-gfx@lists.freedesktop.org>,
	Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>,
	Ashutosh Dixit <ashutosh.dixit@intel.com>
Subject: Re: [Intel-gfx] [PATCH 5/6] drm/i915/pmu: Prepare for multi-tile non-engine counters
Date: Mon, 8 May 2023 11:07:18 -0700	[thread overview]
Message-ID: <ZFk6Vmb5X4CYtGoI@orsosgc001.jf.intel.com> (raw)
In-Reply-To: <20230506005816.1891043-6-umesh.nerlige.ramappa@intel.com>

On Fri, May 05, 2023 at 05:58:15PM -0700, Umesh Nerlige Ramappa wrote:
>From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>
>Reserve some bits in the counter config namespace which will carry the
>tile id and prepare the code to handle this.
>
>No per tile counters have been added yet.
>
>v2:
>- Fix checkpatch issues
>- Use 4 bits for gt id in non-engine counters. Drop FIXME.
>- Set MAX GTs to 4. Drop FIXME.

I touched this one, so cannot review it. Also a reminder to myself to 
add the UMD changes (intel_gpu_top) link here.

Umesh

>
>Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
>---
> drivers/gpu/drm/i915/i915_pmu.c | 150 +++++++++++++++++++++++---------
> drivers/gpu/drm/i915/i915_pmu.h |   9 +-
> include/uapi/drm/i915_drm.h     |  17 +++-
> 3 files changed, 129 insertions(+), 47 deletions(-)
>
>diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
>index 669a42e44082..12b2f3169abf 100644
>--- a/drivers/gpu/drm/i915/i915_pmu.c
>+++ b/drivers/gpu/drm/i915/i915_pmu.c
>@@ -56,11 +56,21 @@ static bool is_engine_config(u64 config)
> 	return config < __I915_PMU_OTHER(0);
> }
>
>+static unsigned int config_gt_id(const u64 config)
>+{
>+	return config >> __I915_PMU_GT_SHIFT;
>+}
>+
>+static u64 config_counter(const u64 config)
>+{
>+	return config & ~(~0ULL << __I915_PMU_GT_SHIFT);
>+}
>+
> static unsigned int other_bit(const u64 config)
> {
> 	unsigned int val;
>
>-	switch (config) {
>+	switch (config_counter(config)) {
> 	case I915_PMU_ACTUAL_FREQUENCY:
> 		val =  __I915_PMU_ACTUAL_FREQUENCY_ENABLED;
> 		break;
>@@ -78,15 +88,20 @@ static unsigned int other_bit(const u64 config)
> 		return -1;
> 	}
>
>-	return I915_ENGINE_SAMPLE_COUNT + val;
>+	return I915_ENGINE_SAMPLE_COUNT +
>+	       config_gt_id(config) * __I915_PMU_TRACKED_EVENT_COUNT +
>+	       val;
> }
>
> static unsigned int config_bit(const u64 config)
> {
>-	if (is_engine_config(config))
>+	if (is_engine_config(config)) {
>+		GEM_BUG_ON(config_gt_id(config));
>+
> 		return engine_config_sample(config);
>-	else
>+	} else {
> 		return other_bit(config);
>+	}
> }
>
> static u64 config_mask(u64 config)
>@@ -104,6 +119,18 @@ static unsigned int event_bit(struct perf_event *event)
> 	return config_bit(event->attr.config);
> }
>
>+static u64 frequency_enabled_mask(void)
>+{
>+	unsigned int i;
>+	u64 mask = 0;
>+
>+	for (i = 0; i < I915_PMU_MAX_GTS; i++)
>+		mask |= config_mask(__I915_PMU_ACTUAL_FREQUENCY(i)) |
>+			config_mask(__I915_PMU_REQUESTED_FREQUENCY(i));
>+
>+	return mask;
>+}
>+
> static bool pmu_needs_timer(struct i915_pmu *pmu, bool gpu_active)
> {
> 	struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu);
>@@ -120,9 +147,7 @@ static bool pmu_needs_timer(struct i915_pmu *pmu, bool gpu_active)
> 	 * Mask out all the ones which do not need the timer, or in
> 	 * other words keep all the ones that could need the timer.
