crypto/internal/fips140/subtle: add assembly implementation of xorBytes for mips64x

goos: linux
goarch: mips64le
pkg: crypto/subtle
                                     │  oldsubtle   │             newsubtle              │
                                     │    sec/op    │   sec/op     vs base               │
ConstantTimeByteEq-4                    5.011n ± 0%   5.014n ± 0%        ~ (p=0.110 n=8)
ConstantTimeEq-4                        3.342n ± 0%   3.342n ± 0%        ~ (p=0.993 n=8)
ConstantTimeLessOrEq-4                  4.455n ± 0%   4.458n ± 0%        ~ (p=0.182 n=8)
XORBytes/8Bytes-4                       36.48n ± 0%   26.73n ± 0%  -26.74% (p=0.000 n=8)
XORBytes/128Bytes-4                     70.21n ± 0%   50.14n ± 0%  -28.59% (p=0.000 n=8)
XORBytes/2048Bytes-4                    566.1n ± 0%   257.2n ± 0%  -54.58% (p=0.000 n=8)
XORBytes/8192Bytes-4                   2123.0n ± 0%   966.8n ± 0%  -54.46% (p=0.000 n=8)
XORBytes/32768Bytes-4                  13.740µ ± 0%   5.614µ ± 0%  -59.14% (p=0.000 n=8)
XORBytesAlignment/8Bytes0Offset-4       38.98n ± 0%   26.53n ± 0%  -31.95% (p=0.000 n=8)
XORBytesAlignment/8Bytes1Offset-4       43.27n ± 0%   26.54n ± 0%  -38.68% (p=0.000 n=8)
XORBytesAlignment/8Bytes2Offset-4       43.28n ± 0%   26.54n ± 0%  -38.69% (p=0.000 n=8)
XORBytesAlignment/8Bytes3Offset-4       43.32n ± 0%   26.54n ± 0%  -38.74% (p=0.000 n=8)
XORBytesAlignment/8Bytes4Offset-4       43.49n ± 0%   26.53n ± 0%  -38.99% (p=0.000 n=8)
XORBytesAlignment/8Bytes5Offset-4       43.53n ± 0%   26.54n ± 0%  -39.03% (p=0.000 n=8)
XORBytesAlignment/8Bytes6Offset-4       43.48n ± 0%   26.53n ± 0%  -38.98% (p=0.000 n=8)
XORBytesAlignment/8Bytes7Offset-4       43.46n ± 1%   26.53n ± 0%  -38.96% (p=0.000 n=8)
XORBytesAlignment/128Bytes0Offset-4     71.84n ± 0%   47.70n ± 1%  -33.60% (p=0.000 n=8)
XORBytesAlignment/128Bytes1Offset-4    260.60n ± 0%   59.87n ± 0%  -77.03% (p=0.000 n=8)
XORBytesAlignment/128Bytes2Offset-4    260.60n ± 0%   59.81n ± 0%  -77.05% (p=0.000 n=8)
XORBytesAlignment/128Bytes3Offset-4    260.55n ± 0%   59.89n ± 0%  -77.01% (p=0.000 n=8)
XORBytesAlignment/128Bytes4Offset-4    260.60n ± 0%   59.84n ± 0%  -77.04% (p=0.000 n=8)
XORBytesAlignment/128Bytes5Offset-4    260.70n ± 0%   59.82n ± 0%  -77.05% (p=0.000 n=8)
XORBytesAlignment/128Bytes6Offset-4    260.60n ± 0%   59.89n ± 0%  -77.02% (p=0.000 n=8)
XORBytesAlignment/128Bytes7Offset-4    260.70n ± 0%   59.85n ± 0%  -77.04% (p=0.000 n=8)
XORBytesAlignment/2048Bytes0Offset-4    552.2n ± 1%   250.0n ± 0%  -54.73% (p=0.000 n=8)
XORBytesAlignment/2048Bytes1Offset-4   3603.0n ± 0%   548.6n ± 0%  -84.77% (p=0.000 n=8)
XORBytesAlignment/2048Bytes2Offset-4   3602.0n ± 0%   548.6n ± 0%  -84.77% (p=0.000 n=8)
XORBytesAlignment/2048Bytes3Offset-4   3604.0n ± 0%   548.6n ± 0%  -84.78% (p=0.000 n=8)
XORBytesAlignment/2048Bytes4Offset-4   3603.5n ± 0%   548.9n ± 0%  -84.77% (p=0.000 n=8)
XORBytesAlignment/2048Bytes5Offset-4   3603.0n ± 0%   548.8n ± 0%  -84.77% (p=0.000 n=8)
XORBytesAlignment/2048Bytes6Offset-4   3602.0n ± 0%   548.6n ± 0%  -84.77% (p=0.000 n=8)
XORBytesAlignment/2048Bytes7Offset-4   3601.5n ± 0%   548.5n ± 0%  -84.77% (p=0.000 n=8)
geomean                                 220.0n        81.91n       -62.77%

