Hi,
I noticed we were missing out on LD1 + UXT combinations in some cases
and found it was because of inconsistent use of the unspec enum
UNSPEC_LD1_SVE. The combine pattern for LD1[S][BHWD] uses UNSPEC_LD1_SVE
whereas one of the LD1 expanders was using UNSPEC_PRED_X. I wasn't sure
whether to change the UNSPEC_LD1_SVE into UNSPEC_PRED_X as the enum
doesn't seem to be used for anything in particular, though I decided
against it for now as it is easier to rename UNSPEC_LD1_SVE to
UNSPEC_PRED_X if there is no use for it than it is to rename only
specific instances of UNSPEC_PRED_X.
If there is a firm belief the UNSPEC_LD1_SVE will not be used for
anything I am also happy to refactor it out.
Bootstrapped and regression tested aarch64-none-linux-gnu.
Is this OK for trunk?
Kind regards,
Andre Vieira
gcc/ChangeLog:
2021-05-14 Andre Vieira <andre.simoesdiasvie...@arm.com>
* config/aarch64/aarch64-sve.md: Use UNSPEC_LD1_SVE instead of
UNSPEC_PRED_X.
gcc/testsuite/ChangeLog:
2021-05-14 Andre Vieira <andre.simoesdiasvie...@arm.com>
* gcc.target/aarch64/sve/logical_unpacked_and_2.c: Remove
superfluous uxtb.
* gcc.target/aarch64/sve/logical_unpacked_and_3.c: Likewise.
* gcc.target/aarch64/sve/logical_unpacked_and_4.c: Likewise.
* gcc.target/aarch64/sve/logical_unpacked_and_6.c: Likewise.
* gcc.target/aarch64/sve/logical_unpacked_and_7.c: Likewise.
* gcc.target/aarch64/sve/logical_unpacked_eor_2.c: Likewise.
* gcc.target/aarch64/sve/logical_unpacked_eor_3.c: Likewise.
* gcc.target/aarch64/sve/logical_unpacked_eor_4.c: Likewise.
* gcc.target/aarch64/sve/logical_unpacked_eor_6.c: Likewise.
* gcc.target/aarch64/sve/logical_unpacked_eor_7.c: Likewise.
* gcc.target/aarch64/sve/logical_unpacked_orr_2.c: Likewise.
* gcc.target/aarch64/sve/logical_unpacked_orr_4.c: Likewise.
* gcc.target/aarch64/sve/logical_unpacked_orr_6.c: Likewise.
* gcc.target/aarch64/sve/logical_unpacked_orr_7.c: Likewise.
* gcc.target/aarch64/sve/ld1_extend.c: New test.
diff --git a/gcc/config/aarch64/aarch64-sve.md
b/gcc/config/aarch64/aarch64-sve.md
index
7db2938bb84e04d066a7b07574e5cf344a3a8fb6..5fd74fcf3e0a984b5b40b8128ad9354fb899ce5f
100644
--- a/gcc/config/aarch64/aarch64-sve.md
+++ b/gcc/config/aarch64/aarch64-sve.md
@@ -747,7 +747,7 @@ (define_insn_and_split "@aarch64_pred_mov<mode>"
(unspec:SVE_ALL
[(match_operand:<VPRED> 1 "register_operand" "Upl, Upl, Upl")
(match_operand:SVE_ALL 2 "nonimmediate_operand" "w, m, w")]
- UNSPEC_PRED_X))]
+ UNSPEC_LD1_SVE))]
"TARGET_SVE
&& (register_operand (operands[0], <MODE>mode)
|| register_operand (operands[2], <MODE>mode))"
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/ld1_extend.c
b/gcc/testsuite/gcc.target/aarch64/sve/ld1_extend.c
new file mode 100644
index
0000000000000000000000000000000000000000..7f78cb4b3e4445c4da93b00ae78d6ef6fec1b2de
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/ld1_extend.c
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 --param vect-partial-vector-usage=1" } */
+
+void foo (signed char * __restrict__ a, signed char * __restrict__ b, short *
__restrict__ c, int n)
+{
+ for (int i = 0; i < n; ++i)
+ c[i] = a[i] + b[i];
+}
+
+/* { dg-final { scan-assembler-times {\tld1sb\t} 4 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_2.c
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_2.c
index
08b274512e1c6ce8f5845084a664b2fa0456dafe..cb6029e90ffc815e75092624f611c4631cbd9fd6
100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_2.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_2.c
@@ -11,7 +11,6 @@ f (uint64_t *restrict dst, uint16_t *restrict src1, uint8_t
*restrict src2)
/* { dg-final { scan-assembler-times {\tld1h\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
-/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.h,} 1 } } */
/* { dg-final { scan-assembler-times {\tand\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_3.c
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_3.c
index
c823470ca925ee66929475f74fa8d94bc4735594..02fc5460e5ce89c8a3fef611aac561145ddd0f39
100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_3.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_3.c
@@ -11,7 +11,6 @@ f (uint64_t *restrict dst, uint32_t *restrict src1, uint8_t
