crypto/sha256: use const table for key loading on loong64

Load constant keys from a static memory table rather than loading immediates into registers on loong64.

Benchmark for Loongson-3A5000:
goos: linux
goarch: loong64
pkg: crypto/sha256
cpu: Loongson-3A5000-HV @ 2500.00MHz
                    │   sha256o   │              sha256n              │
                    │   sec/op    │   sec/op     vs base              │
Hash8Bytes/New-4      356.1n ± 0%   347.0n ± 0%  -2.54% (p=0.000 n=8)
Hash8Bytes/Sum224-4   368.7n ± 0%   359.5n ± 0%  -2.50% (p=0.000 n=8)
Hash8Bytes/Sum256-4   367.7n ± 0%   358.9n ± 0%  -2.41% (p=0.000 n=8)
Hash1K/New-4          4.741µ ± 0%   4.578µ ± 0%  -3.44% (p=0.000 n=8)
Hash1K/Sum224-4       4.755µ ± 0%   4.591µ ± 0%  -3.44% (p=0.000 n=8)
Hash1K/Sum256-4       4.753µ ± 0%   4.589µ ± 0%  -3.46% (p=0.000 n=8)
Hash8K/New-4          35.42µ ± 0%   34.19µ ± 0%  -3.45% (p=0.000 n=8)
Hash8K/Sum224-4       35.43µ ± 0%   34.21µ ± 0%  -3.44% (p=0.000 n=8)
Hash8K/Sum256-4       35.46µ ± 0%   34.22µ ± 0%  -3.48% (p=0.000 n=8)
Hash256K/New-4        1.138m ± 0%   1.098m ± 0%  -3.54% (p=0.000 n=8)
Hash256K/Sum224-4     1.138m ± 0%   1.098m ± 0%  -3.53% (p=0.000 n=8)
Hash256K/Sum256-4     1.139m ± 0%   1.099m ± 0%  -3.48% (p=0.000 n=8)
Hash1M/New-4          4.488m ± 0%   4.388m ± 0%  -2.22% (p=0.000 n=8)
Hash1M/Sum224-4       4.488m ± 0%   4.387m ± 0%  -2.24% (p=0.000 n=8)
Hash1M/Sum256-4       4.489m ± 0%   4.388m ± 0%  -2.25% (p=0.000 n=8)
geomean               50.02µ        48.50µ       -3.03%

                    │   sha256o    │              sha256n               │
                    │     B/s      │     B/s       vs base              │
Hash8Bytes/New-4      21.42Mi ± 0%   21.99Mi ± 0%  +2.63% (p=0.000 n=8)
Hash8Bytes/Sum224-4   20.69Mi ± 0%   21.22Mi ± 0%  +2.56% (p=0.000 n=8)
Hash8Bytes/Sum256-4   20.74Mi ± 0%   21.26Mi ± 0%  +2.48% (p=0.000 n=8)
Hash1K/New-4          206.0Mi ± 0%   213.3Mi ± 0%  +3.57% (p=0.000 n=8)
Hash1K/Sum224-4       205.4Mi ± 0%   212.7Mi ± 0%  +3.57% (p=0.000 n=8)
Hash1K/Sum256-4       205.5Mi ± 0%   212.8Mi ± 0%  +3.58% (p=0.000 n=8)
Hash8K/New-4          220.6Mi ± 0%   228.5Mi ± 0%  +3.58% (p=0.000 n=8)
Hash8K/Sum224-4       220.5Mi ± 0%   228.4Mi ± 0%  +3.56% (p=0.000 n=8)
Hash8K/Sum256-4       220.3Mi ± 0%   228.3Mi ± 0%  +3.61% (p=0.000 n=8)
Hash256K/New-4        219.7Mi ± 0%   227.7Mi ± 0%  +3.67% (p=0.000 n=8)
Hash256K/Sum224-4     219.6Mi ± 0%   227.6Mi ± 0%  +3.66% (p=0.000 n=8)
Hash256K/Sum256-4     219.6Mi ± 0%   227.5Mi ± 0%  +3.60% (p=0.000 n=8)
Hash1M/New-4          222.8Mi ± 0%   227.9Mi ± 0%  +2.27% (p=0.000 n=8)
Hash1M/Sum224-4       222.8Mi ± 0%   227.9Mi ± 0%  +2.29% (p=0.000 n=8)
Hash1M/Sum256-4       222.8Mi ± 0%   227.9Mi ± 0%  +2.30% (p=0.000 n=8)
geomean               136.0Mi        140.2Mi       +3.13%

