On 07/23/2018 05:01 PM, Sudakshina Das wrote:
Hi Sam
On Monday 23 July 2018 11:39 AM, Sam Tebbs wrote:
Hi all,
This patch extends the aarch64_get_lane_zero_extendsi instruction
definition to
also cover DI mode. This prevents a redundant AND instruction from being
generated due to the pattern failing to be matched.
Example:
typedef char v16qi __attribute__ ((vector_size (16)));
unsigned long long
foo (v16qi a)
{
return a[0];
}
Previously generated:
foo:
umov w0, v0.b[0]
and x0, x0, 255
ret
And now generates:
foo:
umov w0, v0.b[0]
ret
Bootstrapped on aarch64-none-linux-gnu and tested on aarch64-none-elf
with no
regressions.
gcc/
2018-07-23 Sam Tebbs <sam.te...@arm.com>
* config/aarch64/aarch64-simd.md
(*aarch64_get_lane_zero_extendsi<mode>):
Rename to...
(*aarch64_get_lane_zero_extend<mode><VDQQH:mode>): ... This.
Use GPI iterator instead of SI mode.
gcc/testsuite
2018-07-23 Sam Tebbs <sam.te...@arm.com>
* gcc.target/aarch64/extract_zero_extend.c: New file
You will need an approval from a maintainer, but I would only add one
request to this:
diff --git a/gcc/config/aarch64/aarch64-simd.md
b/gcc/config/aarch64/aarch64-simd.md
index 89e38e6..15fb661 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -3032,15 +3032,16 @@
[(set_attr "type" "neon_to_gp<q>")]
)
-(define_insn "*aarch64_get_lane_zero_extendsi<mode>"
- [(set (match_operand:SI 0 "register_operand" "=r")
- (zero_extend:SI
+(define_insn "*aarch64_get_lane_zero_extend<mode><VDQQH:mode>"
+ [(set (match_operand:GPI 0 "register_operand" "=r")
+ (zero_extend:GPI
Since you are adding 4 new patterns with this change, could you add
more cases in your test as well to make sure you have coverage for
each of them.
Thanks
Sudi
Hi Sudi,
Thanks for the feedback. Here is an updated patch that adds more
testcases to cover the patterns generated by the different mode
combinations. The changelog and description from my original email still
apply.
(vec_select:<VEL>
(match_operand:VDQQH 1 "register_operand" "w")
(parallel [(match_operand:SI 2 "immediate_operand" "i")]))))]
"TARGET_SIMD"
{
- operands[2] = aarch64_endian_lane_rtx (<MODE>mode, INTVAL
(operands[2]));
+ operands[2] = aarch64_endian_lane_rtx (<VDQQH:MODE>mode,
+ INTVAL (operands[2]));
return "umov\\t%w0, %1.<Vetype>[%2]";
}
[(set_attr "type" "neon_to_gp<q>")]
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index f1784d72e55c412d076de43f2f7aad4632d55ecb..e92a3b49c65e84d2a16a2a480c359a0b4d8fa3e3 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -3033,15 +3033,16 @@
[(set_attr "type" "neon_to_gp<q>")]
)
-(define_insn "*aarch64_get_lane_zero_extendsi<mode>"
- [(set (match_operand:SI 0 "register_operand" "=r")
- (zero_extend:SI
+(define_insn "*aarch64_get_lane_zero_extend<GPI:mode><VDQQH:mode>"
+ [(set (match_operand:GPI 0 "register_operand" "=r")
+ (zero_extend:GPI
(vec_select:<VEL>
(match_operand:VDQQH 1 "register_operand" "w")
(parallel [(match_operand:SI 2 "immediate_operand" "i")]))))]
"TARGET_SIMD"
{
- operands[2] = aarch64_endian_lane_rtx (<MODE>mode, INTVAL (operands[2]));
+ operands[2] = aarch64_endian_lane_rtx (<VDQQH:MODE>mode,
+ INTVAL (operands[2]));
return "umov\\t%w0, %1.<Vetype>[%2]";
}
[(set_attr "type" "neon_to_gp<q>")]
diff --git a/gcc/testsuite/gcc.target/aarch64/extract_zero_extend.c b/gcc/testsuite/gcc.target/aarch64/extract_zero_extend.c
new file mode 100644
index 0000000000000000000000000000000000000000..deb613cd23150a83dfd36ae84504415993b97be3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/extract_zero_extend.c
@@ -0,0 +1,39 @@
+/* { dg-do compile } */
+/* { dg-options "-O3" } */
+
+/* Tests *aarch64_get_lane_zero_extenddiv16qi. */
+typedef unsigned char v16qi __attribute__ ((vector_size (16)));
+/* Tests *aarch64_get_lane_zero_extenddiv8qi. */
+typedef unsigned char v8qi __attribute__ ((vector_size (8)));
+
+/* Tests *aarch64_get_lane_zero_extendsiv8hi. */
+typedef unsigned short v16hi __attribute__ ((vector_size (16)));
+/* Tests *aarch64_get_lane_zero_extendsiv4hi. */
+typedef unsigned short v8hi __attribute__ ((vector_size (8)));
+
+unsigned long long
+foo_16qi (v16qi a)
+{
+ return a[0];
+}
+
+unsigned long long
+foo_8qi (v8qi a)
+{
+ return a[0];
+}
+
+unsigned int
+foo_16hi (v16hi a)
+{
+ return a[0];
+}
+
+unsigned int
+foo_8hi (v8hi a)
+{
+ return a[0];
+}
+
+/* { dg-final { scan-assembler-times "umov\\t" 4 } } */
+/* { dg-final { scan-assembler-not "and\\t" } } */
