On Fri, 7 Jun 2019 at 18:26, Richard Sandiford
<richard.sandif...@arm.com> wrote:
>
> Prathamesh Kulkarni <prathamesh.kulka...@linaro.org> writes:
> > On Thu, 6 Jun 2019 at 16:54, Richard Sandiford
> > <richard.sandif...@arm.com> wrote:
> >>
> >> Szabolcs Nagy <szabolcs.n...@arm.com> writes:
> >> > On 03/06/2019 08:26, Prathamesh Kulkarni wrote:
> >> >> +++ b/gcc/testsuite/gcc.target/aarch64/sve/init_8.c
> >> >> @@ -0,0 +1,32 @@
> >> >> +/* { dg-do assemble { target aarch64_asm_sve_ok } } */
> >> >> +/* { dg-options "-O2 -fno-schedule-insns -msve-vector-bits=256
> >> >> --save-temps" } */
> >> >> +
> >> >> +/* Case 5.2: Interleaved elements and constants. */
> >> >> +
> >> >> +#include <stdint.h>
> >> >> +
> >> >> +typedef int32_t vnx4si __attribute__((vector_size (32)));
> >> >> +
> >> >> +__attribute__((noipa))
> >> >> +vnx4si foo(int a, int b, int c, int d)
> >> >> +{
> >> >> + return (vnx4si) { a, 1, b, 2, c, 3, d, 4 };
> >> >> +}
> >> >> +
> >> >> +/*
> >> >> +foo:
> >> >> +.LFB0:
> >> >> + .cfi_startproc
> >> >> + ptrue p0.s, vl8
> >> >> + mov z0.s, w3
> >> >> + adrp x3, .LANCHOR0
> >> >> + insr z0.s, w2
> >> >> + add x3, x3, :lo12:.LANCHOR0
> >> >> + insr z0.s, w1
> >> >> + ld1w z1.s, p0/z, [x3]
> >> >> + insr z0.s, w0
> >> >> + zip1 z0.s, z0.s, z1.s
> >> >> + ret
> >> >> +*/
> >> >> +
> >> >> +/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s),
> >> >> w3\n\tadrp\t(x[0-9]+), \.LANCHOR0\n\tinsr\t\1, w2\n\tadd\t\2, \2,
> >> >> :lo12:\.LANCHOR0\n\tinsr\t\1, w1\n\tld1w\t(z[0-9]+\.s), p[0-9]+/z,
> >> >> \[\2\]\n\tinsr\t\1, w0\n\tzip1\t\1, \1, \3} } } */
> >> >
> >> > this fails with tiny model when i'm testing aarch64-none-elf
> >> >
> >> > $ make check-c
> >> > 'RUNTESTFLAGS=--target_board=aarch64-elf-qemu{-mcmodel=tiny}
> >> > aarch64-sve.exp=init_8.c'
> >> > ...
> >> > FAIL: gcc.target/aarch64/sve/init_8.c -march=armv8.2-a+sve
> >> > scan-assembler \\tmov\\t(z[0-9]+\\.s), w3\\n\\tadrp\\t(x[0-9]+),
> >> > \\.LANCHOR0\\n\\tinsr\\t\\1, w2\\n\\tadd\\t\\2, \\2,
> >> > :lo12:\\.LANCHOR0\\n\\tinsr\\t\\1, w1\\n\\tld1w\\t(z[0-9]+\\.s),
> >> > p[0-9]+/z,
> >> > \\[\\2\\]\\n\\tinsr\\t\\1, w0\\n\\tzip1\\t\\1, \\1, \\3
> >> >
> >> > i think you need conditional scan asm for { target aarch64_small }
> >> > and { target aarch64_tiny } or just skip the test for tiny,
> >>
> >> Maybe we should remove the address calculation and replace the ld1w
> >> address with \[[^]]*\]. All that really matters for this test is that
> >> the vector is loaded from memory.
> >>
> >> > but even then matching exact register name and instruction scheduling
> >> > seems fragile.
> >>
> >> The only hard-coded register names are the parameters, which are
> >> guaranteed by the ABI. Testing for those should be fine.