Benchmark for Loongson-3A6000:
goos: linux
goarch: loong64
pkg: crypto/sha256
cpu: Loongson-3A6000 @ 2500.00MHz
                    │ sha256.old  │             sha256.new             │
                    │   sec/op    │   sec/op     vs base               │
Hash8Bytes/New-8      294.5n ± 0%   288.6n ± 0%  -2.00% (p=0.000 n=10)
Hash8Bytes/Sum224-8   305.0n ± 0%   299.7n ± 0%  -1.74% (p=0.000 n=10)
Hash8Bytes/Sum256-8   302.0n ± 0%   296.8n ± 0%  -1.74% (p=0.000 n=10)
Hash1K/New-8          4.186µ ± 0%   4.096µ ± 0%  -2.15% (p=0.000 n=10)
Hash1K/Sum224-8       4.193µ ± 0%   4.104µ ± 0%  -2.12% (p=0.000 n=10)
Hash1K/Sum256-8       4.194µ ± 0%   4.108µ ± 0%  -2.04% (p=0.000 n=10)
Hash8K/New-8          31.44µ ± 0%   30.76µ ± 0%  -2.17% (p=0.000 n=10)
Hash8K/Sum224-8       31.45µ ± 0%   30.79µ ± 0%  -2.10% (p=0.000 n=10)
Hash8K/Sum256-8       31.45µ ± 0%   30.78µ ± 0%  -2.12% (p=0.000 n=10)
Hash256K/New-8        996.7µ ± 0%   975.6µ ± 0%  -2.12% (p=0.000 n=10)
Hash256K/Sum224-8     996.8µ ± 0%   975.8µ ± 0%  -2.11% (p=0.000 n=10)
Hash256K/Sum256-8     996.8µ ± 0%   975.6µ ± 0%  -2.12% (p=0.000 n=10)
Hash1M/New-8          3.987m ± 0%   3.904m ± 0%  -2.08% (p=0.000 n=10)
Hash1M/Sum224-8       3.990m ± 0%   3.902m ± 0%  -2.20% (p=0.000 n=10)
Hash1M/Sum256-8       3.987m ± 0%   3.903m ± 0%  -2.10% (p=0.000 n=10)
geomean               43.59µ        42.69µ       -2.06%

