-
Notifications
You must be signed in to change notification settings - Fork 37
Added optimized ppc64le support functions for ML-KEM. #1184
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.
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
dannytsen
wants to merge
19
commits into
pq-code-package:main
Choose a base branch
from
dannytsen:main
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+3,908
−0
Open
Changes from all commits
Commits
Show all changes
19 commits
Select commit
Hold shift + click to select a range
0a81791
Added optimized ppc64le support functions for ML-KEM.
dannytsen 68ee31c
Document nix 2.18 requirement; disable nix setup test for nix 2.6
mkannwischer 1f41a2e
Add clang_21 to compiler and constant-time tests
mkannwischer d4e8c28
bitwuzla: update the bitwuzla version from 0.7.0 to 0.8.2 in nix
willieyz 4e33b28
Add compiler test for zig 0.15
mkannwischer aa3b87b
Fixed auto.mk, components.mk and YML files.
dannytsen 5f71ef6
Fixed format and styling by using autogen but no simpasm was run.
f3a7d3c
Add MLK_CONFIG_NO_RANDOMIZED_API with default not set
willieyz 25d3218
Guard the `crypto_kem_keypair` and `crypto_kem_enc` from:
willieyz b4d8771
Add new example `basic_deterministic`
willieyz 95d003e
CBMC: Increase the CBMC_OBJECT_BITS of `matvec_mul` to 12
willieyz 111fbd9
Add `--exclude example` args for "PCT enabled" CI testing
willieyz f768bb5
Introduce explicit upper bounds on lengths of
rod-chapman 61abb93
Removed un-wanted comment.
dannytsen 6f1e95c
Merge branch 'pq-code-package:main' into main
dannytsen 52b9c78
Removed unused comment lines.
dannytsen df55bea
Merge branch 'pq-code-package:main' into main
dannytsen 33858ec
Fixed failure in INTT unit tests.
dannytsen 615cf86
Merge branch 'main' into main
dannytsen File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,6 @@ | ||
| [//]: # (SPDX-License-Identifier: CC-BY-4.0) | ||
|
|
||
| # ppc64le backend (little endian) | ||
|
|
||
| This directory contains a native backend for little endian POWER 8 (ppc64le) and above systems. | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,53 @@ | ||
| /* | ||
| * Copyright (c) The mlkem-native project authors | ||
| * SPDX-License-Identifier: Apache-2.0 OR ISC OR MIT | ||
| */ | ||
|
|
||
| #ifndef MLK_DEV_PPC64LE_META_H | ||
| #define MLK_DEV_PPC64LE_META_H | ||
|
|
||
| /* Identifier for this backend so that source and assembly files | ||
| * in the build can be appropriately guarded. */ | ||
| #define MLK_ARITH_BACKEND_PPC64LE_DEFAULT | ||
|
|
||
| #define MLK_ARITH_BACKEND_NAME PPC64LE_DEFAULT | ||
|
|
||
| /* Set of primitives that this backend replaces */ | ||
| #define MLK_USE_NATIVE_NTT | ||
| #define MLK_USE_NATIVE_INTT | ||
| #define MLK_USE_NATIVE_POLY_REDUCE | ||
| #define MLK_USE_NATIVE_POLY_TOMONT | ||
|
|
||
