* [Qemu-devel] [PULL 1/2] target-alpha: Rewrite helper_cmpbge using bit tests
2015-09-02 19:58 [Qemu-devel] [PULL 0/2] target-alpha cmpbge improvements Richard Henderson
@ 2015-09-02 19:58 ` Richard Henderson
2015-09-02 19:58 ` [Qemu-devel] [PULL 2/2] target-alpha: Special case cmpbge with zero Richard Henderson
2015-09-03 12:05 ` [Qemu-devel] [PULL 0/2] target-alpha cmpbge improvements Peter Maydell
2 siblings, 0 replies; 4+ messages in thread
From: Richard Henderson @ 2015-09-02 19:58 UTC (permalink / raw)
To: qemu-devel; +Cc: peter.maydell
Not quite as good as using a proper host vector compare,
but certainly better than a loop.
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
target-alpha/int_helper.c | 39 ++++++++++++++++++++++++++-------------
1 file changed, 26 insertions(+), 13 deletions(-)
diff --git a/target-alpha/int_helper.c b/target-alpha/int_helper.c
index 74f38cb..4a6e955 100644
--- a/target-alpha/int_helper.c
+++ b/target-alpha/int_helper.c
@@ -58,20 +58,33 @@ uint64_t helper_zap(uint64_t val, uint64_t mask)
return helper_zapnot(val, ~mask);
}
-uint64_t helper_cmpbge(uint64_t op1, uint64_t op2)
+uint64_t helper_cmpbge(uint64_t a, uint64_t b)
{
- uint8_t opa, opb, res;
- int i;
-
- res = 0;
- for (i = 0; i < 8; i++) {
- opa = op1 >> (i * 8);
- opb = op2 >> (i * 8);
- if (opa >= opb) {
- res |= 1 << i;
- }
- }
- return res;
+ uint64_t mask = 0x00ff00ff00ff00ffULL;
+ uint64_t test = 0x0100010001000100ULL;
+ uint64_t al, ah, bl, bh, cl, ch;
+
+ /* Separate the bytes to avoid false positives. */
+ al = a & mask;
+ bl = b & mask;
+ ah = (a >> 8) & mask;
+ bh = (b >> 8) & mask;
+
+ /* "Compare". If a byte in B is greater than a byte in A,
+ it will clear the test bit. */
+ cl = ((al | test) - bl) & test;
+ ch = ((ah | test) - bh) & test;
+
+ /* Fold all of the test bits into a contiguous set. */
+ /* ch=.......a...............c...............e...............g........ */
+ /* cl=.......b...............d...............f...............h........ */
+ cl += ch << 1;
+ /* cl=......ab..............cd..............ef..............gh........ */
+ cl |= cl << 14;
+ /* cl=......abcd............cdef............efgh............gh........ */
+ cl |= cl << 28;
+ /* cl=......abcdefgh........cdefgh..........efgh............gh........ */
+ return cl >> 50;
}
uint64_t helper_minub8(uint64_t op1, uint64_t op2)
--
2.4.3
^ permalink raw reply related [flat|nested] 4+ messages in thread* [Qemu-devel] [PULL 2/2] target-alpha: Special case cmpbge with zero
2015-09-02 19:58 [Qemu-devel] [PULL 0/2] target-alpha cmpbge improvements Richard Henderson
2015-09-02 19:58 ` [Qemu-devel] [PULL 1/2] target-alpha: Rewrite helper_cmpbge using bit tests Richard Henderson
@ 2015-09-02 19:58 ` Richard Henderson
2015-09-03 12:05 ` [Qemu-devel] [PULL 0/2] target-alpha cmpbge improvements Peter Maydell
2 siblings, 0 replies; 4+ messages in thread
From: Richard Henderson @ 2015-09-02 19:58 UTC (permalink / raw)
To: qemu-devel; +Cc: peter.maydell
Knowing the comparator is zero leads to a simpler operation.
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
target-alpha/helper.h | 1 +
target-alpha/int_helper.c | 14 ++++++++++++++
target-alpha/translate.c | 7 ++++++-
3 files changed, 21 insertions(+), 1 deletion(-)
diff --git a/target-alpha/helper.h b/target-alpha/helper.h
index d221f0d..83cbe2a 100644
--- a/target-alpha/helper.h
+++ b/target-alpha/helper.h
@@ -10,6 +10,7 @@ DEF_HELPER_FLAGS_1(cttz, TCG_CALL_NO_RWG_SE, i64, i64)
DEF_HELPER_FLAGS_2(zap, TCG_CALL_NO_RWG_SE, i64, i64, i64)
DEF_HELPER_FLAGS_2(zapnot, TCG_CALL_NO_RWG_SE, i64, i64, i64)
+DEF_HELPER_FLAGS_1(cmpbe0, TCG_CALL_NO_RWG_SE, i64, i64)
DEF_HELPER_FLAGS_2(cmpbge, TCG_CALL_NO_RWG_SE, i64, i64, i64)
DEF_HELPER_FLAGS_2(minub8, TCG_CALL_NO_RWG_SE, i64, i64, i64)
diff --git a/target-alpha/int_helper.c b/target-alpha/int_helper.c
index 4a6e955..d7f4774 100644
--- a/target-alpha/int_helper.c
+++ b/target-alpha/int_helper.c
@@ -58,6 +58,20 @@ uint64_t helper_zap(uint64_t val, uint64_t mask)
return helper_zapnot(val, ~mask);
}
+uint64_t helper_cmpbe0(uint64_t a)
+{
+ uint64_t m = 0x7f7f7f7f7f7f7f7fULL;
+ uint64_t c = ~(((a & m) + m) | a | m);
+ /* a.......b.......c.......d.......e.......f.......g.......h....... */
+ c |= c << 7;
+ /* ab......bc......cd......de......ef......fg......gh......h....... */
+ c |= c << 14;
+ /* abcd....bcde....cdef....defg....efgh....fgh.....gh......h....... */
+ c |= c << 28;
+ /* abcdefghbcdefgh.cdefgh..defgh...efgh....fgh.....gh......h....... */
+ return c >> 56;
+}
+
uint64_t helper_cmpbge(uint64_t a, uint64_t b)
{
uint64_t mask = 0x00ff00ff00ff00ffULL;
diff --git a/target-alpha/translate.c b/target-alpha/translate.c
index 81d4ff8..b766ae3 100644
--- a/target-alpha/translate.c
+++ b/target-alpha/translate.c
@@ -1507,7 +1507,12 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
break;
case 0x0F:
/* CMPBGE */
- gen_helper_cmpbge(vc, va, vb);
+ if (ra == 31) {
+ /* Special case 0 >= X as X == 0. */
+ gen_helper_cmpbe0(vc, vb);
+ } else {
+ gen_helper_cmpbge(vc, va, vb);
+ }
break;
case 0x12:
/* S8ADDL */
--
2.4.3
^ permalink raw reply related [flat|nested] 4+ messages in thread