> >>
> >> The dg-options pass -fno-schedule-insns, but I guess they should
> >> also pass -fno-schedule-insns2. Or maybe just use -O instead.
> >> We can always revisit this later if even that isn't enough to make
> >> the order stable.
> > Thanks for the suggestions. Passing -fno-schedule-insns2 does seem to
> > make the order stable.
> > For init_1.c to init_4.c there were no intervening instructions, and
> > for remaining tests, the patch passes -fno-schedule-insns2
> > and adjusts dg-scan accordingly. I verified the tests pass with
> > -mcmodel=tiny.
>
> I think we should use consistent options for all the test though.
> So either we should add -fno-schedule-insns2 to all of them,
> or we should switch to -O. TBH -O seems easier :-) (I checked
> that all tests do still pass with -O.)
>
> > diff --git a/gcc/testsuite/gcc.target/aarch64/sve/init_10.c
> > b/gcc/testsuite/gcc.target/aarch64/sve/init_10.c
> > index 9d6e2dfc876..08437e5d8f1 100644
> > --- a/gcc/testsuite/gcc.target/aarch64/sve/init_10.c
> > +++ b/gcc/testsuite/gcc.target/aarch64/sve/init_10.c
> > @@ -1,5 +1,5 @@
> > /* { dg-do assemble { target aarch64_asm_sve_ok } } */
> > -/* { dg-options "-O2 -fno-schedule-insns -msve-vector-bits=256
> > --save-temps" } */
> > +/* { dg-options "-O2 -fno-schedule-insns -fno-schedule-insns2
> > -msve-vector-bits=256 --save-temps" } */
> >
> > /* Case 5.4: Interleaved repeating elements and non-repeating elements. */
> >
> > @@ -17,13 +17,14 @@ vnx4si foo(int a, int b, int c, int f)
> > foo:
> > .LFB0:
> > .cfi_startproc
> > - mov z0.s, w2
> > mov z1.s, w3
> > + mov z0.s, w2
> > insr z0.s, w1
> > - ptrue p0.s, vl8
> > insr z0.s, w0
> > zip1 z0.s, z0.s, z1.s
> > + ptrue p0.s, vl8
> > + st1w z0.s, p0, [x8]
> > ret
> > */
> >
> > -/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s),
> > w3\n\tmov\t(z[0-9]+\.s), w2\n.*\n\tinsr\t\2, w1\n\tinsr\t\2,
> > w0\n\tzip1\t\2, \2, \1} } } */
> > +/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s),
> > w3\n\tmov\t(z[0-9]+\.s), w2\n\tinsr\t\2, w1\n\tinsr\t\2, w0\n\tzip1\t\2,
> > \2, \1} } } */
>
> You're reintroducing the st1w as part of the asms. We should either
> do that for all the tests or leave it out.
Oops, sorry about that.
Attached patch removes st1w and passes -O for all tests in the attached patch.
OK to commit ?
Thanks,
Prathamesh
>
> Thanks,
> Richard
2019-06-07 Prathamesh Kulkarni <prathamesh.kulka...@linaro.org>
* gcc.target/aarch64/sve/init_1.c: Remove options
-O2 -fno-schedule-insns and instead pass -O.
Update assembly in comments.
* gcc.target/aarch64/sve/init_2.c: Likewise.
* gcc.target/aarch64/sve/init_3.c: Likewise.
* gcc.target/aarch64/sve/init_4.c: Likewise.
* gcc.target/aarch64/sve/init_5.c: Likewise and additionally
adjust dg-scan.
* gcc.target/aarch64/sve/init_6.c: Likewise.
* gcc.target/aarch64/sve/init_7.c: Likewise.
* gcc.target/aarch64/sve/init_8.c: Likewise.
* gcc.target/aarch64/sve/init_9.c: Likewise.
* gcc.target/aarch64/sve/init_10.c: Likewise.
* gcc.target/aarch64/sve/init_11.c: Likewise.
* gcc.target/aarch64/sve/init_12.c: Likewise.
