diff --git a/manuscrit/30_palmed/30_pipedream.tex b/manuscrit/30_palmed/30_pipedream.tex
index e56f74f..035d214 100644
--- a/manuscrit/30_palmed/30_pipedream.tex
+++ b/manuscrit/30_palmed/30_pipedream.tex
@@ -1,8 +1,6 @@
 \section{Measuring a kernel's throughput:
 \pipedream{}}\label{sec:palmed_pipedream}
 
-\todo{Introduce pipedream notation for instructions}
-
 To build a mapping of a CPU, Palmed fundamentally depends on the ability to
 measure the execution time $\cyc{\kerK}$ of a kernel $\kerK$. However, as we
 saw above, Palmed defines a kernel as a multiset of instructions, and makes
@@ -40,6 +38,13 @@ that $\texttt{\footnotesize{}UNROLL\_SIZE} \times
 \lstc{UNROLL_SIZE}, \lstc{TOTAL_INSN} and \lstc{NUM_MEASURES} are
 parameters of the benchmark generation.
 
+\pipedream{} must be able to distinguish between variants of instructions with
+the same mnemonic --~\eg{} \lstxasm{mov}~-- but different operand kinds,
+altering the semantics and performance of the instruction --~such as a
+\lstxasm{mov} loading from memory versus a \lstxasm{mov} between registers. To
+this end, \pipedream{} represents instructions fully qualified with their
+operands' kind --~this can be seen as a process akin to C++'s name mangling.
+
 As \pipedream{} gets a multiset of instructions as a kernel, these
 instructions' arguments must be instantiated to turn them into actual assembly
 code ---~that is, turn \eg{} \lstxasm{ADD_GPR64i64_IMMi8} (the x86-64 variant