Armv8.1-M: Add clean x4 Keccak code and SLOTHY Makefile

Add the clean (non-optimized) Keccak x4 assembly and Makefile to enable
regeneration of the SLOTHY-optimized assembly.

Extend autogen --slothy to support new function, and also add
--slothy armv81m and --slothy aarch64 group options.
Update CI to only run aarch64 SLOTHY targets.

Optimization of Armv8.1-M assembly is not currently tested in CI, but has been
tested locally.

Update SLOTHY to version 0.1.10 as the code requires disabling the address
offset fixup which is not supported for Armv8.1-M in the older versionf of
SLOTHY.

Co-Authored-By: Brendan Moran <brendan.moran@arm.com>
Signed-off-by: Matthias J. Kannwischer <matthias@kannwischer.eu>

Author: mkannwischer

.github/workflows/ci_ec2_reusable.yml

@@ -199,7 +199,7 @@ jobs:
           nix-cache: true
           nix-shell: slothy
           script: |
-            autogen --slothy
+            autogen --slothy aarch64
             tests all --opt opt
             # Force testing of SLOTHY-optimized Keccak variants
             # We can't run the examples here because some of them also specify the backend

dev/fips202/armv81m/src/Makefile

@@ -0,0 +1,47 @@
+# Copyright (c) The mlkem-native project authors
+# SPDX-License-Identifier: Apache-2.0 OR ISC OR MIT
+
+.PHONY: all purge
+.DEFAULT_GOAL := all
+
+# ISA to optimize for
+TARGET_ISA=Arm_v81M
+
+# MicroArch target to optimize for
+TARGET_MICROARCH=Arm_Cortex_M55
+
+keccak_f1600_x4_mve.S: ../../armv81m_symbolic/keccak_f1600_x4_mve_clean.S
+	$(eval TMP := $(shell mktemp))
+	slothy-cli $(TARGET_ISA) $(TARGET_MICROARCH) $< -o $(TMP) \
+		-s keccak_f1600_x4_mve_asm_roundstart \
+		-e keccak_f1600_x4_mve_asm_roundend_pre \
+		-c unsafe_address_offset_fixup=False \
+		-c inputs_are_outputs=True \
+		-c constraints.functional_only=True \
+		-c constraints.allow_reordering=True \
+		-c constraints.max_displacement=0.1
+	slothy-cli $(TARGET_ISA) $(TARGET_MICROARCH) $(TMP) -o $@ \
+		-s keccak_f1600_x4_mve_asm_roundstart \
+		-e keccak_f1600_x4_mve_asm_roundend_pre \
+		-c constraints.functional_only=False \
+		-c constraints.allow_reordering=True \
+		-c variable_size=True \
+        -c inputs_are_outputs=True \
+		-c constraints.stalls_first_attempt=64 \
+		-c constraints.max_displacement=1.0 \
+		-c constraints.stalls_maximum_attempt=4096 \
+        -c unsafe_address_offset_fixup=False \
+		-c split_heuristic=True \
+		-c split_heuristic_stepsize=0.05 \
+		-c split_heuristic_factor=26 \
+		-c split_heuristic_repeat=2 \
+		-c split_heuristic_estimate_performance=False \
+		-c split_heuristic_optimize_seam=2
+	rm -f $(TMP)
+
+ALL=keccak_f1600_x4_mve.S
+
+all: $(ALL)
+
+purge:
+	rm -rf $(ALL)