                                     │  oldsubtle   │               newsubtle               │
                                     │     B/s      │      B/s       vs base                │
XORBytes/8Bytes-4                      209.1Mi ± 0%    285.5Mi ± 0%   +36.52% (p=0.000 n=8)
XORBytes/128Bytes-4                    1.698Gi ± 0%    2.378Gi ± 0%   +40.04% (p=0.000 n=8)
XORBytes/2048Bytes-4                   3.369Gi ± 0%    7.418Gi ± 0%  +120.17% (p=0.000 n=8)
XORBytes/8192Bytes-4                   3.594Gi ± 0%    7.892Gi ± 0%  +119.59% (p=0.000 n=8)
XORBytes/32768Bytes-4                  2.221Gi ± 0%    5.436Gi ± 0%  +144.76% (p=0.000 n=8)
XORBytesAlignment/8Bytes0Offset-4      195.7Mi ± 0%    287.6Mi ± 0%   +46.96% (p=0.000 n=8)
XORBytesAlignment/8Bytes1Offset-4      176.3Mi ± 0%    287.5Mi ± 0%   +63.06% (p=0.000 n=8)
XORBytesAlignment/8Bytes2Offset-4      176.3Mi ± 0%    287.4Mi ± 0%   +63.07% (p=0.000 n=8)
XORBytesAlignment/8Bytes3Offset-4      176.1Mi ± 0%    287.5Mi ± 0%   +63.25% (p=0.000 n=8)
XORBytesAlignment/8Bytes4Offset-4      175.5Mi ± 0%    287.6Mi ± 0%   +63.90% (p=0.000 n=8)
XORBytesAlignment/8Bytes5Offset-4      175.3Mi ± 0%    287.5Mi ± 0%   +64.02% (p=0.000 n=8)
XORBytesAlignment/8Bytes6Offset-4      175.5Mi ± 0%    287.6Mi ± 0%   +63.86% (p=0.000 n=8)
XORBytesAlignment/8Bytes7Offset-4      175.5Mi ± 0%    287.6Mi ± 0%   +63.85% (p=0.000 n=8)
XORBytesAlignment/128Bytes0Offset-4    1.659Gi ± 0%    2.499Gi ± 1%   +50.61% (p=0.000 n=8)
XORBytesAlignment/128Bytes1Offset-4    468.4Mi ± 0%   2039.0Mi ± 0%  +335.30% (p=0.000 n=8)
XORBytesAlignment/128Bytes2Offset-4    468.4Mi ± 0%   2040.9Mi ± 0%  +335.73% (p=0.000 n=8)
XORBytesAlignment/128Bytes3Offset-4    468.5Mi ± 0%   2038.1Mi ± 0%  +335.02% (p=0.000 n=8)
XORBytesAlignment/128Bytes4Offset-4    468.4Mi ± 0%   2040.0Mi ± 0%  +335.52% (p=0.000 n=8)
XORBytesAlignment/128Bytes5Offset-4    468.2Mi ± 0%   2040.5Mi ± 0%  +335.82% (p=0.000 n=8)
XORBytesAlignment/128Bytes6Offset-4    468.4Mi ± 0%   2038.2Mi ± 0%  +335.13% (p=0.000 n=8)
XORBytesAlignment/128Bytes7Offset-4    468.2Mi ± 0%   2039.4Mi ± 0%  +335.58% (p=0.000 n=8)
XORBytesAlignment/2048Bytes0Offset-4   3.454Gi ± 1%    7.629Gi ± 0%  +120.90% (p=0.000 n=8)
XORBytesAlignment/2048Bytes1Offset-4   542.1Mi ± 0%   3560.1Mi ± 0%  +556.68% (p=0.000 n=8)
XORBytesAlignment/2048Bytes2Offset-4   542.3Mi ± 0%   3560.1Mi ± 0%  +556.48% (p=0.000 n=8)
XORBytesAlignment/2048Bytes3Offset-4   541.9Mi ± 0%   3560.0Mi ± 0%  +556.93% (p=0.000 n=8)
XORBytesAlignment/2048Bytes4Offset-4   542.0Mi ± 0%   3558.8Mi ± 0%  +556.67% (p=0.000 n=8)
XORBytesAlignment/2048Bytes5Offset-4   542.1Mi ± 3%   3558.8Mi ± 0%  +556.53% (p=0.000 n=8)
XORBytesAlignment/2048Bytes6Offset-4   542.2Mi ± 0%   3560.2Mi ± 0%  +556.57% (p=0.000 n=8)
XORBytesAlignment/2048Bytes7Offset-4   542.3Mi ± 0%   3560.5Mi ± 0%  +556.56% (p=0.000 n=8)
geomean                                514.9Mi         1.496Gi       +197.56%

Change-Id: I649fa6bfca31296d65cccdf5fceb3dcfa0c588a1
Reviewed-on: https://go-review.googlesource.com/c/go/+/666255


Reviewed-by: Keith Randall <khr@google.com>
Auto-Submit: Keith Randall <khr@golang.org>
Reviewed-by: Cherry Mui <cherryyz@google.com>
Reviewed-by: Keith Randall <khr@golang.org>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>