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/init_1.c
b/gcc/testsuite/gcc.target/aarch64/sve/init_1.c
index 5c14b603f46..4f18088f3b0 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/init_1.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/init_1.c
@@ -1,5 +1,5 @@
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
-/* { dg-options "-O2 -fno-schedule-insns -msve-vector-bits=256 --save-temps" }
*/
+/* { dg-options "-O -msve-vector-bits=256 --save-temps" } */
/* Case 1.1: Trailing constants with stepped sequence. */
@@ -17,10 +17,10 @@ vnx4si foo(int a, int b)
foo:
.LFB0:
.cfi_startproc
- ptrue p0.s, vl8
index z0.s, #1, #1
insr z0.s, w1
insr z0.s, w0
+ ptrue p0.s, vl8
ret
*/
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/init_10.c
b/gcc/testsuite/gcc.target/aarch64/sve/init_10.c
index 9d6e2dfc876..1ee1db723e6 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/init_10.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/init_10.c
@@ -1,5 +1,5 @@
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
-/* { dg-options "-O2 -fno-schedule-insns -msve-vector-bits=256 --save-temps" }
*/
+/* { dg-options "-O -msve-vector-bits=256 --save-temps" } */
/* Case 5.4: Interleaved repeating elements and non-repeating elements. */
@@ -17,13 +17,13 @@ vnx4si foo(int a, int b, int c, int f)
foo:
.LFB0:
.cfi_startproc
- mov z0.s, w2
mov z1.s, w3
+ mov z0.s, w2
insr z0.s, w1
- ptrue p0.s, vl8
insr z0.s, w0
zip1 z0.s, z0.s, z1.s
+ ptrue p0.s, vl8
ret
*/
-/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w3\n\tmov\t(z[0-9]+\.s),
w2\n.*\n\tinsr\t\2, w1\n\tinsr\t\2, w0\n\tzip1\t\2, \2, \1} } } */
+/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w3\n\tmov\t(z[0-9]+\.s),
w2\n\tinsr\t\2, w1\n\tinsr\t\2, w0\n\tzip1\t\2, \2, \1} } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/init_11.c
b/gcc/testsuite/gcc.target/aarch64/sve/init_11.c
index e50cd54ef13..0b3c4a51198 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/init_11.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/init_11.c
@@ -1,5 +1,5 @@
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
-/* { dg-options "-O2 -fno-schedule-insns -msve-vector-bits=256 --save-temps" }
*/
+/* { dg-options "-O -msve-vector-bits=256 --save-temps" } */
/* Case 5.5: Interleaved repeating elements and trailing same elements. */
@@ -18,11 +18,11 @@ foo:
.LFB0:
.cfi_startproc
mov z0.s, w1
- mov z1.s, w2
insr z0.s, w0
- ptrue p0.s, vl8
+ mov z1.s, w2
zip1 z0.s, z0.s, z1.s
+ ptrue p0.s, vl8
ret
*/
-/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w1\n\tmov\t(z[0-9]+\.s),
w2\n\tinsr\t\1, w0\n.*\tzip1\t\1, \1, \2} } } */
+/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w1\n\tinsr\t\1,
w0\n\tmov\t(z[0-9]+\.s), w2\n\tzip1\t\1, \1, \2} } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/init_12.c
b/gcc/testsuite/gcc.target/aarch64/sve/init_12.c
index 21d9e764360..2473a5ecb80 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/init_12.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/init_12.c
@@ -1,5 +1,5 @@
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
-/* { dg-options "-O2 -fno-schedule-insns -msve-vector-bits=256 --save-temps" }
*/
+/* { dg-options "-O -msve-vector-bits=256 --save-temps" } */
/* Case 5.5: Interleaved repeating elements and trailing same elements. */
@@ -17,14 +17,14 @@ vnx4si foo(int a, int b, int f)
foo:
.LFB0:
.cfi_startproc
- mov z0.s, w0
mov z1.s, w2
+ mov z0.s, w0
insr z0.s, w1
- ptrue p0.s, vl8
insr z0.s, w1
insr z0.s, w1
zip1 z0.s, z0.s, z1.s
