diff options
| author | Mauro Carvalho Chehab <mchehab@redhat.com> | 2012-03-27 11:32:29 -0300 |
|---|---|---|
| committer | Mauro Carvalho Chehab <mchehab@redhat.com> | 2012-03-27 11:32:29 -0300 |
| commit | 50953e0640b3473dcb409d5d0d938c2742c93b0d (patch) | |
| tree | 3b0dc374e61564fbbd8adff92c8fae16fdeb423a /arch/x86/crypto/serpent-sse2-i586-asm_32.S | |
| parent | f92c97c8bd77992ff8bd6ef29a23dc82dca799cb (diff) | |
| parent | 626cf236608505d376e4799adb4f7eb00a8594af (diff) | |
Merge branch 'poll' into staging/for_v3.4
* poll: (5970 commits)
poll: add poll_requested_events() and poll_does_not_wait() functions
crc32: select an algorithm via Kconfig
crc32: add self-test code for crc32c
crypto: crc32c should use library implementation
crc32: bolt on crc32c
crc32: add note about this patchset to crc32.c
crc32: optimize loop counter for x86
crc32: add slice-by-8 algorithm to existing code
crc32: make CRC_*_BITS definition correspond to actual bit counts
crc32: fix mixing of endian-specific types
crc32: miscellaneous cleanups
crc32: simplify unit test code
crc32: move long comment about crc32 fundamentals to Documentation/
crc32: remove two instances of trailing whitespaces
checkpatch: check for quoted strings broken across lines
checkpatch: whitespace - add/remove blank lines
checkpatch: warn on use of yield()
checkpatch: add --strict tests for braces, comments and casts
checkpatch: add [] to type extensions
checkpatch: high precedence operators do not require additional parentheses in #defines
...
Diffstat (limited to 'arch/x86/crypto/serpent-sse2-i586-asm_32.S')
| -rw-r--r-- | arch/x86/crypto/serpent-sse2-i586-asm_32.S | 29 |
1 files changed, 13 insertions, 16 deletions
diff --git a/arch/x86/crypto/serpent-sse2-i586-asm_32.S b/arch/x86/crypto/serpent-sse2-i586-asm_32.S index 4e37677ca85..c00053d42f9 100644 --- a/arch/x86/crypto/serpent-sse2-i586-asm_32.S +++ b/arch/x86/crypto/serpent-sse2-i586-asm_32.S @@ -463,23 +463,20 @@ pand x0, x4; \ pxor x2, x4; -#define transpose_4x4(x0, x1, x2, x3, t1, t2, t3) \ - movdqa x2, t3; \ - movdqa x0, t1; \ - unpcklps x3, t3; \ +#define transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \ movdqa x0, t2; \ - unpcklps x1, t1; \ - unpckhps x1, t2; \ - movdqa t3, x1; \ - unpckhps x3, x2; \ - movdqa t1, x0; \ - movhlps t1, x1; \ - movdqa t2, t1; \ - movlhps t3, x0; \ - movlhps x2, t1; \ - movhlps t2, x2; \ - movdqa x2, x3; \ - movdqa t1, x2; + punpckldq x1, x0; \ + punpckhdq x1, t2; \ + movdqa x2, t1; \ + punpckhdq x3, x2; \ + punpckldq x3, t1; \ + movdqa x0, x1; \ + punpcklqdq t1, x0; \ + punpckhqdq t1, x1; \ + movdqa t2, x3; \ + punpcklqdq x2, t2; \ + punpckhqdq x2, x3; \ + movdqa t2, x2; #define read_blocks(in, x0, x1, x2, x3, t0, t1, t2) \ movdqu (0*4*4)(in), x0; \ |