*restrict src2)
/* { dg-final { scan-assembler-times {\tld1w\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
-/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.s,} 1 } } */
/* { dg-final { scan-assembler-times {\tand\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_4.c
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_4.c
index
52c92911d9b548662d43b23816e4d450a9e67846..8a441300ba59da6f96365bc6ad5482911ed605f8
100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_4.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_4.c
@@ -11,7 +11,6 @@ f (uint64_t *restrict dst, uint32_t *restrict src1, uint16_t
*restrict src2)
/* { dg-final { scan-assembler-times {\tld1w\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tld1h\tz[0-9]+\.d,} 2 } } */
-/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.s,} 1 } } */
/* { dg-final { scan-assembler-times {\tand\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_6.c
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_6.c
index
1552ed85302373bb16ad8265f5c84cea71ccbc66..2f657736f37162c1c422b318e6f23242c68fea48
100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_6.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_6.c
@@ -11,7 +11,6 @@ f (uint64_t *restrict dst, uint16_t *restrict src1, uint8_t
*restrict src2)
/* { dg-final { scan-assembler-times {\tld1h\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
-/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.h,} 1 } } */
/* { dg-final { scan-assembler-times {\tand\tz[0-9]+\.d, z[0-9]+\.d,
z[0-9]+\.d\n} 2 } } */
/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_7.c
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_7.c
index
484d9daf38f0779109484eab5a2a03a626c16fe8..d67bdb7233e906581517463386fabe293a8d7170
100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_7.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_7.c
@@ -10,7 +10,6 @@ f (uint64_t *restrict dst, uint32_t *restrict src1, uint8_t
*restrict src2){
/* { dg-final { scan-assembler-times {\tld1w\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
-/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.s,} 1 } } */
/* { dg-final { scan-assembler-times {\tand\tz[0-9]+\.d, z[0-9]+\.d,
z[0-9]+\.d\n} 2 } } */
/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_2.c
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_2.c
index
23ddeb9f9b11f80783e1b173696a15d1d73762a3..594e4117477ffc78665eac617bb7c3452217cacd
100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_2.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_2.c
@@ -11,7 +11,6 @@ f (uint64_t *restrict dst, uint16_t *restrict src1, uint8_t
*restrict src2)
/* { dg-final { scan-assembler-times {\tld1h\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
-/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.h,} 1 } } */
/* { dg-final { scan-assembler-times {\teor\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_3.c
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_3.c
index
4dd1e085646c6d0e6d3d4e02534c94ea592ea7be..1f684feade878fda293e55fca24541d1fa4133ef
100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_3.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_3.c
@@ -11,7 +11,6 @@ f (uint64_t *restrict dst, uint32_t *restrict src1, uint8_t
*restrict src2)
/* { dg-final { scan-assembler-times {\tld1w\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
-/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.s,} 1 } } */
/* { dg-final { scan-assembler-times {\teor\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_4.c
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_4.c
index
a31a2d425faa11c6faa5306d4c0a7e5a5fa086d8..b051eb28c51a02a5240a81a33cbcbd3d163098b3
100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_4.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_4.c
@@ -11,7 +11,6 @@ f (uint64_t *restrict dst, uint32_t *restrict src1, uint16_t
*restrict src2)
/* { dg-final { scan-assembler-times {\tld1w\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tld1h\tz[0-9]+\.d,} 2 } } */
-/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.s,} 1 } } */