| #if !defined(__ASSEMBLER__) | ||
| #include <string.h> | ||
| #include "../../common.h" | ||
| #include "../../params.h" | ||
| #include "../api.h" | ||
| #include "src/arith_native_ppc64le.h" | ||
|
|
||
| static MLK_INLINE int mlk_ntt_native(int16_t data[MLKEM_N]) | ||
| { | ||
| mlk_ntt_ppc(data, mlk_ppc_qdata); | ||
| return MLK_NATIVE_FUNC_SUCCESS; | ||
| } | ||
|
|
||
| static MLK_INLINE int mlk_intt_native(int16_t data[MLKEM_N]) | ||
| { | ||
| mlk_intt_ppc(data, mlk_ppc_qdata); | ||
| return MLK_NATIVE_FUNC_SUCCESS; | ||
| } | ||
|
|
||
| static MLK_INLINE int mlk_poly_reduce_native(int16_t data[MLKEM_N]) | ||
| { | ||
| mlk_reduce_ppc(data, mlk_ppc_qdata); | ||
| return MLK_NATIVE_FUNC_SUCCESS; | ||
| } | ||
|
|
||
| static MLK_INLINE int mlk_poly_tomont_native(int16_t data[MLKEM_N]) | ||
| { | ||
| mlk_poly_tomont_ppc(data, mlk_ppc_qdata); | ||
| return MLK_NATIVE_FUNC_SUCCESS; | ||
| } | ||
| #endif /* !__ASSEMBLER__ */ | ||
|
|
||
| #endif /* !MLK_DEV_PPC64LE_META_H */ |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,24 @@ | ||
| /* | ||
| * Copyright (c) 2024-2025 The mlkem-native project authors | ||
| * SPDX-License-Identifier: Apache-2.0 | ||
| */ | ||
| #ifndef MLK_DEV_PPC64LE_SRC_ARITH_NATIVE_PPC64LE_H | ||
| #define MLK_DEV_PPC64LE_SRC_ARITH_NATIVE_PPC64LE_H | ||
|
|
||
| #include <stdint.h> | ||
| #include "../../../common.h" | ||
| #include "consts.h" | ||
|
|
||
| #define mlk_ntt_ppc MLK_NAMESPACE(ntt_ppc) | ||
| void mlk_ntt_ppc(int16_t *, const int16_t *); | ||
|
|
||
| #define mlk_intt_ppc MLK_NAMESPACE(intt_ppc) | ||
| void mlk_intt_ppc(int16_t *, const int16_t *); | ||
|
|
||
| #define mlk_reduce_ppc MLK_NAMESPACE(reduce_ppc) | ||
| void mlk_reduce_ppc(int16_t *r, const int16_t *); | ||
|
|
||
| #define mlk_poly_tomont_ppc MLK_NAMESPACE(poly_tomont_ppc) | ||
| void mlk_poly_tomont_ppc(int16_t *, const int16_t *); | ||
|
|
||
| #endif /* !MLK_DEV_PPC64LE_SRC_ARITH_NATIVE_PPC64LE_H */ |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,132 @@ | ||
| /* | ||
| * Copyright (c) The mlkem-native project authors | ||
| * SPDX-License-Identifier: Apache-2.0 OR ISC OR MIT | ||
| */ | ||
|
|
||
| #include <stdint.h> | ||
| #include <stdio.h> | ||
| #include <stdlib.h> | ||
| #include <string.h> | ||
|
|
||
| #include "../../../common.h" | ||
|
|
||
| #if defined(MLK_ARITH_BACKEND_PPC64LE_DEFAULT) && \ | ||
| !defined(MLK_CONFIG_MULTILEVEL_NO_SHARED) | ||
|
|
||
| #include "consts.h" | ||
|
|
||
| MLK_ALIGN const int16_t mlk_ppc_qdata[1072] = { | ||
| /* -Q */ | ||
| -3329, -3329, -3329, -3329, -3329, -3329, -3329, -3329, | ||
| /* QINV */ | ||
| -3327, -3327, -3327, -3327, -3327, -3327, -3327, -3327, | ||
| /* Q */ | ||
| 3329, 3329, 3329, 3329, 3329, 3329, 3329, 3329, | ||
| /* const 20159 for reduce.S and intt */ | ||