                    │  sha256.old  │             sha256.new              │
                    │     B/s      │     B/s       vs base               │
Hash8Bytes/New-8      25.90Mi ± 0%   26.44Mi ± 0%  +2.06% (p=0.000 n=10)
Hash8Bytes/Sum224-8   25.01Mi ± 0%   25.46Mi ± 0%  +1.77% (p=0.000 n=10)
Hash8Bytes/Sum256-8   25.26Mi ± 0%   25.72Mi ± 0%  +1.79% (p=0.000 n=10)
Hash1K/New-8          233.3Mi ± 0%   238.5Mi ± 0%  +2.19% (p=0.000 n=10)
Hash1K/Sum224-8       232.9Mi ± 0%   238.0Mi ± 0%  +2.17% (p=0.000 n=10)
Hash1K/Sum256-8       232.9Mi ± 0%   237.7Mi ± 0%  +2.07% (p=0.000 n=10)
Hash8K/New-8          248.5Mi ± 0%   254.0Mi ± 0%  +2.22% (p=0.000 n=10)
Hash8K/Sum224-8       248.4Mi ± 0%   253.7Mi ± 0%  +2.14% (p=0.000 n=10)
Hash8K/Sum256-8       248.4Mi ± 0%   253.8Mi ± 0%  +2.17% (p=0.000 n=10)
Hash256K/New-8        250.8Mi ± 0%   256.3Mi ± 0%  +2.17% (p=0.000 n=10)
Hash256K/Sum224-8     250.8Mi ± 0%   256.2Mi ± 0%  +2.16% (p=0.000 n=10)
Hash256K/Sum256-8     250.8Mi ± 0%   256.2Mi ± 0%  +2.17% (p=0.000 n=10)
Hash1M/New-8          250.8Mi ± 0%   256.2Mi ± 0%  +2.12% (p=0.000 n=10)
Hash1M/Sum224-8       250.6Mi ± 0%   256.3Mi ± 0%  +2.25% (p=0.000 n=10)
Hash1M/Sum256-8       250.8Mi ± 0%   256.2Mi ± 0%  +2.14% (p=0.000 n=10)
geomean               156.0Mi        159.3Mi       +2.11%

Change-Id: Ib72cf3c746d4ad73e52e5d31f6b4a834fd36d934
Reviewed-on: https://go-review.googlesource.com/c/go/+/678435
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
Reviewed-by: sophie zhao <zhaoxiaolin@loongson.cn>
Reviewed-by: Mark Freeman <markfreeman@google.com>
Reviewed-by: abner chenc <chenguoqi@loongson.cn>

diff --git a/src/crypto/internal/fips140/sha256/sha256block_loong64.s b/src/crypto/internal/fips140/sha256/sha256block_loong64.s
index e171d93e0ba5f0273fd233585decd5fde2511439..ad03cd9931b7f5c8a405bc50c18fe88929bb847d 100644 (file)
--- a/src/crypto/internal/fips140/sha256/sha256block_loong64.s
+++ b/src/crypto/internal/fips140/sha256/sha256block_loong64.s
@@ -52,6 +52,7 @@
 #define REGTMP3        R18
 #define REGTMP4        R7
 #define REGTMP5        R6
+#define REG_KT R19
 
 // W[i] = M[i]; for 0 <= i <= 15
 #define LOAD0(index) \
@@ -89,8 +90,9 @@
 // Ch(x, y, z) = (x AND y) XOR (NOT x AND z)
 //             = ((y XOR z) AND x) XOR z
 // Calculate T1 in REGTMP4
-#define SHA256T1(const, e, f, g, h) \
-       ADDV    $const, h; \
+#define SHA256T1(index, e, f, g, h) \
+       MOVW    (index*4)(REG_KT), REGTMP5; \
+       ADDV    REGTMP5, h; \
        ADD     REGTMP4, h; \
        ROTR    $6, e, REGTMP5; \
        ROTR    $11, e, REGTMP; \
@@ -122,19 +124,19 @@
 
 // Calculate T1 and T2, then e = d + T1 and a = T1 + T2.
 // The values for e and a are stored in d and h, ready for rotation.
-#define SHA256ROUND(const, a, b, c, d, e, f, g, h) \
-       SHA256T1(const, e, f, g, h); \
+#define SHA256ROUND(index, a, b, c, d, e, f, g, h) \
+       SHA256T1(index, e, f, g, h); \
        SHA256T2(a, b, c); \
        ADD     REGTMP4, d; \
        ADD     REGTMP1, REGTMP4, h
 
-#define SHA256ROUND0(index, const, a, b, c, d, e, f, g, h) \
+#define SHA256ROUND0(index, a, b, c, d, e, f, g, h) \
        LOAD0(index); \
-       SHA256ROUND(const, a, b, c, d, e, f, g, h)
+       SHA256ROUND(index, a, b, c, d, e, f, g, h)
 
