Skip to content

Armv8.1-M: Add clean x4 Keccak code and SLOTHY Makefile #1527

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mkannwischer wants to merge 2 commits into
base: main
Choose a base branch
from
+560 −14
Open

Armv8.1-M: Add clean x4 Keccak code and SLOTHY Makefile #1527

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d0a737c
Armv8.1-M: Add clean x4 Keccak code and SLOTHY Makefile
mkannwischer Jan 28, 2026
0758df6
Armv8.1-M: Trim x4 Keccak register saves
bremoran Jun 5, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/ci_ec2_reusable.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,7 +207,7 @@ 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
Expand Down
47 changes: 47 additions & 0 deletions dev/fips202/armv81m/src/Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -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)
8 changes: 4 additions & 4 deletions dev/fips202/armv81m/src/keccak_f1600_x4_mve.S
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,8 +28,8 @@
c_parameter: const uint32_t *rc
description: Keccak round constants in bit-interleaved form (24 pairs of 32-bit words)
Stack:
bytes: 236
description: register preservation (44) + SIMD registers (64) + temporary storage (128)
bytes: 228
description: register preservation (36) + SIMD registers (64) + temporary storage (128)
*/

// ---------------------------------------------------------------------------
Expand Down Expand Up @@ -460,7 +460,7 @@ qA20_l .req q2
.global MLK_ASM_NAMESPACE(keccak_f1600_x4_mve_asm)
MLK_ASM_FN_SYMBOL(keccak_f1600_x4_mve_asm)

push {r3,r4,r5,r6,r7,r8,r9,r10,r11,r12,lr}
push {r4,r5,r6,r7,r8,r9,r10,r11,lr}
vpush {d8-d15}
sub sp, #8*16

Expand Down Expand Up @@ -1626,7 +1626,7 @@ keccak_f1600_x4_mve_asm_roundend:
add sp, #8*16

vpop {d8-d15}
ldmia.w sp!, {r3,r4,r5,r6,r7,r8,r9,r10,r11,r12, pc}
ldmia.w sp!, {r4,r5,r6,r7,r8,r9,r10,r11, pc}

/****************** REGISTER DEALLOCATIONS *******************/
.unreq qA00_h
Expand Down
Loading
Loading