> 	 */
>-	enable &= config_mask(I915_PMU_ACTUAL_FREQUENCY) |
>-		  config_mask(I915_PMU_REQUESTED_FREQUENCY) |
>-		  ENGINE_SAMPLE_MASK;
>+	enable &= frequency_enabled_mask() | ENGINE_SAMPLE_MASK;
>
> 	/*
> 	 * When the GPU is idle per-engine counters do not need to be
>@@ -164,9 +189,37 @@ static inline s64 ktime_since_raw(const ktime_t kt)
> 	return ktime_to_ns(ktime_sub(ktime_get_raw(), kt));
> }
>
>+static unsigned int
>+__sample_idx(struct i915_pmu *pmu, unsigned int gt_id, int sample)
>+{
>+	unsigned int idx = gt_id * __I915_NUM_PMU_SAMPLERS + sample;
>+
>+	GEM_BUG_ON(idx >= ARRAY_SIZE(pmu->sample));
>+
>+	return idx;
>+}
>+
>+static u64 read_sample(struct i915_pmu *pmu, unsigned int gt_id, int sample)
>+{
>+	return pmu->sample[__sample_idx(pmu, gt_id, sample)].cur;
>+}
>+
>+static void
>+store_sample(struct i915_pmu *pmu, unsigned int gt_id, int sample, u64 val)
>+{
>+	pmu->sample[__sample_idx(pmu, gt_id, sample)].cur = val;
>+}
>+
>+static void
>+add_sample_mult(struct i915_pmu *pmu, unsigned int gt_id, int sample, u32 val, u32 mul)
>+{
>+	pmu->sample[__sample_idx(pmu, gt_id, sample)].cur += mul_u32_u32(val, mul);
>+}
>+
> static u64 get_rc6(struct intel_gt *gt)
> {
> 	struct drm_i915_private *i915 = gt->i915;
>+	const unsigned int gt_id = gt->info.id;
> 	struct i915_pmu *pmu = &i915->pmu;
> 	unsigned long flags;
> 	bool awake = false;
>@@ -181,7 +234,7 @@ static u64 get_rc6(struct intel_gt *gt)
> 	spin_lock_irqsave(&pmu->lock, flags);
>
> 	if (awake) {
>-		pmu->sample[__I915_SAMPLE_RC6].cur = val;
>+		store_sample(pmu, gt_id, __I915_SAMPLE_RC6, val);
> 	} else {
> 		/*
> 		 * We think we are runtime suspended.
>@@ -190,14 +243,14 @@ static u64 get_rc6(struct intel_gt *gt)
> 		 * on top of the last known real value, as the approximated RC6
> 		 * counter value.
> 		 */
>-		val = ktime_since_raw(pmu->sleep_last);
>-		val += pmu->sample[__I915_SAMPLE_RC6].cur;
>+		val = ktime_since_raw(pmu->sleep_last[gt_id]);
>+		val += read_sample(pmu, gt_id, __I915_SAMPLE_RC6);
> 	}
>
>-	if (val < pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur)
>-		val = pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur;
>+	if (val < read_sample(pmu, gt_id, __I915_SAMPLE_RC6_LAST_REPORTED))
>+		val = read_sample(pmu, gt_id, __I915_SAMPLE_RC6_LAST_REPORTED);
> 	else
>-		pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur = val;
>+		store_sample(pmu, gt_id, __I915_SAMPLE_RC6_LAST_REPORTED, val);
>
> 	spin_unlock_irqrestore(&pmu->lock, flags);
>
>@@ -207,13 +260,20 @@ static u64 get_rc6(struct intel_gt *gt)
> static void init_rc6(struct i915_pmu *pmu)
> {
> 	struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu);
>-	intel_wakeref_t wakeref;
>+	struct intel_gt *gt;
>+	unsigned int i;
>+
>+	for_each_gt(gt, i915, i) {
>+		intel_wakeref_t wakeref;
>
>-	with_intel_runtime_pm(to_gt(i915)->uncore->rpm, wakeref) {
>-		pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(to_gt(i915));
>-		pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur =
>-					pmu->sample[__I915_SAMPLE_RC6].cur;
>-		pmu->sleep_last = ktime_get_raw();
>+		with_intel_runtime_pm(gt->uncore->rpm, wakeref) {
>+			u64 val = __get_rc6(gt);
>+
>+			store_sample(pmu, i, __I915_SAMPLE_RC6, val);
>+			store_sample(pmu, i, __I915_SAMPLE_RC6_LAST_REPORTED,
>+				     val);
>+			pmu->sleep_last[i] = ktime_get_raw();
>+		}
> 	}
> }
>
>@@ -221,8 +281,8 @@ static void park_rc6(struct intel_gt *gt)
> {
> 	struct i915_pmu *pmu = &gt->i915->pmu;
>
>-	pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(gt);
>-	pmu->sleep_last = ktime_get_raw();
>+	store_sample(pmu, gt->info.id, __I915_SAMPLE_RC6, __get_rc6(gt));
>+	pmu->sleep_last[gt->info.id] = ktime_get_raw();
> }
>
> static void __i915_pmu_maybe_start_timer(struct i915_pmu *pmu)
>@@ -362,34 +422,30 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
> 	}
> }
>
>-static void