-#define SHA256ROUND1(index, const, a, b, c, d, e, f, g, h) \
+#define SHA256ROUND1(index, a, b, c, d, e, f, g, h) \
        LOAD1(index); \
-       SHA256ROUND(const, a, b, c, d, e, f, g, h)
+       SHA256ROUND(index, a, b, c, d, e, f, g, h)
 
 // A stack frame size of 64 bytes is required here, because
 // the frame size used for data expansion is 64 bytes.
@@ -147,6 +149,8 @@ TEXT ·block(SB),NOSPLIT,$64-32
        AND     $~63, R6
        BEQ     R6, end
 
+       MOVV    $·_K(SB), REG_KT               // const table
+
        // p_len >= 64
        MOVV    dig+0(FP), R4
        ADDV    R5, R6, R25
@@ -160,71 +164,71 @@ TEXT ·block(SB),NOSPLIT,$64-32
        MOVW    (7*4)(R4), R15  // h = H7
 
 loop:
-       SHA256ROUND0(0,  0x428a2f98, R8,  R9,  R10, R11, R12, R13, R14, R15)
-       SHA256ROUND0(1,  0x71374491, R15, R8,  R9,  R10, R11, R12, R13, R14)
-       SHA256ROUND0(2,  0xb5c0fbcf, R14, R15, R8,  R9,  R10, R11, R12, R13)
-       SHA256ROUND0(3,  0xe9b5dba5, R13, R14, R15, R8,  R9,  R10, R11, R12)
-       SHA256ROUND0(4,  0x3956c25b, R12, R13, R14, R15, R8,  R9,  R10, R11)
-       SHA256ROUND0(5,  0x59f111f1, R11, R12, R13, R14, R15, R8,  R9,  R10)
-       SHA256ROUND0(6,  0x923f82a4, R10, R11, R12, R13, R14, R15, R8,  R9)
-       SHA256ROUND0(7,  0xab1c5ed5, R9,  R10, R11, R12, R13, R14, R15, R8)
-       SHA256ROUND0(8,  0xd807aa98, R8,  R9,  R10, R11, R12, R13, R14, R15)
-       SHA256ROUND0(9,  0x12835b01, R15, R8,  R9,  R10, R11, R12, R13, R14)
-       SHA256ROUND0(10, 0x243185be, R14, R15, R8,  R9,  R10, R11, R12, R13)
-       SHA256ROUND0(11, 0x550c7dc3, R13, R14, R15, R8,  R9,  R10, R11, R12)
-       SHA256ROUND0(12, 0x72be5d74, R12, R13, R14, R15, R8,  R9,  R10, R11)
-       SHA256ROUND0(13, 0x80deb1fe, R11, R12, R13, R14, R15, R8,  R9,  R10)
-       SHA256ROUND0(14, 0x9bdc06a7, R10, R11, R12, R13, R14, R15, R8,  R9)
-       SHA256ROUND0(15, 0xc19bf174, R9,  R10, R11, R12, R13, R14, R15, R8)
+       SHA256ROUND0(0,  R8,  R9,  R10, R11, R12, R13, R14, R15)
+       SHA256ROUND0(1,  R15, R8,  R9,  R10, R11, R12, R13, R14)
+       SHA256ROUND0(2,  R14, R15, R8,  R9,  R10, R11, R12, R13)
+       SHA256ROUND0(3,  R13, R14, R15, R8,  R9,  R10, R11, R12)
+       SHA256ROUND0(4,  R12, R13, R14, R15, R8,  R9,  R10, R11)
+       SHA256ROUND0(5,  R11, R12, R13, R14, R15, R8,  R9,  R10)
+       SHA256ROUND0(6,  R10, R11, R12, R13, R14, R15, R8,  R9)
+       SHA256ROUND0(7,  R9,  R10, R11, R12, R13, R14, R15, R8)
+       SHA256ROUND0(8,  R8,  R9,  R10, R11, R12, R13, R14, R15)
+       SHA256ROUND0(9,  R15, R8,  R9,  R10, R11, R12, R13, R14)
+       SHA256ROUND0(10, R14, R15, R8,  R9,  R10, R11, R12, R13)
+       SHA256ROUND0(11, R13, R14, R15, R8,  R9,  R10, R11, R12)
+       SHA256ROUND0(12, R12, R13, R14, R15, R8,  R9,  R10, R11)
+       SHA256ROUND0(13, R11, R12, R13, R14, R15, R8,  R9,  R10)
+       SHA256ROUND0(14, R10, R11, R12, R13, R14, R15, R8,  R9)
+       SHA256ROUND0(15, R9,  R10, R11, R12, R13, R14, R15, R8)
 