| 20159, 20159, 20159, 20159, 20159, 20159, 20159, 20159, | ||
| /* const 1441 for intt */ | ||
| 1441, 1441, 1441, 1441, 1441, 1441, 1441, 1441, | ||
| /* for poly_tomont.S */ | ||
| 1353, 1353, 1353, 1353, 1353, 1353, 1353, 1353, | ||
| /* zetas */ | ||
| /* For ntt Len=128, offset 96 */ | ||
| -758, -758, -758, -758, -758, -758, -758, -758, -359, -359, -359, -359, | ||
| -359, -359, -359, -359, -1517, -1517, -1517, -1517, -1517, -1517, -1517, | ||
| -1517, 1493, 1493, 1493, 1493, 1493, 1493, 1493, 1493, 1422, 1422, 1422, | ||
| 1422, 1422, 1422, 1422, 1422, 287, 287, 287, 287, 287, 287, 287, 287, 202, | ||
| 202, 202, 202, 202, 202, 202, 202, -171, -171, -171, -171, -171, -171, -171, | ||
| -171, 622, 622, 622, 622, 622, 622, 622, 622, 1577, 1577, 1577, 1577, 1577, | ||
| 1577, 1577, 1577, 182, 182, 182, 182, 182, 182, 182, 182, 962, 962, 962, | ||
| 962, 962, 962, 962, 962, -1202, -1202, -1202, -1202, -1202, -1202, -1202, | ||
| -1202, -1474, -1474, -1474, -1474, -1474, -1474, -1474, -1474, 1468, 1468, | ||
| 1468, 1468, 1468, 1468, 1468, 1468, 573, 573, 573, 573, 573, 573, 573, 573, | ||
| -1325, -1325, -1325, -1325, -1325, -1325, -1325, -1325, 264, 264, 264, 264, | ||
| 264, 264, 264, 264, 383, 383, 383, 383, 383, 383, 383, 383, -829, -829, | ||
| -829, -829, -829, -829, -829, -829, 1458, 1458, 1458, 1458, 1458, 1458, | ||
| 1458, 1458, -1602, -1602, -1602, -1602, -1602, -1602, -1602, -1602, -130, | ||
| -130, -130, -130, -130, -130, -130, -130, -681, -681, -681, -681, -681, | ||
| -681, -681, -681, 1017, 1017, 1017, 1017, 1017, 1017, 1017, 1017, 732, 732, | ||
| 732, 732, 732, 732, 732, 732, 608, 608, 608, 608, 608, 608, 608, 608, -1542, | ||
| -1542, -1542, -1542, -1542, -1542, -1542, -1542, 411, 411, 411, 411, 411, | ||
| 411, 411, 411, -205, -205, -205, -205, -205, -205, -205, -205, -1571, -1571, | ||
| -1571, -1571, -1571, -1571, -1571, -1571, | ||
| /* For Len=4 */ | ||
| 1223, 1223, 1223, 1223, 652, 652, 652, 652, -552, -552, -552, -552, 1015, | ||
| 1015, 1015, 1015, -1293, -1293, -1293, -1293, 1491, 1491, 1491, 1491, -282, | ||
| -282, -282, -282, -1544, -1544, -1544, -1544, 516, 516, 516, 516, -8, -8, | ||
| -8, -8, -320, -320, -320, -320, -666, -666, -666, -666, -1618, -1618, -1618, | ||
| -1618, -1162, -1162, -1162, -1162, 126, 126, 126, 126, 1469, 1469, 1469, | ||
| 1469, -853, -853, -853, -853, -90, -90, -90, -90, -271, -271, -271, -271, | ||
| 830, 830, 830, 830, 107, 107, 107, 107, -1421, -1421, -1421, -1421, -247, | ||
| -247, -247, -247, -951, -951, -951, -951, -398, -398, -398, -398, 961, 961, | ||
| 961, 961, -1508, -1508, -1508, -1508, -725, -725, -725, -725, 448, 448, 448, | ||
| 448, -1065, -1065, -1065, -1065, 677, 677, 677, 677, -1275, -1275, -1275, | ||
| -1275, | ||
| /* | ||
| * For ntt Len=2 | ||
| * reorder zeta array, (1, 2, 3, 4) -> (3, 1, 4, 2) | ||