+ ptrue p0.s, vl8
ret
*/
-/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w2\n\tmov\t(z[0-9]+\.s),
w0\n.*\n\tinsr\t\2, w1\n\tinsr\t\2, w1\n\tinsr\t\2, w1\n\tzip1\t\2, \2, \1} } }
*/
+/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w2\n\tmov\t(z[0-9]+\.s),
w0\n\tinsr\t\2, w1\n\tinsr\t\2, w1\n\tinsr\t\2, w1\n\tzip1\t\2, \2, \1} } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/init_2.c
b/gcc/testsuite/gcc.target/aarch64/sve/init_2.c
index a8b2a25b325..5b4ba105af2 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/init_2.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/init_2.c
@@ -1,5 +1,5 @@
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
-/* { dg-options "-O2 -fno-schedule-insns -msve-vector-bits=256 --save-temps" }
*/
+/* { dg-options "-O -msve-vector-bits=256 --save-temps" } */
/* Case 1.2: Trailing constants with repeating sequence. */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/init_3.c
b/gcc/testsuite/gcc.target/aarch64/sve/init_3.c
index 6b000b887ba..62f31b75efd 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/init_3.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/init_3.c
@@ -1,5 +1,5 @@
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
-/* { dg-options "-O2 -fno-schedule-insns -msve-vector-bits=256 --save-temps" }
*/
+/* { dg-options "-O -msve-vector-bits=256 --save-temps" } */
/* Case 2.1: Leading constants with stepped sequence. */
@@ -17,11 +17,11 @@ vnx4si foo(int a, int b)
foo:
.LFB0:
.cfi_startproc
- ptrue p0.s, vl8
index z0.s, #6, #-1
insr z0.s, w0
insr z0.s, w1
rev z0.s, z0.s
+ ptrue p0.s, vl8
ret
*/
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/init_4.c
b/gcc/testsuite/gcc.target/aarch64/sve/init_4.c
index 619274928e4..94484b1a4e6 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/init_4.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/init_4.c
@@ -1,5 +1,5 @@
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
-/* { dg-options "-O2 -fno-schedule-insns -msve-vector-bits=256 --save-temps" }
*/
+/* { dg-options "-O -msve-vector-bits=256 --save-temps" } */
/* Case 2.2: Leading constants with stepped sequence. */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/init_5.c
b/gcc/testsuite/gcc.target/aarch64/sve/init_5.c
index e7fbdd1a2aa..0a0e8ebd1fe 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/init_5.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/init_5.c
@@ -1,5 +1,5 @@
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
-/* { dg-options "-O2 -fno-schedule-insns -msve-vector-bits=256 --save-temps" }
*/
+/* { dg-options "-O -msve-vector-bits=256 --save-temps" } */
/* Case 3: Trailing same element. */
@@ -18,10 +18,10 @@ foo:
.LFB0:
.cfi_startproc
mov z0.s, w2
- ptrue p0.s, vl8
insr z0.s, w1
insr z0.s, w0
+ ptrue p0.s, vl8
ret
*/
-/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w2\n.*\tinsr\t\1,
w1\n\tinsr\t\1, w0} } } */
+/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w2\n\tinsr\t\1,
w1\n\tinsr\t\1, w0} } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/init_6.c
b/gcc/testsuite/gcc.target/aarch64/sve/init_6.c
index f6f3da5958d..10eca3a9001 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/init_6.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/init_6.c
@@ -1,5 +1,5 @@
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
-/* { dg-options "-O2 -fno-schedule-insns -msve-vector-bits=256 --save-temps" }
*/
+/* { dg-options "-O -msve-vector-bits=256 --save-temps" } */
/* Case 3: Trailing same element. */
@@ -18,11 +18,11 @@ foo:
.LFB0:
