Update slides

presenter_demo/Makefile

@@ -6,17 +6,24 @@ all:	presenter_demo.dsk
 
 presenter_demo.dsk:	PRESENTER_DEMO \
 	TITLE.HGR PLASMA_DPOSV.HGR \
-	RAPL_MICRO.HGR \
+	RAPL_MICRO.HGR WATTSUP.HGR \
-	NUM.SHAPE MMM
+	NUM.SHAPE MMM LOAD_DEMO
 	../dos33 presenter_demo.dsk SAVE A PRESENTER_DEMO
 	../dos33 presenter_demo.dsk SAVE B TITLE.HGR
 	../dos33 presenter_demo.dsk SAVE B PLASMA_DPOSV.HGR
 	../dos33 presenter_demo.dsk SAVE B RAPL_MICRO.HGR
 	../dos33 presenter_demo.dsk SAVE B NUM.SHAPE
+	../dos33 presenter_demo.dsk SAVE B WATTSUP.HGR
 	../dos33 presenter_demo.dsk SAVE A MMM
+	../dos33 presenter_demo.dsk SAVE A LOAD_DEMO
 
+LOAD_DEMO:	load_demo.bas
+	../tokenize_asoft < load_demo.bas > LOAD_DEMO
 
-RAPL_MICRO.HGR:	rapl_micro.pcx
+WATTSUP.HGR:		wattsup.pcx
+	../pcx2hgr wattsup.pcx > WATTSUP.HGR
+
+RAPL_MICRO.HGR:		rapl_micro.pcx
 	../pcx2hgr rapl_micro.pcx > RAPL_MICRO.HGR
 
 
@@ -39,5 +46,5 @@ demo.bas:		../asoft_presenter info
 	../asoft_presenter . > demo.bas
 
 clean:	
-	rm -f *~ *.IMG *.HGR demo.bas PRESENTER_DEMO NUM.SHAPE MMM
+	rm -f *~ *.IMG *.HGR demo.bas PRESENTER_DEMO NUM.SHAPE MMM LOAD_DEMO
 

presenter_demo/info

@@ -8,12 +8,36 @@ EMAIL
 vweaver1@eecs.utk.edu
 
 SLIDES
-slide_nvml_plot
-slide_wattsup_plot
-slide_rapl_intro
-slide_piotr_img
-slide_rapl_continued
-slide_rapl_more
-slide_rapl_finish
 slide_title
+slide_01_intro
+slide_02_intro
+slide_03_piotr
+slide_04_shortcomings
+slide_05_papi
+slide_06_papi_benefits
+slide_07_current_components
+slide_08_wattsup_pic
+slide_09_wattsup
+slide_10_wattsup_plot
+slide_11_rapl_intro
+slide_12_rapl_works
+slide_13_rapl_more
+slide_14_rapl_valid
+slide_15_rapl_accuracy
+slide_16_rapl_papi
+slide_17_rapl_power
+slide_18_rapl_energy
+slide_19_nvml
+slide_20_nvml_plot
+slide_21_future_papi
+slide_22_amd
+slide_23_powermon
+slide_24_user
+slide_25_measuring
+slide_26_events
+slide_27_multiple
+slide_28_questions
+slide_29_appleIIe
+slide_30_linpack
+slide_31_questions
 END_SLIDES

presenter_demo/load_demo.bas

@@ -0,0 +1,5 @@
+10 REM LOAD BASIC PROGRAM INTO HGR2 AREA
+15 PRINT "LOADING PRESENTER DEMO TO A$4000"
+20 POKE 104,64
+30 POKE 16384,0
+40 PRINT CHR$(4);"LOAD PRESENTER_DEMO"

presenter_demo/slide_01_intro

@@ -0,0 +1,11 @@
+40COL
+%c%Power and Energy - Why do We Care?
+
+* New, massive, HPC machines use 
+  impressive amounts of power 
+
+* When you have 100k+ cores, saving 
+  a few Joules per core quickly adds up
+
+* To improve power/energy draw, you 
+  need some way of measuring it

presenter_demo/slide_02_intro

@@ -0,0 +1,18 @@
+40COL
+%c%Energy/Power Measurement is Already 
+%c%Possible
+
+Three common ways of doing this:
+
+* Hand-instrumenting a system by 
+  tapping all power inputs to CPU, 
+  memory, disk, etc., and using a 
+  data logger
+  
+* Using a pass-through power meter 
+  that you plug your server into.
+  Often these will log over USB
+      
+* Estimating power/energy with a 
+  software model based on
+  system behavior

presenter_demo/slide_03_piotr

@@ -0,0 +1,5 @@
+HGR
+PLASMA_DPOSV.HGR
+%c%Existing Related Work
+%c%Plasma/dposv results with 
+%c%Virginia Tech's PowerPack

presenter_demo/slide_04_shortcomings

@@ -0,0 +1,14 @@
+40COL
+%c%Shortcomings of Current Methods
+
+* Each measurement platform has a 
+  different interface
+
+* Typically data can only be recorded
+  off-line, to a separate logging
+  machine, and analysis is done after 
+  the fact
+
+* Correlating energy/power with other 
+  performance metrics can be difficult
+