| * Transpose z[0], z[1], z[2], z[3] | ||
| * -> z[3], z[3], z[1], z[1], z[4], z[4], z[2], z[2] | ||
| */ | ||
| 555, 555, -1103, -1103, 843, 843, 430, 430, 1550, 1550, -1251, -1251, 105, | ||
| 105, 871, 871, 177, 177, 422, 422, -235, -235, 587, 587, 1574, 1574, -291, | ||
| -291, 1653, 1653, -460, -460, 1159, 1159, -246, -246, -147, -147, 778, 778, | ||
| -602, -602, -777, -777, 1119, 1119, 1483, 1483, -872, -872, -1590, -1590, | ||
| 349, 349, 644, 644, -156, -156, 418, 418, -75, -75, 329, 329, 603, 603, 817, | ||
| 817, 610, 610, 1097, 1097, -1465, -1465, 1322, 1322, 384, 384, -1285, -1285, | ||
| 1218, 1218, -1215, -1215, -1335, -1335, -136, -136, -1187, -1187, -874, | ||
| -874, -1659, -1659, 220, 220, -1278, -1278, -1185, -1185, 794, 794, -1530, | ||
| -1530, -870, -870, -1510, -1510, 478, 478, -854, -854, 996, 996, -108, -108, | ||
| 991, 991, -308, -308, 1522, 1522, 958, 958, 1628, 1628, -1460, -1460, | ||
| /* | ||
| * For intt Len=2, offset IZETA_NTT_OFFSET127 | ||
| * reorder zeta array, (1, 2, 3, 4) -> (3, 1, 4, 2) | ||
| * Transpose z[0], z[1], z[2], z[3] | ||
| * -> z[3], z[3], z[1], z[1], z[4], z[4], z[2], z[2] | ||
| */ | ||
| -1460, -1460, 1628, 1628, 958, 958, 1522, 1522, -308, -308, 991, 991, -108, | ||
| -108, 996, 996, -854, -854, 478, 478, -1510, -1510, -870, -870, -1530, | ||
| -1530, 794, 794, -1185, -1185, -1278, -1278, 220, 220, -1659, -1659, -874, | ||
| -874, -1187, -1187, -136, -136, -1335, -1335, -1215, -1215, 1218, 1218, | ||
| -1285, -1285, 384, 384, 1322, 1322, -1465, -1465, 1097, 1097, 610, 610, 817, | ||
| 817, 603, 603, 329, 329, -75, -75, 418, 418, -156, -156, 644, 644, 349, 349, | ||
| -1590, -1590, -872, -872, 1483, 1483, 1119, 1119, -777, -777, -602, -602, | ||
| 778, 778, -147, -147, -246, -246, 1159, 1159, -460, -460, 1653, 1653, -291, | ||
| -291, 1574, 1574, 587, 587, -235, -235, 422, 422, 177, 177, 871, 871, 105, | ||
| 105, -1251, -1251, 1550, 1550, 430, 430, 843, 843, -1103, -1103, 555, 555, | ||
| /* For intt Len=4 */ | ||
| -1275, -1275, -1275, -1275, 677, 677, 677, 677, -1065, -1065, -1065, -1065, | ||
| 448, 448, 448, 448, -725, -725, -725, -725, -1508, -1508, -1508, -1508, 961, | ||
| 961, 961, 961, -398, -398, -398, -398, -951, -951, -951, -951, -247, -247, | ||
| -247, -247, -1421, -1421, -1421, -1421, 107, 107, 107, 107, 830, 830, 830, | ||
| 830, -271, -271, -271, -271, -90, -90, -90, -90, -853, -853, -853, -853, | ||
| 1469, 1469, 1469, 1469, 126, 126, 126, 126, -1162, -1162, -1162, -1162, | ||
| -1618, -1618, -1618, -1618, -666, -666, -666, -666, -320, -320, -320, -320, | ||
| -8, -8, -8, -8, 516, 516, 516, 516, -1544, -1544, -1544, -1544, -282, -282, | ||
| -282, -282, 1491, 1491, 1491, 1491, -1293, -1293, -1293, -1293, 1015, 1015, | ||