-       SHA256ROUND1(16, 0xe49b69c1, R8,  R9,  R10, R11, R12, R13, R14, R15)
-       SHA256ROUND1(17, 0xefbe4786, R15, R8,  R9,  R10, R11, R12, R13, R14)
-       SHA256ROUND1(18, 0x0fc19dc6, R14, R15, R8,  R9,  R10, R11, R12, R13)
-       SHA256ROUND1(19, 0x240ca1cc, R13, R14, R15, R8,  R9,  R10, R11, R12)
-       SHA256ROUND1(20, 0x2de92c6f, R12, R13, R14, R15, R8,  R9,  R10, R11)
-       SHA256ROUND1(21, 0x4a7484aa, R11, R12, R13, R14, R15, R8,  R9,  R10)
-       SHA256ROUND1(22, 0x5cb0a9dc, R10, R11, R12, R13, R14, R15, R8,  R9)
-       SHA256ROUND1(23, 0x76f988da, R9,  R10, R11, R12, R13, R14, R15, R8)
-       SHA256ROUND1(24, 0x983e5152, R8,  R9,  R10, R11, R12, R13, R14, R15)
-       SHA256ROUND1(25, 0xa831c66d, R15, R8,  R9,  R10, R11, R12, R13, R14)
-       SHA256ROUND1(26, 0xb00327c8, R14, R15, R8,  R9,  R10, R11, R12, R13)
-       SHA256ROUND1(27, 0xbf597fc7, R13, R14, R15, R8,  R9,  R10, R11, R12)
-       SHA256ROUND1(28, 0xc6e00bf3, R12, R13, R14, R15, R8,  R9,  R10, R11)
-       SHA256ROUND1(29, 0xd5a79147, R11, R12, R13, R14, R15, R8,  R9,  R10)
-       SHA256ROUND1(30, 0x06ca6351, R10, R11, R12, R13, R14, R15, R8,  R9)
-       SHA256ROUND1(31, 0x14292967, R9,  R10, R11, R12, R13, R14, R15, R8)
-       SHA256ROUND1(32, 0x27b70a85, R8,  R9,  R10, R11, R12, R13, R14, R15)
-       SHA256ROUND1(33, 0x2e1b2138, R15, R8,  R9,  R10, R11, R12, R13, R14)
-       SHA256ROUND1(34, 0x4d2c6dfc, R14, R15, R8,  R9,  R10, R11, R12, R13)
-       SHA256ROUND1(35, 0x53380d13, R13, R14, R15, R8,  R9,  R10, R11, R12)
-       SHA256ROUND1(36, 0x650a7354, R12, R13, R14, R15, R8,  R9,  R10, R11)
-       SHA256ROUND1(37, 0x766a0abb, R11, R12, R13, R14, R15, R8,  R9,  R10)
-       SHA256ROUND1(38, 0x81c2c92e, R10, R11, R12, R13, R14, R15, R8,  R9)
-       SHA256ROUND1(39, 0x92722c85, R9,  R10, R11, R12, R13, R14, R15, R8)
-       SHA256ROUND1(40, 0xa2bfe8a1, R8,  R9,  R10, R11, R12, R13, R14, R15)
-       SHA256ROUND1(41, 0xa81a664b, R15, R8,  R9,  R10, R11, R12, R13, R14)
-       SHA256ROUND1(42, 0xc24b8b70, R14, R15, R8,  R9,  R10, R11, R12, R13)
-       SHA256ROUND1(43, 0xc76c51a3, R13, R14, R15, R8,  R9,  R10, R11, R12)
-       SHA256ROUND1(44, 0xd192e819, R12, R13, R14, R15, R8,  R9,  R10, R11)
-       SHA256ROUND1(45, 0xd6990624, R11, R12, R13, R14, R15, R8,  R9,  R10)