presenter_demo/slide_05_papi

@@ -0,0 +1,15 @@
+40COL
+%c%Can we make this easier?
+
+%c%Use PAPI!
+
+* PAPI (Performance API) is a 
+  platform-independent library for
+  gathering performance-related data
+
+* PAPI-C interface makes adding new
+  power measuring components 
+  straightforward
+
+* PAPI can provide power/energy 
+  results in-line to running programs

presenter_demo/slide_06_papi_benefits

@@ -0,0 +1,16 @@
+40COL
+%c%More PAPI benefits
+
+* One interface for all power 
+  measurement devices
+
+* Existing PAPI code and  
+  instrumentation can easily be 
+  extended to measure power
+
+* Existing high-level tools (Tau, 
+  VAMPIR, etc.) can be used with 
+  no changes
+
+* Easy to measure other performance 
+  metrics at same time

presenter_demo/slide_07_current_components

@@ -0,0 +1,8 @@
+40COL
+%c%Current PAPI Components
+
+* Various components are nearing 
+  completion
+
+* Code for many of them already 
+  available in papi.git

presenter_demo/slide_08_wattsup_pic

@@ -0,0 +1,3 @@
+HGR
+WATTSUP.HGR
+%c%Watt's Up Pro Meter

presenter_demo/slide_09_wattsup

@@ -0,0 +1,14 @@
+40COL
+%c%Watt's Up Pro Features
+
+* Can measure 18 different values 
+  with 1 second resolution
+  (Watts, Volts, Amps, etc.)
+
+* Values read over USB
+
+* Joules can be derived from power
+  and time
+
+* Can only measure system-wide
+

presenter_demo/slide_10_wattsup_plot

@@ -61,6 +61,6 @@ START
 38 35.4
 39 35.1
 STOP
-    Average Power (W) versus Time (s)
+%c%Average Power (W) versus Time (s)
 
-     PLASMA Cholesky on Intel Core2
+%c%PLASMA Cholesky on Intel Core2

presenter_demo/slide_11_rapl_intro

@@ -0,0 +1,12 @@
+40COL
+%c%RAPL
+
+* Running Average Power Limit
+
+* Part of an infrastructure to allow
+  setting custom  per-package hardware
+  enforced power limits
+
+* User Accessible Energy/Power 
+  readings are a bonus feature
+  of the interface

presenter_demo/slide_12_rapl_works

@@ -0,0 +1,17 @@
+40COL
+%c%How RAPL Works
+
+* RAPL is not an analog power meter
+
+* RAPL uses a software power model, 
+  running on a helper controller
+  on the main chip package
+
+* Energy is estimated using various 
+  hardware performance counters, 
+  temperature, leakage models and I/O
+
+* The model is used for CPU throttling
+  and turbo-boost, but the values are 
+  also exposed to users via a 
+  model-specific register (MSR)

presenter_demo/slide_13_rapl_more

@@ -0,0 +1,18 @@
+40COL
+%c%Available RAPL Readings
+
+* PACKAGE_ENERGY: total energy used 
+  by entire package
+
+* PP0_ENERGY: energy used by 
+  'Power Plane 0' which includes 
+  all cores and caches
+
+* PP1_ENERGY: on original Sandybridge
+  this includes the on-chip Intel GPU
+
+* DRAM_ENERGY: on Sandybridge EP this 
+  measures DRAM energy usage.  
+  It is unclear whether this is just 
+  the interface or if it includes all 
+  power used by all the DIMMs too

presenter_demo/slide_14_rapl_valid

@@ -0,0 +1,4 @@
+HGR
+RAPL_MICRO.HGR
+%c%Rotem at al. (IEEE Micro Mar/Apr 2012)
+%c%Validate Against Actual Power Readings

presenter_demo/slide_15_rapl_accuracy

@@ -0,0 +1,19 @@
+40COL
+%c%RAPL Measurement Accuracy
+
+* Intel Documentation indicates Energy
+  readings are updated roughly every 
+  millisecond (1kHz)
+
+* The hardware also reports measurement
+  quanta. This can vary among processor
+  releases. On our Sandybridge EP all 
+  Energy measurements are in multiples 
+  of 15.2nJ
+
+* Power and Energy can vary between 
+  identical packages on a system, 
+  even when running identical workloads.  
+  It is unclear whether this is due to 
+  process variation or else calibration
+

presenter_demo/slide_16_rapl_papi

@@ -0,0 +1,17 @@
+40COL
+%c%RAPL PAPI Interface
+
+* Access to RAPL data requires reading
+  a CPU MSR register.  
+  This requires OS support
+
+* Linux currently has no driver and 
+  likely won't for the near future
+
+* Linux does support an 'MSR' driver.  
+  Given proper read permissions, MSRs 
+  can be accessed via /dev/cpu/*/msr
+
+* PAPI uses the 'MSR' driver to gather 
+  RAPL values
+