| 1015, 1015, -552, -552, -552, -552, 652, 652, 652, 652, 1223, 1223, 1223, | ||
| 1223, | ||
| /* For intt Len=8 and others */ | ||
| -1571, -1571, -1571, -1571, -1571, -1571, -1571, -1571, -205, -205, -205, | ||
| -205, -205, -205, -205, -205, 411, 411, 411, 411, 411, 411, 411, 411, -1542, | ||
| -1542, -1542, -1542, -1542, -1542, -1542, -1542, 608, 608, 608, 608, 608, | ||
| 608, 608, 608, 732, 732, 732, 732, 732, 732, 732, 732, 1017, 1017, 1017, | ||
| 1017, 1017, 1017, 1017, 1017, -681, -681, -681, -681, -681, -681, -681, | ||
| -681, -130, -130, -130, -130, -130, -130, -130, -130, -1602, -1602, -1602, | ||
| -1602, -1602, -1602, -1602, -1602, 1458, 1458, 1458, 1458, 1458, 1458, 1458, | ||
| 1458, -829, -829, -829, -829, -829, -829, -829, -829, 383, 383, 383, 383, | ||
| 383, 383, 383, 383, 264, 264, 264, 264, 264, 264, 264, 264, -1325, -1325, | ||
| -1325, -1325, -1325, -1325, -1325, -1325, 573, 573, 573, 573, 573, 573, 573, | ||
| 573, 1468, 1468, 1468, 1468, 1468, 1468, 1468, 1468, -1474, -1474, -1474, | ||
| -1474, -1474, -1474, -1474, -1474, -1202, -1202, -1202, -1202, -1202, -1202, | ||
| -1202, -1202, 962, 962, 962, 962, 962, 962, 962, 962, 182, 182, 182, 182, | ||
| 182, 182, 182, 182, 1577, 1577, 1577, 1577, 1577, 1577, 1577, 1577, 622, | ||
| 622, 622, 622, 622, 622, 622, 622, -171, -171, -171, -171, -171, -171, -171, | ||
| -171, 202, 202, 202, 202, 202, 202, 202, 202, 287, 287, 287, 287, 287, 287, | ||
| 287, 287, 1422, 1422, 1422, 1422, 1422, 1422, 1422, 1422, 1493, 1493, 1493, | ||
| 1493, 1493, 1493, 1493, 1493, -1517, -1517, -1517, -1517, -1517, -1517, | ||
| -1517, -1517, -359, -359, -359, -359, -359, -359, -359, -359, -758, -758, | ||
| -758, -758, -758, -758, -758, -758}; | ||
|
|
||
| #endif /* MLK_ARITH_BACKEND_PPC64LE_DEFAULT && \ | ||
| !MLK_CONFIG_MULTILEVEL_NO_SHARED */ |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,24 @@ | ||
| /* | ||
| * Copyright (c) The mlkem-native project authors | ||
| * SPDX-License-Identifier: Apache-2.0 OR ISC OR MIT | ||
| */ | ||
|
|
||
| #ifndef MLK_DEV_PPC64LE_SRC_CONSTS_H | ||
| #define MLK_DEV_PPC64LE_SRC_CONSTS_H | ||
| #include "../../../common.h" | ||
|
|
||
| #define NQ_OFFSET 0 | ||
| #define QINV_OFFSET 16 | ||
| #define Q_OFFSET 32 | ||
| #define C20159_OFFSET 48 | ||
| #define C1441_OFFSET 64 | ||
| #define C1353_OFFSET 80 | ||
| #define ZETA_NTT_OFFSET 96 | ||
| #define ZETA_INTT_OFFSET 1104 | ||
|
|
||
| #ifndef __ASSEMBLER__ | ||
| #define mlk_ppc_qdata MLK_NAMESPACE(ppc_qdata) | ||
| extern const int16_t mlk_ppc_qdata[]; | ||
| #endif | ||
|
|
||
| #endif /* !MLK_DEV_PPC64LE_SRC_CONSTS_H */ |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
As discussed before, I couldn't yet run the code with power8 emulation, and I think you mentioned you only tested power9 and power10. Are you sure it works on power8?