MIPS: csum_partial: Improve instruction parallelism.

Computing sum introduces true data dependency. This patch removes some
true data depdendencies, hence increases instruction level parallelism.

This patch brings up to 50% csum performance gain on Loongson 3a.

One example about how this patch works is in CSUM_BIGCHUNK1:
// ** original **    vs    ** patch applied **
    ADDC(sum, t0)           ADDC(t0, t1)
    ADDC(sum, t1)           ADDC(t2, t3)
    ADDC(sum, t2)           ADDC(sum, t0)
    ADDC(sum, t3)           ADDC(sum, t2)

In the original implementation, each ADDC(sum, ...) depends on the sum
value updated by previous ADDC(as source operand).

With this patch applied, the first two ADDC operations are independent,
hence can be executed simultaneously if possible.

Another example is in the "copy and sum calculating chunk":
// ** original **    vs    ** patch applied **
    STORE(t0, UNIT(0) ...   STORE(t0, UNIT(0) ...
    ADDC(sum, t0)           ADDC(t0, t1)
    STORE(t1, UNIT(1) ...   STORE(t1, UNIT(1) ...
    ADDC(sum, t1)           ADDC(sum, t0)
    STORE(t2, UNIT(2) ...   STORE(t2, UNIT(2) ...
    ADDC(sum, t2)           ADDC(t2, t3)
    STORE(t3, UNIT(3) ...   STORE(t3, UNIT(3) ...
    ADDC(sum, t3)           ADDC(sum, t2)

With this patch applied, ADDC and the **next next** ADDC are independent.

Signed-off-by: chenj <chenj@lemote.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/9608/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

arch/mips/lib/csum_partial.S

@@ -76,10 +76,10 @@
 	LOAD	_t1, (offset + UNIT(1))(src);			\
 	LOAD	_t2, (offset + UNIT(2))(src);			\
 	LOAD	_t3, (offset + UNIT(3))(src);			\
+	ADDC(_t0, _t1);						\
+	ADDC(_t2, _t3);						\
 	ADDC(sum, _t0);						\
-	ADDC(sum, _t1);						\
-	ADDC(sum, _t2);						\
-	ADDC(sum, _t3)
+	ADDC(sum, _t2)
 
 #ifdef USE_DOUBLE
 #define CSUM_BIGCHUNK(src, offset, sum, _t0, _t1, _t2, _t3)	\
@@ -504,21 +504,21 @@ LEAF(csum_partial)
 	SUB	len, len, 8*NBYTES
 	ADD	src, src, 8*NBYTES
 	STORE(t0, UNIT(0)(dst),	.Ls_exc\@)
-	ADDC(sum, t0)
+	ADDC(t0, t1)
 	STORE(t1, UNIT(1)(dst),	.Ls_exc\@)
-	ADDC(sum, t1)
+	ADDC(sum, t0)
 	STORE(t2, UNIT(2)(dst),	.Ls_exc\@)
-	ADDC(sum, t2)
+	ADDC(t2, t3)
 	STORE(t3, UNIT(3)(dst),	.Ls_exc\@)
-	ADDC(sum, t3)
+	ADDC(sum, t2)
 	STORE(t4, UNIT(4)(dst),	.Ls_exc\@)
-	ADDC(sum, t4)
+	ADDC(t4, t5)
 	STORE(t5, UNIT(5)(dst),	.Ls_exc\@)
-	ADDC(sum, t5)
+	ADDC(sum, t4)
 	STORE(t6, UNIT(6)(dst),	.Ls_exc\@)
-	ADDC(sum, t6)
+	ADDC(t6, t7)
 	STORE(t7, UNIT(7)(dst),	.Ls_exc\@)
-	ADDC(sum, t7)
+	ADDC(sum, t6)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, 8*NBYTES
 	bgez	len, 1b
@@ -544,13 +544,13 @@ LEAF(csum_partial)
 	SUB	len, len, 4*NBYTES
 	ADD	src, src, 4*NBYTES
 	STORE(t0, UNIT(0)(dst),	.Ls_exc\@)
-	ADDC(sum, t0)
+	ADDC(t0, t1)
 	STORE(t1, UNIT(1)(dst),	.Ls_exc\@)
-	ADDC(sum, t1)
+	ADDC(sum, t0)
 	STORE(t2, UNIT(2)(dst),	.Ls_exc\@)
-	ADDC(sum, t2)
+	ADDC(t2, t3)
 	STORE(t3, UNIT(3)(dst),	.Ls_exc\@)
-	ADDC(sum, t3)
+	ADDC(sum, t2)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, 4*NBYTES
 	beqz	len, .Ldone\@
@@ -649,13 +649,13 @@ LEAF(csum_partial)
 	nop				# improves slotting
 #endif
 	STORE(t0, UNIT(0)(dst),	.Ls_exc\@)
-	ADDC(sum, t0)
+	ADDC(t0, t1)
 	STORE(t1, UNIT(1)(dst),	.Ls_exc\@)
-	ADDC(sum, t1)
+	ADDC(sum, t0)
 	STORE(t2, UNIT(2)(dst),	.Ls_exc\@)
-	ADDC(sum, t2)
+	ADDC(t2, t3)
 	STORE(t3, UNIT(3)(dst),	.Ls_exc\@)
-	ADDC(sum, t3)
+	ADDC(sum, t2)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, 4*NBYTES
 	bne	len, rem, 1b