Fixed PPC SHA1

[linux@horizon.com]

Okay, here's a tested and working version (the earlier version worked,
too) of a better-scheduled PPC SHA1.  This is about 15% faster that the
current sha1ppc.S on a G4, and 5% faster on a G5 when hashing 10 million
bytes, unaligned.  (The G5 ratio seems to get better as the sizes fall.)

It's also somewhat smaller, due to using load-multiple instructions.

I have a variant that uses load string (lswi) to load the values to be
hashed that is a few percent faster on a G5, but a few percent slower
on a G4.  It's also 52 bytes smaller (out of 4000).

Does anyone have any feeling for the ratio of G4 and G5 machines
out there?  I presume for that small a percentage, run-time processor
detection isn't worth it.  (Cc: to linuxppc-dev for the experts on
this question.)

I've tried using lmw to load the data, and it's faster if the data is
aligned, but it absolutely dies if the data is not.  And due to git's
variable-sized hash prefix, most of git's hashes are of unaligned data.

(No copyright is claimed on the changes to Paul Mackerras' work below.
Enjoy.)

/*
 * SHA-1 implementation for PowerPC.
 *
 * Copyright (C) 2005 Paul Mackerras <paulus@samba.org>
 */

/*
 * PowerPC calling convention:
 * %r0 - volatile temp
 * %r1 - stack pointer.
 * %r2 - reserved
 * %r3-%r12 - Incoming arguments & return values; volatile.
 * %r13-%r31 - Callee-save registers
 * %lr - Return address, volatile
 * %ctr - volatile
 *
 * Register usage in this routine:
 * %r0 - temp
 * %r3 - argument (pointer to 5 words of SHA state)
 * %r4 - argument (pointer to data to hash)
 * %r5 - Contant K in SHA round (initially number of blocks to hash)
 * %r6-%r10 - Working copies of SHA variables A..E (actually E..A order)
 * %r11-%r26 - Data being hashed W[].
 * %r27-%r31 - Previous copies of A..E, for final add back.
 * %ctr - loop count
 */


/*
 * We roll the registers for A, B, C, D, E around on each
 * iteration; E on iteration t is D on iteration t+1, and so on.
 * We use registers 6 - 10 for this.  (Registers 27 - 31 hold
 * the previous values.)
 */
#define RA(t)	(((t)+4)%5+6)
#define RB(t)	(((t)+3)%5+6)
#define RC(t)	(((t)+2)%5+6)
#define RD(t)	(((t)+1)%5+6)
#define RE(t)	(((t)+0)%5+6)

/* We use registers 11 - 26 for the W values */
#define W(t)	((t)%16+11)

/* Register 5 is used for the constant k */

/*
 * The basic SHA-1 round function is:
 * E += ROTL(A,5) + F(B,C,D) + W[i] + K;  B = ROTL(B,30)
 * Then the variables are renamed: (A,B,C,D,E) = (E,A,B,C,D).
 *
 * Every 20 rounds, the function F() and the contant K changes:
 * - 20 rounds of f0(b,c,d) = "bit wise b ? c : d" =  (^b & d) + (b & c)
 * - 20 rounds of f1(b,c,d) = b^c^d = (b^d)^c
 * - 20 rounds of f2(b,c,d) = majority(b,c,d) = (b&d) + ((b^d)&c)
 * - 20 more rounds of f1(b,c,d)
 *
 * These are all scheduled for near-optimal performance on a G4.
 * The G4 is a 3-issue out-of-order machine with 3 ALUs, but it can only
 * *consider* starting the oldest 3 instructions per cycle.  So to get
 * maximum performace out of it, you have to treat it as an in-order
 * machine.  Which means interleaving the computation round t with the
 * computation of W[t+4].
 *
 * The first 16 rounds use W values loaded directly from memory, while the
 * remianing 64 use values computed from those first 16.  We preload
 * 4 values before starting, so there are three kinds of rounds:
 * - The first 12 (all f0) also load the W values from memory.
 * - The next 64 compute W(i+4) in parallel. 8*f0, 20*f1, 20*f2, 16*f1.
 * - The last 4 (all f1) do not do anything with W.
 *
 * Therefore, we have 6 different round functions:
 * STEPD0_LOAD(t,s) - Perform round t and load W(s).  s < 16
 * STEPD0_UPDATE(t,s) - Perform round t and compute W(s).  s >= 16.
 * STEPD1_UPDATE(t,s)
 * STEPD2_UPDATE(t,s)
 * STEPD1(t) - Perform round t with no load or update.
 * 
 * The G5 is more fully out-of-order, and can find the parallelism
 * by itself.  The big limit is that it has a 2-cycle ALU latency, so
 * even though it's 2-way, the code has to be scheduled as if it's
 * 4-way, which can be a limit.  To help it, we try to schedule the
 * read of RA(t) as late as possible so it doesn't stall waiting for
 * the previous round's RE(t-1), and we try to rotate RB(t) as early
 * as possible while reading RC(t) (= RB(t-1)) as late as possible.
 */