.cfi_startproc
mov z0.s, w2
- ptrue p0.s, vl8
insr z0.s, w1
insr z0.s, w0
rev z0.s, z0.s
+ ptrue p0.s, vl8
ret
*/
-/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w2\n.*\tinsr\t\1,
w1\n\tinsr\t\1, w0\n\trev\t\1, \1} } } */
+/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w2\n\tinsr\t\1,
w1\n\tinsr\t\1, w0\n\trev\t\1, \1} } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/init_7.c
b/gcc/testsuite/gcc.target/aarch64/sve/init_7.c
index e3104a35f13..d83fa9c08f2 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/init_7.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/init_7.c
@@ -1,5 +1,5 @@
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
-/* { dg-options "-O2 -fno-schedule-insns -msve-vector-bits=256 --save-temps" }
*/
+/* { dg-options "-O -msve-vector-bits=256 --save-temps" } */
/* Case 5.1: All elements. */
@@ -18,7 +18,6 @@ foo:
.LFB0:
.cfi_startproc
mov z0.s, w7
- ptrue p0.s, vl8
insr z0.s, w6
insr z0.s, w5
insr z0.s, w4
@@ -26,7 +25,8 @@ foo:
insr z0.s, w2
insr z0.s, w1
insr z0.s, w0
+ ptrue p0.s, vl8
ret
*/
-/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w7\n.*\tinsr\t\1,
w6\n\tinsr\t\1, w5\n\tinsr\t\1, w4\n\tinsr\t\1, w3\n\tinsr\t\1, w2\n\tinsr\t\1,
w1\n\tinsr\t\1, w0} } } */
+/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w7\n\tinsr\t\1,
w6\n\tinsr\t\1, w5\n\tinsr\t\1, w4\n\tinsr\t\1, w3\n\tinsr\t\1, w2\n\tinsr\t\1,
w1\n\tinsr\t\1, w0} } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/init_8.c
b/gcc/testsuite/gcc.target/aarch64/sve/init_8.c
index 7ff3e0849cc..73f7aba3df3 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/init_8.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/init_8.c
@@ -1,5 +1,5 @@
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
-/* { dg-options "-O2 -fno-schedule-insns -msve-vector-bits=256 --save-temps" }
*/
+/* { dg-options "-O -msve-vector-bits=256 --save-temps" } */
/* Case 5.2: Interleaved elements and constants. */
@@ -18,15 +18,15 @@ foo:
.LFB0:
.cfi_startproc
ptrue p0.s, vl8
+ adrp x4, .LANCHOR0
+ add x4, x4, :lo12:.LANCHOR0
+ ld1w z1.s, p0/z, [x4]
mov z0.s, w3
- adrp x3, .LANCHOR0
insr z0.s, w2
- add x3, x3, :lo12:.LANCHOR0
insr z0.s, w1
- ld1w z1.s, p0/z, [x3]
insr z0.s, w0
zip1 z0.s, z0.s, z1.s
ret
*/
-/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w3\n\tadrp\t(x[0-9]+),
\.LANCHOR0\n\tinsr\t\1, w2\n\tadd\t\2, \2, :lo12:\.LANCHOR0\n\tinsr\t\1,
w1\n\tld1w\t(z[0-9]+\.s), p[0-9]+/z, \[\2\]\n\tinsr\t\1, w0\n\tzip1\t\1, \1,
\3} } } */
+/* { dg-final { scan-assembler {\tld1w\t(z[0-9]+\.s), p[0-9]+/z,
\[x[0-9]+\]\n\tmov\t(z[0-9]+\.s), w3\n\tinsr\t\2, w2\n\tinsr\t\2,
w1\n\tinsr\t\2, w0\n\tzip1\t\2, \2, \1} } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/init_9.c
b/gcc/testsuite/gcc.target/aarch64/sve/init_9.c
index 4d3c59b3bf8..668b4efdbc5 100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/init_9.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/init_9.c
@@ -1,5 +1,5 @@
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
-/* { dg-options "-O2 -fno-schedule-insns -msve-vector-bits=256 --save-temps" }
*/
+/* { dg-options "-O -msve-vector-bits=256 --save-temps" } */
/* Case 5.3: Repeated elements. */
@@ -19,9 +19,9 @@ foo:
.cfi_startproc
mov z0.s, w0
mov z1.s, w1
- ptrue p0.s, vl8
zip1 z0.s, z0.s, z1.s
+ ptrue p0.s, vl8
ret
*/
-/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w0\n\tmov\t(z[0-9]+\.s),
w1\n.*\tzip1\t\1, \1, \2} } } */
+/* { dg-final { scan-assembler {\tmov\t(z[0-9]+\.s), w0\n\tmov\t(z[0-9]+\.s),
w1\n\tzip1\t\1, \1, \2} } } */