>-add_sample_mult(struct i915_pmu_sample *sample, u32 val, u32 mul)
>-{
>-	sample->cur += mul_u32_u32(val, mul);
>-}
>-
>-static bool frequency_sampling_enabled(struct i915_pmu *pmu)
>+static bool
>+frequency_sampling_enabled(struct i915_pmu *pmu, unsigned int gt)
> {
> 	return pmu->enable &
>-	       (config_mask(I915_PMU_ACTUAL_FREQUENCY) |
>-		config_mask(I915_PMU_REQUESTED_FREQUENCY));
>+	       (config_mask(__I915_PMU_ACTUAL_FREQUENCY(gt)) |
>+		config_mask(__I915_PMU_REQUESTED_FREQUENCY(gt)));
> }
>
> static void
> frequency_sample(struct intel_gt *gt, unsigned int period_ns)
> {
> 	struct drm_i915_private *i915 = gt->i915;
>+	const unsigned int gt_id = gt->info.id;
> 	struct i915_pmu *pmu = &i915->pmu;
> 	struct intel_rps *rps = &gt->rps;
>
>-	if (!frequency_sampling_enabled(pmu))
>+	if (!frequency_sampling_enabled(pmu, gt_id))
> 		return;
>
> 	/* Report 0/0 (actual/requested) frequency while parked. */
> 	if (!intel_gt_pm_get_if_awake(gt))
> 		return;
>
>-	if (pmu->enable & config_mask(I915_PMU_ACTUAL_FREQUENCY)) {
>+	if (pmu->enable & config_mask(__I915_PMU_ACTUAL_FREQUENCY(gt_id))) {
> 		u32 val;
>
> 		/*
>@@ -405,12 +461,12 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns)
> 		if (!val)
> 			val = intel_gpu_freq(rps, rps->cur_freq);
>
>-		add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_ACT],
>+		add_sample_mult(pmu, gt_id, __I915_SAMPLE_FREQ_ACT,
> 				val, period_ns / 1000);
> 	}
>
>-	if (pmu->enable & config_mask(I915_PMU_REQUESTED_FREQUENCY)) {
>-		add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_REQ],
>+	if (pmu->enable & config_mask(__I915_PMU_REQUESTED_FREQUENCY(gt_id))) {
>+		add_sample_mult(pmu, gt_id, __I915_SAMPLE_FREQ_REQ,
> 				intel_rps_get_requested_frequency(rps),
> 				period_ns / 1000);
> 	}
>@@ -447,9 +503,7 @@ static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer)
> 			continue;
>
> 		engines_sample(gt, period_ns);
>-
>-		if (i == 0) /* FIXME */
>-			frequency_sample(gt, period_ns);
>+		frequency_sample(gt, period_ns);
> 	}
>
> 	hrtimer_forward(hrtimer, now, ns_to_ktime(PERIOD));
>@@ -491,7 +545,12 @@ config_status(struct drm_i915_private *i915, u64 config)
> {
> 	struct intel_gt *gt = to_gt(i915);
>
>-	switch (config) {
>+	unsigned int gt_id = config_gt_id(config);
>+
>+	if (gt_id)
>+		return -ENOENT;
>+
>+	switch (config_counter(config)) {
> 	case I915_PMU_ACTUAL_FREQUENCY:
> 		if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
> 			/* Requires a mutex for sampling! */
>@@ -599,22 +658,27 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
> 			val = engine->pmu.sample[sample].cur;
> 		}
> 	} else {
>-		switch (event->attr.config) {
>+		const unsigned int gt_id = config_gt_id(event->attr.config);
>+		const u64 config = config_counter(event->attr.config);
>+
>+		switch (config) {
> 		case I915_PMU_ACTUAL_FREQUENCY:
> 			val =
>-			   div_u64(pmu->sample[__I915_SAMPLE_FREQ_ACT].cur,
>+			   div_u64(read_sample(pmu, gt_id,
>+					       __I915_SAMPLE_FREQ_ACT),
> 				   USEC_PER_SEC /* to MHz */);
> 			break;
> 		case I915_PMU_REQUESTED_FREQUENCY:
> 			val =
>-			   div_u64(pmu->sample[__I915_SAMPLE_FREQ_REQ].cur,
>+			   div_u64(read_sample(pmu, gt_id,
>+					       __I915_SAMPLE_FREQ_REQ),
> 				   USEC_PER_SEC /* to MHz */);
> 			break;
> 		case I915_PMU_INTERRUPTS:
> 			val = READ_ONCE(pmu->irq_count);
> 			break;
> 		case I915_PMU_RC6_RESIDENCY:
>-			val = get_rc6(to_gt(i915));
>+			val = get_rc6(i915->gt[gt_id]);
> 			break;
> 		case I915_PMU_SOFTWARE_GT_AWAKE_TIME:
> 			val = ktime_to_ns(intel_gt_get_awake_time(to_gt(i915)));
>diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h
>index 3a811266ac6a..d47846f21ddf 100644
>--- a/drivers/gpu/drm/i915/i915_pmu.h
>+++ b/drivers/gpu/drm/i915/i915_pmu.h
>@@ -38,13 +38,16 @@ enum {
> 	__I915_NUM_PMU_SAMPLERS
> };
>
>+#define I915_PMU_MAX_GTS (4)
>+
> /*
>  * How many different events we track in the global PMU mask.