/* the initial loads. */
#define LOADW(s) \
	lwz	W(s),(s)*4(%r4)

/*
 * Perform a step with F0, and load W(s).  Uses W(s) as a temporary
 * before loading it.
 * This is actually 10 instructions, which is an awkward fit.
 * It can execute grouped as listed, or delayed one instruction.
 * (If delayed two instructions, there is a stall before the start of the
 * second line.)  Thus, two iterations take 7 cycles, 3.5 cycles per round.
 */
#define STEPD0_LOAD(t,s) \
add RE(t),RE(t),W(t); andc   %r0,RD(t),RB(t);  and    W(s),RC(t),RB(t); \
add RE(t),RE(t),%r0;  rotlwi %r0,RA(t),5;      rotlwi RB(t),RB(t),30;   \
add RE(t),RE(t),W(s); add    %r0,%r0,%r5;      lwz    W(s),(s)*4(%r4);  \
add RE(t),RE(t),%r0

/*
 * This is likewise awkward, 13 instructions.  However, it can also
 * execute starting with 2 out of 3 possible moduli, so it does 2 rounds
 * in 9 cycles, 4.5 cycles/round.
 */
#define STEPD0_UPDATE(t,s,loadk...) \
add RE(t),RE(t),W(t); andc   %r0,RD(t),RB(t); xor    W(s),W((s)-16),W((s)-3); \
add RE(t),RE(t),%r0;  and    %r0,RC(t),RB(t); xor    W(s),W(s),W((s)-8);      \
add RE(t),RE(t),%r0;  rotlwi %r0,RA(t),5;     xor    W(s),W(s),W((s)-14);     \
add RE(t),RE(t),%r5;  loadk; rotlwi RB(t),RB(t),30;  rotlwi W(s),W(s),1;     \
add RE(t),RE(t),%r0

/* Nicely optimal.  Conveniently, also the most common. */
#define STEPD1_UPDATE(t,s,loadk...) \
add RE(t),RE(t),W(t); xor    %r0,RD(t),RB(t); xor    W(s),W((s)-16),W((s)-3); \
add RE(t),RE(t),%r5;  loadk; xor %r0,%r0,RC(t);  xor W(s),W(s),W((s)-8);      \
add RE(t),RE(t),%r0;  rotlwi %r0,RA(t),5;     xor    W(s),W(s),W((s)-14);     \
add RE(t),RE(t),%r0;  rotlwi RB(t),RB(t),30;  rotlwi W(s),W(s),1

/*
 * The naked version, no UPDATE, for the last 4 rounds.  3 cycles per.
 * We could use W(s) as a temp register, but we don't need it.
 */
#define STEPD1(t) \
                        add   RE(t),RE(t),W(t); xor    %r0,RD(t),RB(t); \
rotlwi RB(t),RB(t),30;  add   RE(t),RE(t),%r5;  xor    %r0,%r0,RC(t);   \
add    RE(t),RE(t),%r0; rotlwi %r0,RA(t),5;     /* spare slot */        \
add    RE(t),RE(t),%r0

