diff --git a/OmaxLTO.cfg b/OmaxLTO.cfg
index 5c029b91..f7a11a59 100644
--- a/OmaxLTO.cfg
+++ b/OmaxLTO.cfg
@@ -1,3 +1,4 @@
 -flto=full \
 -fvirtual-function-elimination \
--fwhole-program-vtables
+-fwhole-program-vtables \
+-mllvm -extra-LTO-loop-unroll=true
diff --git a/README.md b/README.md
index 32e7afc1..ad7e865a 100644
--- a/README.md
+++ b/README.md
@@ -172,6 +172,7 @@ and/or increased memory usage during linking. Some of the options in the config
 corresponding optimisation passes in the [LLVM project](https://github.com/llvm/llvm-project)
 to find out more. Users are also encouraged to create their own configs and tune their own
 flag parameters.
+Information on LLVM Embedded Toolchain for Arm specific optimization flags is available in [Optimization Flags](https://github.com/ARM-software/LLVM-embedded-toolchain-for-Arm/blob/main/docs/optimization-flags.md)
 
 Binary releases of the LLVM Embedded Toolchain for Arm are based on release
 branches of the upstream LLVM Project, thus can safely be used with all tools
diff --git a/docs/optimization-flags.md b/docs/optimization-flags.md
new file mode 100644
index 00000000..f67f6412
--- /dev/null
+++ b/docs/optimization-flags.md
@@ -0,0 +1,9 @@
+Additional optimization flags
+=============================
+
+## Additional loop unroll in the LTO pipeline
+In some cases it is benefitial to perform an additional loop unroll pass so that extra information becomes available to later passes, e.g. SROA. 
+Use cases where this could be beneficial - multiple (N>=4) nested loops.
+
+### Usage: 
+    -mllvm -extra-LTO-loop-unroll=true/false
diff --git a/patches/llvm-project-perf/0000-Placeholder-commit.patch b/patches/llvm-project-perf/0000-Placeholder-commit.patch
deleted file mode 100644
index ff8059cb..00000000
--- a/patches/llvm-project-perf/0000-Placeholder-commit.patch
+++ /dev/null
@@ -1,22 +0,0 @@
-From e79697a54cba9bfc1a755ed048e42054d679de61 Mon Sep 17 00:00:00 2001
-From: David Candler <david.candler@arm.com>
-Date: Wed, 2 Oct 2024 14:13:31 +0100
-Subject: [PATCH] Placeholder commit
-
----
- .gitignore | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/.gitignore b/.gitignore
-index 0e7c6c790013..dfa0b8da0ccd 100644
---- a/.gitignore
-+++ b/.gitignore
-@@ -1,4 +1,4 @@
--#==============================================================================#
-+#==============================================================================#
- # This file specifies intentionally untracked files that git should ignore.
- # See: http://www.kernel.org/pub/software/scm/git/docs/gitignore.html
- #
--- 
-2.34.1
-
diff --git a/patches/llvm-project-perf/0001-LTOpasses-add-loop-unroll.patch b/patches/llvm-project-perf/0001-LTOpasses-add-loop-unroll.patch
new file mode 100644
index 00000000..88c68109
--- /dev/null
+++ b/patches/llvm-project-perf/0001-LTOpasses-add-loop-unroll.patch
@@ -0,0 +1,55 @@
+From 4adfc5231d2c0182d6278b4aa75eec57648e5dd4 Mon Sep 17 00:00:00 2001
+From: Vladi Krapp <vladi.krapp@arm.com>
+Date: Tue, 3 Sep 2024 14:12:48 +0100
+Subject: [Pipelines] Additional unrolling  in LTO 
+
+Some workloads require specific sequences of events to happen
+to fully simplify. This adds an extra full unrolling pass to help these
+cases on the cores with branch predictors. It helps produce simplified
+loops, which can then be SROA'd allowing further simplification, which
+can be important for performance.
+Feature adds extra compile time to get extra performance and 
+is enabled by the opt flag 'extra-LTO-loop-unroll' (off by default).
+
+Original patch by David Green (david.green@arm.com)
+---
+ llvm/lib/Passes/PassBuilderPipelines.cpp | 16 ++++++++++++++++
+ 1 file changed, 16 insertions(+)
+
+diff --git a/llvm/lib/Passes/PassBuilderPipelines.cpp b/llvm/lib/Passes/PassBuilderPipelines.cpp
+index 1184123c7710..6dc45d85927a 100644
+--- a/llvm/lib/Passes/PassBuilderPipelines.cpp
++++ b/llvm/lib/Passes/PassBuilderPipelines.cpp
+@@ -332,6 +332,10 @@ namespace llvm {
+ extern cl::opt<unsigned> MaxDevirtIterations;
+ } // namespace llvm
+ 
++static cl::opt<bool> LTOExtraLoopUnroll(
++    "extra-LTO-loop-unroll", cl::init(false), cl::Hidden,
++    cl::desc("Perform extra loop unrolling pass to assist SROA"));
++
+ void PassBuilder::invokePeepholeEPCallbacks(FunctionPassManager &FPM,
+                                             OptimizationLevel Level) {
+   for (auto &C : PeepholeEPCallbacks)
+@@ -1940,6 +1944,18 @@ PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level,
+   MPM.addPass(createModuleToPostOrderCGSCCPassAdaptor(ArgumentPromotionPass()));
+ 
+   FunctionPassManager FPM;
++
++  if (LTOExtraLoopUnroll) {
++    LoopPassManager OmaxLPM;
++    OmaxLPM.addPass(LoopFullUnrollPass(Level.getSpeedupLevel(),
++                                       /* OnlyWhenForced= */ !PTO.LoopUnrolling,
++                                       PTO.ForgetAllSCEVInLoopUnroll));
++    FPM.addPass(
++        createFunctionToLoopPassAdaptor(std::move(OmaxLPM),
++                                        /*UseMemorySSA=*/false,
++                                        /*UseBlockFrequencyInfo=*/true));
++  }
++
+   // The IPO Passes may leave cruft around. Clean up after them.
+   FPM.addPass(InstCombinePass());
+   invokePeepholeEPCallbacks(FPM, Level);
+-- 
+2.34.1
+