>  *
>  * It is also used to know to needed number of event reference counters.
>  */
> #define I915_PMU_MASK_BITS \
>-	(I915_ENGINE_SAMPLE_COUNT + __I915_PMU_TRACKED_EVENT_COUNT)
>+	(I915_ENGINE_SAMPLE_COUNT + \
>+	 I915_PMU_MAX_GTS * __I915_PMU_TRACKED_EVENT_COUNT)
>
> #define I915_ENGINE_SAMPLE_COUNT (I915_SAMPLE_SEMA + 1)
>
>@@ -124,11 +127,11 @@ struct i915_pmu {
> 	 * Only global counters are held here, while the per-engine ones are in
> 	 * struct intel_engine_cs.
> 	 */
>-	struct i915_pmu_sample sample[__I915_NUM_PMU_SAMPLERS];
>+	struct i915_pmu_sample sample[I915_PMU_MAX_GTS * __I915_NUM_PMU_SAMPLERS];
> 	/**
> 	 * @sleep_last: Last time GT parked for RC6 estimation.
> 	 */
>-	ktime_t sleep_last;
>+	ktime_t sleep_last[I915_PMU_MAX_GTS];
> 	/**
> 	 * @irq_count: Number of interrupts
> 	 *
>diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
>index dba7c5a5b25e..d5ac1fdeb2b1 100644
>--- a/include/uapi/drm/i915_drm.h
>+++ b/include/uapi/drm/i915_drm.h
>@@ -280,7 +280,16 @@ enum drm_i915_pmu_engine_sample {
> #define I915_PMU_ENGINE_SEMA(class, instance) \
> 	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA)
>
>-#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x))
>+/*
>+ * Top 4 bits of every non-engine counter are GT id.
>+ */
>+#define __I915_PMU_GT_SHIFT (60)
>+
>+#define ___I915_PMU_OTHER(gt, x) \
>+	(((__u64)__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x)) | \
>+	((__u64)(gt) << __I915_PMU_GT_SHIFT))
>+
>+#define __I915_PMU_OTHER(x) ___I915_PMU_OTHER(0, x)
>
> #define I915_PMU_ACTUAL_FREQUENCY	__I915_PMU_OTHER(0)
> #define I915_PMU_REQUESTED_FREQUENCY	__I915_PMU_OTHER(1)
>@@ -290,6 +299,12 @@ enum drm_i915_pmu_engine_sample {
>
> #define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY
>
>+#define __I915_PMU_ACTUAL_FREQUENCY(gt)		___I915_PMU_OTHER(gt, 0)
>+#define __I915_PMU_REQUESTED_FREQUENCY(gt)	___I915_PMU_OTHER(gt, 1)
>+#define __I915_PMU_INTERRUPTS(gt)		___I915_PMU_OTHER(gt, 2)
>+#define __I915_PMU_RC6_RESIDENCY(gt)		___I915_PMU_OTHER(gt, 3)
>+#define __I915_PMU_SOFTWARE_GT_AWAKE_TIME(gt)	___I915_PMU_OTHER(gt, 4)
>+
> /* Each region is a minimum of 16k, and there are at most 255 of them.