-       SHA256ROUND1(46, 0xf40e3585, R10, R11, R12, R13, R14, R15, R8,  R9)
-       SHA256ROUND1(47, 0x106aa070, R9,  R10, R11, R12, R13, R14, R15, R8)
-       SHA256ROUND1(48, 0x19a4c116, R8,  R9,  R10, R11, R12, R13, R14, R15)
-       SHA256ROUND1(49, 0x1e376c08, R15, R8,  R9,  R10, R11, R12, R13, R14)
-       SHA256ROUND1(50, 0x2748774c, R14, R15, R8,  R9,  R10, R11, R12, R13)
-       SHA256ROUND1(51, 0x34b0bcb5, R13, R14, R15, R8,  R9,  R10, R11, R12)
-       SHA256ROUND1(52, 0x391c0cb3, R12, R13, R14, R15, R8,  R9,  R10, R11)
-       SHA256ROUND1(53, 0x4ed8aa4a, R11, R12, R13, R14, R15, R8,  R9,  R10)
-       SHA256ROUND1(54, 0x5b9cca4f, R10, R11, R12, R13, R14, R15, R8,  R9)
-       SHA256ROUND1(55, 0x682e6ff3, R9,  R10, R11, R12, R13, R14, R15, R8)
-       SHA256ROUND1(56, 0x748f82ee, R8,  R9,  R10, R11, R12, R13, R14, R15)
-       SHA256ROUND1(57, 0x78a5636f, R15, R8,  R9,  R10, R11, R12, R13, R14)
-       SHA256ROUND1(58, 0x84c87814, R14, R15, R8,  R9,  R10, R11, R12, R13)
-       SHA256ROUND1(59, 0x8cc70208, R13, R14, R15, R8,  R9,  R10, R11, R12)
-       SHA256ROUND1(60, 0x90befffa, R12, R13, R14, R15, R8,  R9,  R10, R11)
-       SHA256ROUND1(61, 0xa4506ceb, R11, R12, R13, R14, R15, R8,  R9,  R10)
-       SHA256ROUND1(62, 0xbef9a3f7, R10, R11, R12, R13, R14, R15, R8,  R9)
-       SHA256ROUND1(63, 0xc67178f2, R9,  R10, R11, R12, R13, R14, R15, R8)
+       SHA256ROUND1(16, R8,  R9,  R10, R11, R12, R13, R14, R15)
+       SHA256ROUND1(17, R15, R8,  R9,  R10, R11, R12, R13, R14)
+       SHA256ROUND1(18, R14, R15, R8,  R9,  R10, R11, R12, R13)
+       SHA256ROUND1(19, R13, R14, R15, R8,  R9,  R10, R11, R12)
+       SHA256ROUND1(20, R12, R13, R14, R15, R8,  R9,  R10, R11)
+       SHA256ROUND1(21, R11, R12, R13, R14, R15, R8,  R9,  R10)
+       SHA256ROUND1(22, R10, R11, R12, R13, R14, R15, R8,  R9)
+       SHA256ROUND1(23, R9,  R10, R11, R12, R13, R14, R15, R8)
+       SHA256ROUND1(24, R8,  R9,  R10, R11, R12, R13, R14, R15)
+       SHA256ROUND1(25, R15, R8,  R9,  R10, R11, R12, R13, R14)
+       SHA256ROUND1(26, R14, R15, R8,  R9,  R10, R11, R12, R13)
+       SHA256ROUND1(27, R13, R14, R15, R8,  R9,  R10, R11, R12)
+       SHA256ROUND1(28, R12, R13, R14, R15, R8,  R9,  R10, R11)
+       SHA256ROUND1(29, R11, R12, R13, R14, R15, R8,  R9,  R10)