presenter_demo/slide_17_rapl_power

@@ -0,0 +1,3 @@
+40COL
+BLAH
+

presenter_demo/slide_18_rapl_energy

@@ -0,0 +1,3 @@
+40COL
+BLAH
+

presenter_demo/slide_19_nvml

@@ -0,0 +1,13 @@
+40COL
+%c%NVML
+
+* Recent NVIDIA GPUs support reading 
+  power via the NVIDIA Management 
+  Library (NVML)
+
+* On Fermi C2075 GPUs it has milliwatt
+  resolution within +/- 5W and is 
+  updated at roughly 60Hz
+
+* The power reported is that for the 
+  entire board, GPU and memory

presenter_demo/slide_20_nvml_plot

@@ -287,3 +287,4 @@ START
 2.66 122.18
 2.67 117.74
 STOP
+%c%MAGMA LU 10,000, Nvidia Fermi C2075

presenter_demo/slide_21_future_papi

@@ -0,0 +1,6 @@
+40COL
+%c%Near-future PAPI Components
+
+%c%These components do not exist yet,
+%c%but support for them should be 
+%c%straightforward.

presenter_demo/slide_22_amd

@@ -0,0 +1,14 @@
+40COL
+%c%AMD Application Power Management
+
+* Recent AMD Family 15h processors 
+  report 'Current Power In Watts' 
+  via Processor Power in the TDP MSR
+
+* Support for this can be provided 
+  similar to RAPL
+
+* We just need an Interlagos system 
+  where someone gives us read 
+  permissions to /dev/cpu/*/msr
+

presenter_demo/slide_23_powermon

@@ -0,0 +1,12 @@
+40COL
+%c%PowerMon 2
+
+* PowerMon 2: a custom board from RENCI
+
+* Plugs in-line with ATX power supply
+
+* Reports results over USB
+
+* 8 channels, 1kHz sample rate
+ 
+* We have hardware; still debugging

presenter_demo/slide_24_user

@@ -0,0 +1,14 @@
+40COL
+%c%PAPI-based Power Models
+
+* There's a lot of related work on 
+  estimating energy/power using
+  performance counters
+
+* PAPI user-defined events can be 
+  used to create power models using
+  existing events
+
+* Previous work (McKee et al.) shows 
+  accuracy to within 10%%
+

presenter_demo/slide_25_measuring

@@ -0,0 +1,7 @@
+40COL
+%c%Measuring using PAPI
+
+* Measuring Energy/Power with PAPI is 
+  done the same as measuring any other 
+  event
+

presenter_demo/slide_26_events

@@ -0,0 +1,19 @@
+40COL
+%c%Listing Events
+
+>  papi_native_avail
+...
+====================================
+ Events in Component: linux-rapl
+====================================
+------------------------------------
+| PACKAGE_ENERGY:PACKAGE0                                                      
+|   Energy used by chip package 0
+------------------------------------
+| PACKAGE_ENERGY:PACKAGE1           
+|   Energy used by chip package 1   
+------------------------------------
+| DRAM_ENERGY:PACKAGE0              
+|   Energy used by DRAM on package 0
+------------------------------------
+...

presenter_demo/slide_27_multiple

@@ -0,0 +1,4 @@
+40COL
+%c%Measuring Multiple at Once
+
+

presenter_demo/slide_28_questions

@@ -0,0 +1,7 @@
+40COL
+
+
+
+
+
+%c%Questions before Digressing?

presenter_demo/slide_29_appleIIe

@@ -0,0 +1,10 @@
+40COL
+%c%Apple IIe
+
+* Apple II released in 1977
+* Apple IIe Platinum released in 1987
+* 1MHz 65C02 Processor, 128kB RAM
+* 280x192, 6-color graphics 
+  (IIe can do DoubleHiRes)
+* Power: 18 - 20W
+

presenter_demo/slide_30_linpack

@@ -0,0 +1,12 @@
+40COL
+%c%Linpack Results
+
+10x10 Matrix-matrix multiply
+START
+STOP
+HOW MANY SECONDS? 15
+133.333333 FLOP/s
+
+Yes I know using BASIC is unfair
+But I am too lazy to code up a
+6502 FP implementation in assembler

presenter_demo/slide_31_questions

@@ -0,0 +1,7 @@
+40COL
+
+
+
+
+%c%QUESTIONS?
+

presenter_demo/slide_piotr_img

@@ -1,2 +0,0 @@
-HGR
-PLASMA_DPOSV.HGR

presenter_demo/slide_rapl_continued

@@ -1,3 +0,0 @@
-40COL
-RAPL CONTINUE
-* Is freally awesome

presenter_demo/slide_rapl_finish

@@ -1,3 +0,0 @@
-40COL
-RAPL LAST
-* Is really awesome

presenter_demo/slide_rapl_intro

@@ -1,4 +0,0 @@
-40COL
-#c#RAPL
-
-* Is really awesome

presenter_demo/slide_rapl_more

@@ -1,3 +0,0 @@
-40COL
-RAPL MORE
-* Is really awesome