diff --git a/chapters/5-Performance-Analysis-Approaches/5-9 Questions-Exercises.md b/chapters/5-Performance-Analysis-Approaches/5-9 Questions-Exercises.md
index 9b9ae6f907..1abd3aa976 100644
--- a/chapters/5-Performance-Analysis-Approaches/5-9 Questions-Exercises.md	
+++ b/chapters/5-Performance-Analysis-Approaches/5-9 Questions-Exercises.md	
@@ -7,8 +7,3 @@
 - scenario 4: there is a new shiny library that claims to be faster than the one you currently have integrated in your project; you've decided to compare their performance.
 - scenario 5: you were asked to analyze performance of an unfamiliar code; you want to know how frequently a certain branch is taken and how many iterations the loop is doing.
 2. Run the application that you're working with on a daily basis. Practice doing performance analysis using approaches we discussed in this chapter. Collect raw counts for various CPU performance events, find hotspots, collect roofline data, generate and study the compiler optimization report fot the hot function(s) in your program.
-
-[TODO]: Coding exercise?
-Coding exercise: write a microbenchmark that will demonstrate the effect of FMA unrolling.
-At the end of this chapter we offer you a coding exercise to write a microbenchmark that will demonstrate the effect we explored in this study.
-The main author of the book has done many experiments on this code with speedups ranging between 1.1x and 1.9x.
\ No newline at end of file
diff --git a/img/perf-analysis/FMA_tput_uica_orig.png b/img/perf-analysis/FMA_tput_uica_orig.png
deleted file mode 100644
index 838a3c0c8c..0000000000
Binary files a/img/perf-analysis/FMA_tput_uica_orig.png and /dev/null differ