sm3: ppc64x transposeMatrix

.github/workflows/test_ppc64.yaml

@@ -15,7 +15,8 @@ jobs:
     strategy:
       matrix:
         go-version: [1.19.x]
-        arch: [ppc64le]  
+        arch: [ppc64le]
+        ppc64: [power8,power9]
     runs-on: ubuntu-latest
     steps:
     - name: Set up Go
@@ -32,5 +33,11 @@ jobs:
     - name: Test internal
       run: go test ./internal/...
       env:
-        GOARCH: ${{ matrix.arch }}      
+        GOARCH: ${{ matrix.arch }}
+        GOPPC64: ${{ matrix.ppc64 }}
 
+    - name: Test SM3
+      run: go test ./sm3/...
+      env:
+        GOARCH: ${{ matrix.arch }}
+        GOPPC64: ${{ matrix.ppc64 }}

sm3/sm3blocks_ppc64x.go

@@ -0,0 +1,10 @@
+// Copyright 2024 Sun Yimin. All rights reserved.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+//go:build (ppc64 || ppc64le) && !purego
+
+package sm3
+
+//go:noescape
+func transposeMatrix(dig **[8]uint32)

sm3/sm3blocks_ppc64x.s

@@ -0,0 +1,88 @@
+// Copyright 2024 Sun Yimin. All rights reserved.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+//go:build (ppc64 || ppc64le) && !purego
+
+#include "textflag.h"
+
+DATA mask<>+0x00(SB)/8, $0x0001020310111213
+DATA mask<>+0x08(SB)/8, $0x0405060714151617
+DATA mask<>+0x10(SB)/8, $0x08090a0b18191a1b
+DATA mask<>+0x18(SB)/8, $0x0c0d0e0f1c1d1e1f
+DATA mask<>+0x20(SB)/8, $0x0001020304050607
+DATA mask<>+0x28(SB)/8, $0x1011121314151617
+DATA mask<>+0x30(SB)/8, $0x08090a0b0c0d0e0f
+DATA mask<>+0x38(SB)/8, $0x18191a1b1c1d1e1f
+GLOBL mask<>(SB), 8, $64
+
+#ifdef GOARCH_ppc64le
+#define P8_LXVB16X(RA,RB,VT) \
+	LXVD2X	(RA+RB), VT \
+	XXPERMDI VT, VT, $2, VT
+
+#define P8_STXVB16X(VS,RA,RB) \
+	XXPERMDI VS, VS, $2, VS \
+	STXVD2X	VS, (RA+RB)
+
+#else
+#define P8_LXVB16X(RA,RB,VT)  LXVD2X	(RA+RB), VT
+#define P8_STXVB16X(VS,RA,RB) STXVD2X	VS, (RA+RB)	
+#endif
+
+#define TRANSPOSE_MATRIX(T0, T1, T2, T3, M0, M1, M2, M3, TMP0, TMP1, TMP2, TMP3) \
+	VPERM T0, T1, M0, TMP0; \
+	VPERM T2, T3, M0, TMP1; \
+	VPERM T0, T1, M1, TMP2; \
+	VPERM T2, T3, M1, TMP3; \
+	VPERM TMP0, TMP1, M2, T0; \
+	VPERM TMP0, TMP1, M3, T1; \
+	VPERM TMP2, TMP3, M2, T2; \
+	VPERM TMP2, TMP3, M3, T3
+
+// transposeMatrix(dig **[8]uint32)
+TEXT ·transposeMatrix(SB),NOSPLIT,$0
+	MOVD	dig+0(FP), R3
+	MOVD 	$8, R5
+	MOVD 	$16, R6
+	MOVD 	$24, R7
+	MOVD 	$32, R8
+	MOVD 	$48, R9
+
+	MOVD 	(R0)(R3), R4
+	P8_LXVB16X(R4, R0, V0)
+	P8_LXVB16X(R4, R6, V4)
+	MOVD 	(R5)(R3), R4
+	P8_LXVB16X(R4, R0, V1)
+	P8_LXVB16X(R4, R6, V5)
+	MOVD 	(R6)(R3), R4
+	P8_LXVB16X(R4, R0, V2)
+	P8_LXVB16X(R4, R6, V6)
+	MOVD 	(R7)(R3), R4
+	P8_LXVB16X(R4, R0, V3)
+	P8_LXVB16X(R4, R6, V7)
+
+	MOVD $mask<>+0x00(SB), R4
+
+	LVX 	(R0)(R4), V8
+	LVX 	(R6)(R4), V9
+	LVX 	(R8)(R4), V10
+	LVX 	(R9)(R4), V11
+
+	TRANSPOSE_MATRIX(V0, V1, V2, V3, V8, V9, V10, V11, V12, V13, V14, V15)
+	TRANSPOSE_MATRIX(V4, V5, V6, V7, V8, V9, V10, V11, V12, V13, V14, V15)
+
+	MOVD 	(R0)(R3), R4
+	P8_STXVB16X(V0, R4, R0)
+	P8_STXVB16X(V4, R4, R6)
+	MOVD 	(R5)(R3), R4
+	P8_STXVB16X(V1, R4, R0)
+	P8_STXVB16X(V5, R4, R6)
+	MOVD 	(R6)(R3), R4
+	P8_STXVB16X(V2, R4, R0)
+	P8_STXVB16X(V6, R4, R6)
+	MOVD 	(R7)(R3), R4
+	P8_STXVB16X(V3, R4, R0)
+	P8_STXVB16X(V7, R4, R6)
+
+	RET

sm3/sm3blocks_ppc64x_test.go

@@ -0,0 +1,35 @@
+// Copyright 2024 Sun Yimin. All rights reserved.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+//go:build (ppc64 || ppc64le) && !purego
+
+package sm3
+
+import (
+	"fmt"
+	"testing"
+)
+
+func TestTransposeMatrix(t *testing.T) {
+	var m [4][8]uint32
+	var k uint32 = 0
+	for i := 0; i < 4; i++ {
+		for j := 0; j < 8; j++ {
+			m[i][j] = k
+			k++
+			fmt.Printf("%04x ", m[i][j])
+		}
+		fmt.Println()
+	}
+	input := [4]*[8]uint32{&m[0], &m[1], &m[2], &m[3]}
+	transposeMatrix(&input[0])
+	fmt.Println()
+	fmt.Println()
+	for i := 0; i < 4; i++ {
+		for j := 0; j < 8; j++ {
+			fmt.Printf("%04x ", m[i][j])
+		}
+		fmt.Println()
+	}
+}