+       SHA256ROUND1(30, R10, R11, R12, R13, R14, R15, R8,  R9)
+       SHA256ROUND1(31, R9,  R10, R11, R12, R13, R14, R15, R8)
+       SHA256ROUND1(32, R8,  R9,  R10, R11, R12, R13, R14, R15)
+       SHA256ROUND1(33, R15, R8,  R9,  R10, R11, R12, R13, R14)
+       SHA256ROUND1(34, R14, R15, R8,  R9,  R10, R11, R12, R13)
+       SHA256ROUND1(35, R13, R14, R15, R8,  R9,  R10, R11, R12)
+       SHA256ROUND1(36, R12, R13, R14, R15, R8,  R9,  R10, R11)
+       SHA256ROUND1(37, R11, R12, R13, R14, R15, R8,  R9,  R10)
+       SHA256ROUND1(38, R10, R11, R12, R13, R14, R15, R8,  R9)
+       SHA256ROUND1(39, R9,  R10, R11, R12, R13, R14, R15, R8)
+       SHA256ROUND1(40, R8,  R9,  R10, R11, R12, R13, R14, R15)
+       SHA256ROUND1(41, R15, R8,  R9,  R10, R11, R12, R13, R14)
+       SHA256ROUND1(42, R14, R15, R8,  R9,  R10, R11, R12, R13)
+       SHA256ROUND1(43, R13, R14, R15, R8,  R9,  R10, R11, R12)
+       SHA256ROUND1(44, R12, R13, R14, R15, R8,  R9,  R10, R11)
+       SHA256ROUND1(45, R11, R12, R13, R14, R15, R8,  R9,  R10)
+       SHA256ROUND1(46, R10, R11, R12, R13, R14, R15, R8,  R9)
+       SHA256ROUND1(47, R9,  R10, R11, R12, R13, R14, R15, R8)
+       SHA256ROUND1(48, R8,  R9,  R10, R11, R12, R13, R14, R15)
+       SHA256ROUND1(49, R15, R8,  R9,  R10, R11, R12, R13, R14)
+       SHA256ROUND1(50, R14, R15, R8,  R9,  R10, R11, R12, R13)
+       SHA256ROUND1(51, R13, R14, R15, R8,  R9,  R10, R11, R12)
+       SHA256ROUND1(52, R12, R13, R14, R15, R8,  R9,  R10, R11)
+       SHA256ROUND1(53, R11, R12, R13, R14, R15, R8,  R9,  R10)
+       SHA256ROUND1(54, R10, R11, R12, R13, R14, R15, R8,  R9)
+       SHA256ROUND1(55, R9,  R10, R11, R12, R13, R14, R15, R8)
+       SHA256ROUND1(56, R8,  R9,  R10, R11, R12, R13, R14, R15)
+       SHA256ROUND1(57, R15, R8,  R9,  R10, R11, R12, R13, R14)
+       SHA256ROUND1(58, R14, R15, R8,  R9,  R10, R11, R12, R13)
+       SHA256ROUND1(59, R13, R14, R15, R8,  R9,  R10, R11, R12)
+       SHA256ROUND1(60, R12, R13, R14, R15, R8,  R9,  R10, R11)
+       SHA256ROUND1(61, R11, R12, R13, R14, R15, R8,  R9,  R10)
+       SHA256ROUND1(62, R10, R11, R12, R13, R14, R15, R8,  R9)
+       SHA256ROUND1(63, R9,  R10, R11, R12, R13, R14, R15, R8)
 
        MOVW    (0*4)(R4), REGTMP
        MOVW    (1*4)(R4), REGTMP1