/* { dg-final { scan-assembler-times {\teor\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_6.c
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_6.c
index
416567b21f703d6e0ff3792d2089b923ecde0441..cd42405690b39c651ce76416ea3b371f5611cfe6
100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_6.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_6.c
@@ -11,7 +11,6 @@ f (uint64_t *restrict dst, uint16_t *restrict src1, uint8_t
*restrict src2)
/* { dg-final { scan-assembler-times {\tld1h\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
-/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.h,} 1 } } */
/* { dg-final { scan-assembler-times {\teor\tz[0-9]+\.d, z[0-9]+\.d,
z[0-9]+\.d\n} 2 } } */
/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_7.c
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_7.c
index
3f7c3ddbba8a986e01fbdbe51b307bdc3990da37..2154ae8f2485fb81cc77286ae8f1293050378173
100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_7.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_eor_7.c
@@ -10,7 +10,6 @@ f (uint64_t *restrict dst, uint32_t *restrict src1, uint8_t
*restrict src2){
/* { dg-final { scan-assembler-times {\tld1w\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
-/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.s,} 1 } } */
/* { dg-final { scan-assembler-times {\teor\tz[0-9]+\.d, z[0-9]+\.d,
z[0-9]+\.d\n} 2 } } */
/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_2.c
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_2.c
index
593de65a02cd2a16acb48a6dd05163a4e66b7b27..890b7e64f965678c2fe2e5d0a395520d9189b6dc
100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_2.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_2.c
@@ -11,7 +11,6 @@ f (uint64_t *restrict dst, uint16_t *restrict src1, uint8_t
*restrict src2)
/* { dg-final { scan-assembler-times {\tld1h\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
-/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.h,} 1 } } */
/* { dg-final { scan-assembler-times {\torr\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_4.c
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_4.c
index
561a104a23f00759af457e03e8e175589282aeb5..2b419a65d60abd7b7ef330ea538c02fe2ade8f9a
100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_4.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_4.c
@@ -11,7 +11,6 @@ f (uint64_t *restrict dst, uint32_t *restrict src1, uint16_t
*restrict src2)
/* { dg-final { scan-assembler-times {\tld1w\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tld1h\tz[0-9]+\.d,} 2 } } */
-/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.s,} 1 } } */
/* { dg-final { scan-assembler-times {\torr\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_6.c
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_6.c
index
3ce1c3fb1e636c7f8ebcf2a7fbaafe20f3b7cfa0..214a3c7efbb9a776477907e2516d5dd112c77d7d
100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_6.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_6.c
@@ -11,7 +11,6 @@ f (uint64_t *restrict dst, uint16_t *restrict src1, uint8_t
*restrict src2)
/* { dg-final { scan-assembler-times {\tld1h\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
-/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.h,} 1 } } */
/* { dg-final { scan-assembler-times {\torr\tz[0-9]+\.d, z[0-9]+\.d,
z[0-9]+\.d\n} 2 } } */
/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_7.c
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_7.c
index
e6a429167ea38dbbbc7e653cd6d47ffbe0bc768d..66e24058ae2e657bcb804d23b58d7c722e3e2dd5
100644
--- a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_7.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_orr_7.c
@@ -10,7 +10,6 @@ f (uint64_t *restrict dst, uint32_t *restrict src1, uint8_t
*restrict src2){
/* { dg-final { scan-assembler-times {\tld1w\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.d,} 2 } } */
-/* { dg-final { scan-assembler-times {\tuxtb\tz[0-9]+\.s,} 1 } } */
/* { dg-final { scan-assembler-times {\torr\tz[0-9]+\.d, z[0-9]+\.d,
z[0-9]+\.d\n} 2 } } */
/* { dg-final { scan-assembler-times {\tuxtw\tz[0-9]+\.d,} 2 } } */
/* { dg-final { scan-assembler-times {\tst1d\tz[0-9]+\.d,} 2 } } */