/*
 * 14 instructions, 5 cycles per.  The majority function is a bit
 * awkward to compute.  This can execute with a 1-instruction delay,
 * but it causes a 2-instruction delay, which triggers a stall.
 */
#define STEPD2_UPDATE(t,s,loadk...) \
add RE(t),RE(t),W(t); and    %r0,RD(t),RB(t); xor    W(s),W((s)-16),W((s)-3); \
add RE(t),RE(t),%r0;  xor    %r0,RD(t),RB(t); xor    W(s),W(s),W((s)-8);      \
add RE(t),RE(t),%r5;  loadk; and %r0,%r0,RC(t);  xor W(s),W(s),W((s)-14);     \
add RE(t),RE(t),%r0;  rotlwi %r0,RA(t),5;     rotlwi W(s),W(s),1;             \
add RE(t),RE(t),%r0;  rotlwi RB(t),RB(t),30

#define STEP0_LOAD4(t,s)		\
	STEPD0_LOAD(t,s);		\
	STEPD0_LOAD((t+1),(s)+1);	\
	STEPD0_LOAD((t)+2,(s)+2);	\
	STEPD0_LOAD((t)+3,(s)+3)

#define STEPUP4(fn, t, s, loadk...)		\
	STEP##fn##_UPDATE(t,s,);		\
	STEP##fn##_UPDATE((t)+1,(s)+1,);	\
	STEP##fn##_UPDATE((t)+2,(s)+2,);	\
	STEP##fn##_UPDATE((t)+3,(s)+3,loadk)

#define STEPUP20(fn, t, s, loadk...)	\
	STEPUP4(fn, t, s,);		\
	STEPUP4(fn, (t)+4, (s)+4,);	\
	STEPUP4(fn, (t)+8, (s)+8,);	\
	STEPUP4(fn, (t)+12, (s)+12,);	\
	STEPUP4(fn, (t)+16, (s)+16, loadk)

	.globl	sha1_core
sha1_core:
	stwu	%r1,-80(%r1)
	stmw	%r13,4(%r1)

	/* Load up A - E */
	lmw	%r27,0(%r3)

	mtctr	%r5

1:
	LOADW(0)
	lis	%r5,0x5a82
	mr	RE(0),%r31
	LOADW(1)
	mr	RD(0),%r30
	mr	RC(0),%r29
	LOADW(2)
	ori	%r5,%r5,0x7999	/* K0-19 */
	mr	RB(0),%r28
	LOADW(3)
	mr	RA(0),%r27

	STEP0_LOAD4(0, 4)
	STEP0_LOAD4(4, 8)
	STEP0_LOAD4(8, 12)
	STEPUP4(D0, 12, 16,)
	STEPUP4(D0, 16, 20, lis %r5,0x6ed9)

	ori	%r5,%r5,0xeba1	/* K20-39 */
	STEPUP20(D1, 20, 24, lis %r5,0x8f1b)

	ori	%r5,%r5,0xbcdc	/* K40-59 */
	STEPUP20(D2, 40, 44, lis %r5,0xca62)

	ori	%r5,%r5,0xc1d6	/* K60-79 */
	STEPUP4(D1, 60, 64,)
	STEPUP4(D1, 64, 68,)
	STEPUP4(D1, 68, 72,)
	STEPUP4(D1, 72, 76,)
	addi	%r4,%r4,64
	STEPD1(76)
	STEPD1(77)
	STEPD1(78)
	STEPD1(79)

	/* Add results to original values */
	add	%r31,%r31,RE(0)
	add	%r30,%r30,RD(0)
	add	%r29,%r29,RC(0)
	add	%r28,%r28,RB(0)
	add	%r27,%r27,RA(0)

	bdnz	1b

	/* Save final hash, restore registers, and return */
	stmw	%r27,0(%r3)
	lmw	%r13,4(%r1)
	addi	%r1,%r1,80
	blr