>  */
> #define I915_NR_TEX_REGIONS 255	/* table size 2k - maximum due to use
>-- 
>2.36.1
>

  reply	other threads:[~2023-05-08 18:08 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-06  0:58 [Intel-gfx] [PATCH 0/6] Add MTL PMU support for multi-gt Umesh Nerlige Ramappa
2023-05-06  0:58 ` [Intel-gfx] [PATCH 1/6] drm/i915/pmu: Support PMU for all engines Umesh Nerlige Ramappa
2023-05-08 17:52   ` Umesh Nerlige Ramappa
2023-05-09 12:26     ` Tvrtko Ursulin
2023-05-06  0:58 ` [Intel-gfx] [PATCH 2/6] drm/i915/pmu: Skip sampling engines with no enabled counters Umesh Nerlige Ramappa
2023-05-08 17:53   ` Umesh Nerlige Ramappa
2023-05-06  0:58 ` [Intel-gfx] [PATCH 3/6] drm/i915/pmu: Transform PMU parking code to be GT based Umesh Nerlige Ramappa
2023-05-08 17:55   ` Umesh Nerlige Ramappa
2023-05-09 15:10     ` Umesh Nerlige Ramappa
2023-05-06  0:58 ` [Intel-gfx] [PATCH 4/6] drm/i915/pmu: Add reference counting to the sampling timer Umesh Nerlige Ramappa
2023-05-08 17:58   ` Umesh Nerlige Ramappa
2023-05-09 17:25   ` Dixit, Ashutosh
2023-05-10  6:02     ` Dixit, Ashutosh
2023-05-12 22:29   ` Dixit, Ashutosh
2023-05-12 22:44     ` Umesh Nerlige Ramappa
2023-05-12 23:20       ` Dixit, Ashutosh
2023-05-12 23:44         ` Umesh Nerlige Ramappa
2023-05-15  9:52           ` Tvrtko Ursulin
2023-05-15 21:24             ` Dixit, Ashutosh
2023-05-16  7:12               ` Tvrtko Ursulin
2023-05-16 16:29                 ` Dixit, Ashutosh
2023-05-06  0:58 ` [Intel-gfx] [PATCH 5/6] drm/i915/pmu: Prepare for multi-tile non-engine counters Umesh Nerlige Ramappa
2023-05-08 18:07   ` Umesh Nerlige Ramappa [this message]
2023-05-12  1:08   ` Dixit, Ashutosh
2023-05-12 10:56     ` Tvrtko Ursulin
2023-05-12 20:57       ` Umesh Nerlige Ramappa
2023-05-12 22:37         ` Umesh Nerlige Ramappa
2023-05-13  1:09         ` Dixit, Ashutosh
2023-05-15 10:10         ` Tvrtko Ursulin
2023-05-15 22:07           ` Dixit, Ashutosh
2023-05-16  8:35             ` Tvrtko Ursulin
2023-05-06  0:58 ` [Intel-gfx] [PATCH 6/6] drm/i915/pmu: Export counters from all tiles Umesh Nerlige Ramappa
2023-05-08 18:08   ` Umesh Nerlige Ramappa
2023-05-09 12:38   ` Tvrtko Ursulin
2023-05-11 18:57   ` Dixit, Ashutosh
2023-05-12 10:57     ` Tvrtko Ursulin
2023-05-12 17:08       ` Dixit, Ashutosh
2023-05-12 18:53         ` Umesh Nerlige Ramappa
2023-05-12 20:10           ` Dixit, Ashutosh
2023-05-06  2:20 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Add MTL PMU support for multi-gt (rev2) Patchwork
2023-05-06  2:21 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2023-05-06  2:38 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
  -- strict thread matches above, loose matches on Subject: below --
2023-05-13  1:55 [Intel-gfx] [PATCH 0/6] Add MTL PMU support for multi-gt Umesh Nerlige Ramappa
2023-05-13  1:55 ` [Intel-gfx] [PATCH 5/6] drm/i915/pmu: Prepare for multi-tile non-engine counters Umesh Nerlige Ramappa
2023-05-13  4:41   ` Dixit, Ashutosh
2023-05-15  6:16     ` Umesh Nerlige Ramappa
2023-05-15  6:44 [Intel-gfx] [PATCH v4 0/6] Add MTL PMU support for multi-gt Umesh Nerlige Ramappa
2023-05-15  6:44 ` [Intel-gfx] [PATCH 5/6] drm/i915/pmu: Prepare for multi-tile non-engine counters Umesh Nerlige Ramappa
2023-05-15 10:12   ` Tvrtko Ursulin
2023-05-15 18:39     ` Umesh Nerlige Ramappa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=ZFk6Vmb5X4CYtGoI@orsosgc001.jf.intel.com \
    --to=umesh.nerlige.ramappa@intel.com \
    --cc=ashutosh.dixit@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=tvrtko.ursulin@linux.intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox