[PATCH] match.pd: Only merge truncation with conversion for -fno-signed-zeros

2024-03-13 Thread Joe Ramsay 
This optimisation does not honour signed zeros, so should not be
enabled except with -fno-signed-zeros.

OK for master? I do not have commit rights for GCC, so if the patch
is fine would someone be able to commit for me? The bug is present
in all GCC versions from 12.1.0 onwards - is it possible to backport
this?

Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.

Thanks,
Joe

gcc/ChangeLog:

* match.pd: Fix truncation pattern for -fno-signed-zeroes

gcc/testsuite/ChangeLog:

* gcc.target/aarch64/no_merge_trunc_signed_zero.c: New test.
---
 gcc/match.pd  |  2 +-
 .../aarch64/no_merge_trunc_signed_zero.c  | 24 +++
 2 files changed, 25 insertions(+), 1 deletion(-)
 create mode 100644 
gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c

diff --git a/gcc/match.pd b/gcc/match.pd
index 9ce313323a3..45c34c810cf 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -4857,7 +4857,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
 #if GIMPLE
 (simplify
(float (fix_trunc @0))
-   (if (!flag_trapping_math
+   (if (!flag_trapping_math && !HONOR_SIGNED_ZEROS(type)
&& types_match (type, TREE_TYPE (@0))
&& direct_internal_fn_supported_p (IFN_TRUNC, type,
  OPTIMIZE_FOR_BOTH))
diff --git a/gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c 
b/gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c
new file mode 100644
index 000..b2c93e55567
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fno-trapping-math -fsigned-zeros" } */
+
+#include 
+
+float
+f1 (float x)
+{
+  return (int) rintf(x);
+}
+
+double
+f2 (double x)
+{
+  return (long) rint(x);
+}
+
+/* { dg-final { scan-assembler "frintx\\ts\[0-9\]+, s\[0-9\]+" } } */
+/* { dg-final { scan-assembler "cvtzs\\ts\[0-9\]+, s\[0-9\]+" } } */
+/* { dg-final { scan-assembler "scvtf\\ts\[0-9\]+, s\[0-9\]+" } } */
+/* { dg-final { scan-assembler "frintx\\td\[0-9\]+, d\[0-9\]+" } } */
+/* { dg-final { scan-assembler "cvtzs\\td\[0-9\]+, d\[0-9\]+" } } */
+/* { dg-final { scan-assembler "scvtf\\td\[0-9\]+, d\[0-9\]+" } } */
+
-- 
2.27.0

[PATCH v2] match.pd: Only merge truncation with conversion for -fno-signed-zeros

2024-03-14 Thread Joe Ramsay 
This optimisation does not honour signed zeros, so should not be
enabled except with -fno-signed-zeros.

OK for master? I do not have commit rights for GCC, so if the patch
is fine would someone be able to commit for me? The bug is present
in all GCC versions from 12.1.0 onwards - is it possible to backport
this?

Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.

Thanks,
Joe

gcc/ChangeLog:

* match.pd: Fix truncation pattern for -fno-signed-zeroes

gcc/testsuite/ChangeLog:

* gcc.target/aarch64/no_merge_trunc_signed_zero.c: New test.
---
Changes from v1, whitespace change only.
 gcc/match.pd  |  1 +
 .../aarch64/no_merge_trunc_signed_zero.c  | 24 +++
 2 files changed, 25 insertions(+)
 create mode 100644 
gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c

diff --git a/gcc/match.pd b/gcc/match.pd
index 9ce313323a3..15a1e7350d4 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -4858,6 +4858,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
 (simplify
(float (fix_trunc @0))
(if (!flag_trapping_math
+   && !HONOR_SIGNED_ZEROS (type)
&& types_match (type, TREE_TYPE (@0))
&& direct_internal_fn_supported_p (IFN_TRUNC, type,
  OPTIMIZE_FOR_BOTH))
diff --git a/gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c 
b/gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c
new file mode 100644
index 000..b2c93e55567
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fno-trapping-math -fsigned-zeros" } */
+
+#include 
+
+float
+f1 (float x)
+{
+  return (int) rintf(x);
+}
+
+double
+f2 (double x)
+{
+  return (long) rint(x);
+}
+
+/* { dg-final { scan-assembler "frintx\\ts\[0-9\]+, s\[0-9\]+" } } */
+/* { dg-final { scan-assembler "cvtzs\\ts\[0-9\]+, s\[0-9\]+" } } */
+/* { dg-final { scan-assembler "scvtf\\ts\[0-9\]+, s\[0-9\]+" } } */
+/* { dg-final { scan-assembler "frintx\\td\[0-9\]+, d\[0-9\]+" } } */
+/* { dg-final { scan-assembler "cvtzs\\td\[0-9\]+, d\[0-9\]+" } } */
+/* { dg-final { scan-assembler "scvtf\\td\[0-9\]+, d\[0-9\]+" } } */
+
-- 
2.27.0

[PATCH][Backport][GCC12] match.pd: Only merge truncation with conversion for -fno-signed-zeros

2024-04-29 Thread Joe Ramsay 
This optimisation does not honour signed zeros, so should not be
enabled except with -fno-signed-zeros.

Cherry-pick of 7dd3b2b09cbeb6712ec680a0445cb0ad41070423.

Applies cleanly on releases/gcc-12. Regression-tested, only new
failure is in gcc/testsuite/c-c++-common/hwasan/large-aligned-1.c
which I believe is unrelated and known to be flaky.

OK for backport to GCC 12? If so, please commit for me as I do not
have commit rights in GCC.

Thanks,
Joe

gcc/ChangeLog:

* match.pd: Fix truncation pattern for -fno-signed-zeroes

gcc/testsuite/ChangeLog:

* gcc.target/aarch64/no_merge_trunc_signed_zero.c: New test.
---
 gcc/match.pd  |  1 +
 .../aarch64/no_merge_trunc_signed_zero.c  | 24 +++
 2 files changed, 25 insertions(+)
 create mode 100644 
gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c

diff --git a/gcc/match.pd b/gcc/match.pd
index c5a4426e76b..0938d56fa45 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3825,6 +3825,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
 (simplify
(float (fix_trunc @0))
(if (!flag_trapping_math
+   && !HONOR_SIGNED_ZEROS (type)
&& types_match (type, TREE_TYPE (@0))
&& direct_internal_fn_supported_p (IFN_TRUNC, type,
  OPTIMIZE_FOR_BOTH))
diff --git a/gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c 
b/gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c
new file mode 100644
index 000..b2c93e55567
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fno-trapping-math -fsigned-zeros" } */
+
+#include 
+
+float
+f1 (float x)
+{
+  return (int) rintf(x);
+}
+
+double
+f2 (double x)
+{
+  return (long) rint(x);
+}
+
+/* { dg-final { scan-assembler "frintx\\ts\[0-9\]+, s\[0-9\]+" } } */
+/* { dg-final { scan-assembler "cvtzs\\ts\[0-9\]+, s\[0-9\]+" } } */
+/* { dg-final { scan-assembler "scvtf\\ts\[0-9\]+, s\[0-9\]+" } } */
+/* { dg-final { scan-assembler "frintx\\td\[0-9\]+, d\[0-9\]+" } } */
+/* { dg-final { scan-assembler "cvtzs\\td\[0-9\]+, d\[0-9\]+" } } */
+/* { dg-final { scan-assembler "scvtf\\td\[0-9\]+, d\[0-9\]+" } } */
+
-- 
2.27.0

[PATCH][Backport][GCC13] match.pd: Only merge truncation with conversion for -fno-signed-zeros

2024-04-29 Thread Joe Ramsay 
This optimisation does not honour signed zeros, so should not be
enabled except with -fno-signed-zeros.

Cherry-pick of 7dd3b2b09cbeb6712ec680a0445cb0ad41070423.

Applies cleanly on releases/gcc-13, regression-tested with no new
failures.

OK for backport to GCC 13? If so, please commit for me as I do not
have commit rights in GCC.

Thanks,
Joe

gcc/ChangeLog:

* match.pd: Fix truncation pattern for -fno-signed-zeroes

gcc/testsuite/ChangeLog:

* gcc.target/aarch64/no_merge_trunc_signed_zero.c: New test.
---
 gcc/match.pd  |  1 +
 .../aarch64/no_merge_trunc_signed_zero.c  | 24 +++
 2 files changed, 25 insertions(+)
 create mode 100644 
gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c

diff --git a/gcc/match.pd b/gcc/match.pd
index 47e48fa2ca5..dc34e7ead9f 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -4188,6 +4188,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
 (simplify
(float (fix_trunc @0))
(if (!flag_trapping_math
+   && !HONOR_SIGNED_ZEROS (type)
&& types_match (type, TREE_TYPE (@0))
&& direct_internal_fn_supported_p (IFN_TRUNC, type,
  OPTIMIZE_FOR_BOTH))
diff --git a/gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c 
b/gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c
new file mode 100644
index 000..b2c93e55567
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/no_merge_trunc_signed_zero.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fno-trapping-math -fsigned-zeros" } */
+
+#include 
+
+float
+f1 (float x)
+{
+  return (int) rintf(x);
+}
+
+double
+f2 (double x)
+{
+  return (long) rint(x);
+}
+
+/* { dg-final { scan-assembler "frintx\\ts\[0-9\]+, s\[0-9\]+" } } */
+/* { dg-final { scan-assembler "cvtzs\\ts\[0-9\]+, s\[0-9\]+" } } */
+/* { dg-final { scan-assembler "scvtf\\ts\[0-9\]+, s\[0-9\]+" } } */
+/* { dg-final { scan-assembler "frintx\\td\[0-9\]+, d\[0-9\]+" } } */
+/* { dg-final { scan-assembler "cvtzs\\td\[0-9\]+, d\[0-9\]+" } } */
+/* { dg-final { scan-assembler "scvtf\\td\[0-9\]+, d\[0-9\]+" } } */
+
-- 
2.27.0

[PATCH] arm: Add +nomve and +nomve.fp options to -mcpu=cortex-m55

2020-08-10 Thread Joe Ramsay 
From: Joe Ramsay 

Hi,

This patch rearranges feature bits for MVE and FP to implement the
following flags for -mcpu=cortex-m55.

  - +nomve:equivalent to armv8.1-m.main+fp.dp+dsp.
  - +nomve.fp: equivalent to armv8.1-m.main+mve+fp.dp (+dsp is implied by +mve).
  - +nofp: equivalent to armv8.1-m.main+mve (+dsp is implied by +mve).
  - +nodsp:equivalent to armv8.1-m.main+fp.dp.

Combinations of the above:

  - +nomve+nofp: equivalent to armv8.1-m.main+dsp.
  - +nodsp+nofp: equivalent to armv8.1-m.main.

Due to MVE and FP sharing vfp_base, some new syntax was required in the CPU
description to implement the concept of 'implied bits'. These are non-named
features added to the ISA late, depending on whether one or more features which
depend on them are present. This means vfp_base can be present when only one of
MVE and FP is removed, but absent when both are removed.

Bootstrapped and tested on arm-none-eabi. OK for master?

Thanks all!
Joe

gcc/ChangeLog:

2020-07-31  Joe Ramsay  

* config/arm/arm-cpus.in:
(ALL_FPU_INTERNAL): Remove vfp_base.
(VFPv2): Remove vfp_base.
(MVE): Remove vfp_base.
(vfp_base): Redefine as implied bit dependent on MVE or FP
(cortex-m55): Add flags to disable MVE, MVE FP, FP and DSP extensions.
* config/arm/arm.c (arm_configure_build_target): Add implied bits to 
ISA.
* config/arm/parsecpu.awk:
(gen_isa): Print implied bits and their dependencies to ISA header.
(gen_data): Add parsing for implied feature bits.

gcc/testsuite/ChangeLog:

2020-07-31  Joe Ramsay  

* gcc.target/arm/cortex-m55-nodsp-flag.c: New test.
* gcc.target/arm/cortex-m55-nodsp-nofp-flag.c: New test.
* gcc.target/arm/cortex-m55-nofp-flag.c: New test.
* gcc.target/arm/cortex-m55-nofp-nomve-flag.c: New test.
* gcc.target/arm/cortex-m55-nomve-flag.c: New test.
* gcc.target/arm/cortex-m55-nomve.fp-flag.c: New test.
---
 gcc/config/arm/arm-cpus.in | 26 ---
 gcc/config/arm/arm.c   | 14 ++
 gcc/config/arm/parsecpu.awk| 51 ++
 .../gcc.target/arm/cortex-m55-nodsp-flag-hard.c| 15 +++
 .../gcc.target/arm/cortex-m55-nodsp-flag-softfp.c  | 15 +++
 .../arm/cortex-m55-nodsp-nofp-flag-softfp.c| 15 +++
 .../gcc.target/arm/cortex-m55-nofp-flag-hard.c | 15 +++
 .../gcc.target/arm/cortex-m55-nofp-flag-softfp.c   | 15 +++
 .../arm/cortex-m55-nofp-nomve-flag-softfp.c| 15 +++
 .../gcc.target/arm/cortex-m55-nomve-flag-hard.c| 15 +++
 .../gcc.target/arm/cortex-m55-nomve-flag-softfp.c  | 15 +++
 .../gcc.target/arm/cortex-m55-nomve.fp-flag-hard.c | 15 +++
 .../arm/cortex-m55-nomve.fp-flag-softfp.c  | 15 +++
 13 files changed, 234 insertions(+), 7 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/arm/cortex-m55-nodsp-flag-hard.c
 create mode 100644 gcc/testsuite/gcc.target/arm/cortex-m55-nodsp-flag-softfp.c
 create mode 100644 
gcc/testsuite/gcc.target/arm/cortex-m55-nodsp-nofp-flag-softfp.c
 create mode 100644 gcc/testsuite/gcc.target/arm/cortex-m55-nofp-flag-hard.c
 create mode 100644 gcc/testsuite/gcc.target/arm/cortex-m55-nofp-flag-softfp.c
 create mode 100644 
gcc/testsuite/gcc.target/arm/cortex-m55-nofp-nomve-flag-softfp.c
 create mode 100644 gcc/testsuite/gcc.target/arm/cortex-m55-nomve-flag-hard.c
 create mode 100644 gcc/testsuite/gcc.target/arm/cortex-m55-nomve-flag-softfp.c
 create mode 100644 gcc/testsuite/gcc.target/arm/cortex-m55-nomve.fp-flag-hard.c
 create mode 100644 
gcc/testsuite/gcc.target/arm/cortex-m55-nomve.fp-flag-softfp.c

diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in
index c98f8ed..5083028 100644
--- a/gcc/config/arm/arm-cpus.in
+++ b/gcc/config/arm/arm-cpus.in
@@ -135,10 +135,6 @@ define feature armv8_1m_main
 # Floating point and Neon extensions.
 # VFPv1 is not supported in GCC.
 
-# This feature bit is enabled for all VFP, MVE and
-# MVE with floating point extensions.
-define feature vfp_base
-
 # Vector floating point v2.
 define feature vfpv2
 
@@ -251,7 +247,7 @@ define fgroup ALL_SIMD  ALL_SIMD_INTERNAL 
ALL_SIMD_EXTERNAL
 
 # List of all FPU bits to strip out if -mfpu is used to override the
 # default.  fp16 is deliberately missing from this list.
-define fgroup ALL_FPU_INTERNAL vfp_base vfpv2 vfpv3 vfpv4 fpv5 fp16conv fp_dbl 
ALL_SIMD_INTERNAL
+define fgroup ALL_FPU_INTERNAL vfpv2 vfpv3 vfpv4 fpv5 fp16conv fp_dbl 
ALL_SIMD_INTERNAL
 # Similarly, but including fp16 and other extensions that aren't part of
 # -mfpu support.
 define fgroup ALL_FPU_EXTERNAL fp16 bf16
@@ -296,11 +292,11 @@ define fgroup ARMv8r  ARMv8a
 define fgroup ARMv8_1m_main ARMv8m_main armv8_1m_main
 
 # Useful combinations.
-define fgroup VFPv2vfp_base vfpv2
+define fgroup VFPv2vfpv2
 define fgroup VFPv3VFPv2 vfpv3
 define fgroup VFPv4VFPv3 vfpv4 f

[PATCH] arm: Remove coercion from scalar argument to vmin & vmax intrinsics

2020-08-13 Thread Joe Ramsay 
From: Joe Ramsay 

Hi,

This patch fixes an issue with vmin* and vmax* intrinsics which accept
a scalar argument. Previously when the scalar was of different width
to the vector elements this would generate __ARM_undef. This change
allows the scalar argument to be implicitly converted to the correct
width. Also tidied up the relevant unit tests, some of which would
have passed even if only one of two or three intrinsic calls had
compiled correctly.

Bootstrapped and tested on arm-none-eabi, gcc and CMSIS_DSP
testsuites are clean. OK for trunk?

Thanks,
Joe

gcc/ChangeLog:

2020-08-10  Joe Ramsay 

* config/arm/arm_mve.h (__arm_vmaxnmavq): Remove coercion of scalar
argument.
(__arm_vmaxnmvq): Likewise.
(__arm_vminnmavq): Likewise.
(__arm_vminnmvq): Likewise.
(__arm_vmaxnmavq_p): Likewise.
(__arm_vmaxnmvq_p): Likewise (and delete duplicate definition).
(__arm_vminnmavq_p): Likewise.
(__arm_vminnmvq_p): Likewise.
(__arm_vmaxavq): Likewise.
(__arm_vmaxavq_p): Likewise.
(__arm_vmaxvq): Likewise.
(__arm_vmaxvq_p): Likewise.
(__arm_vminavq): Likewise.
(__arm_vminavq_p): Likewise.
(__arm_vminvq): Likewise.
(__arm_vminvq_p): Likewise.

gcc/testsuite/ChangeLog:

2020-08-10  Joe Ramsay 

* gcc.target/arm/mve/intrinsics/vmaxavq_p_s16.c: Add test for mismatched
width of scalar argument.
* gcc.target/arm/mve/intrinsics/vmaxavq_p_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxavq_p_s8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxavq_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxavq_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxavq_s8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxnmavq_f16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxnmavq_f32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxnmavq_p_f16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxnmavq_p_f32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxnmvq_f16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxnmvq_f32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxnmvq_p_f16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxnmvq_p_f32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxvq_p_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxvq_p_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxvq_p_s8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxvq_p_u16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxvq_p_u32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxvq_p_u8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxvq_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxvq_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxvq_s8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxvq_u16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxvq_u32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vmaxvq_u8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminavq_p_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminavq_p_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminavq_p_s8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminavq_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminavq_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminavq_s8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminnmavq_f16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminnmavq_f32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminnmavq_p_f16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminnmavq_p_f32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminnmvq_f16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminnmvq_f32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminnmvq_p_f16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminnmvq_p_f32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminvq_p_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminvq_p_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminvq_p_s8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminvq_p_u16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminvq_p_u32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminvq_p_u8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminvq_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminvq_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminvq_s8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminvq_u16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminvq_u32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vminvq_u8.c: Likewise.
---
 gcc/config/arm/arm_mve.h   | 110 ++---
 .../gcc.target/arm/mve/intrinsics/vmaxavq_p_s16.c  |  11 ++-
 .../gcc.target/arm/mve/intrinsics/vmaxavq_p_s32.c

[PATCH] arm: Require MVE memory operand for destination of vst1q intrinsic

2020-08-13 Thread Joe Ramsay 
From: Joe Ramsay 

Hi,

Previously, the machine description patterns for vst1q accepted a generic memory
operand for the destination, which could lead to an unrecognised builtin when
expanding vst1q* intrinsics. This change fixes the patterns to only accept MVE
memory operands.

Tested on arm-none-eabi, clean w.r.t. gcc and CMSIS-DSP testsuites. OK for
trunk?

Thanks,
Joe

gcc/ChangeLog:

2020-08-13  Joe Ramsay 

* config/arm/mve.md (mve_vst1q_f): Require MVE memory operand for
destination.
(mve_vst1q_): Likewise.

gcc/testsuite/ChangeLog:

2020-08-13  Joe Ramsay 

* gcc.target/arm/mve/intrinsics/vst1q_f16.c: Add test that only MVE
memory operand is accepted.
* gcc.target/arm/mve/intrinsics/vst1q_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vst1q_s8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vst1q_u16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vst1q_u8.c: Likewise.
---
 gcc/config/arm/mve.md   |  4 ++--
 gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c | 10 +++---
 gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c | 10 +++---
 gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s8.c  | 10 +++---
 gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_u16.c | 10 +++---
 gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_u8.c  | 10 +++---
 6 files changed, 37 insertions(+), 17 deletions(-)

diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
index 9758862..465b39a 100644
--- a/gcc/config/arm/mve.md
+++ b/gcc/config/arm/mve.md
@@ -9330,7 +9330,7 @@
   [(set_attr "length" "4")])
 
 (define_expand "mve_vst1q_f"
-  [(match_operand: 0 "memory_operand")
+  [(match_operand: 0 "mve_memory_operand")
(unspec: [(match_operand:MVE_0 1 "s_register_operand")] VST1Q_F)
   ]
   "TARGET_HAVE_MVE || TARGET_HAVE_MVE_FLOAT"
@@ -9340,7 +9340,7 @@
 })
 
 (define_expand "mve_vst1q_"
-  [(match_operand:MVE_2 0 "memory_operand")
+  [(match_operand:MVE_2 0 "mve_memory_operand")
(unspec:MVE_2 [(match_operand:MVE_2 1 "s_register_operand")] VST1Q)
   ]
   "TARGET_HAVE_MVE"
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c 
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c
index 363b4ca..312b746 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c
@@ -10,12 +10,16 @@ foo (float16_t * addr, float16x8_t value)
   vst1q_f16 (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrh.16"  }  } */
-
 void
 foo1 (float16_t * addr, float16x8_t value)
 {
   vst1q (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrh.16"  }  } */
+/* { dg-final { scan-assembler-times "vstrh.16" 2 }  } */
+
+void
+foo2 (float16_t a, float16x8_t x)
+{
+  vst1q (&a, x);
+}
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c 
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c
index 37c4713..cd14e2c 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c
@@ -10,12 +10,16 @@ foo (int16_t * addr, int16x8_t value)
   vst1q_s16 (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrh.16"  }  } */
-
 void
 foo1 (int16_t * addr, int16x8_t value)
 {
   vst1q (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrh.16"  }  } */
+/* { dg-final { scan-assembler-times "vstrh.16" 2 }  } */
+
+void
+foo2 (int16_t a, int16x8_t x)
+{
+  vst1q (&a, x);
+}
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s8.c 
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s8.c
index fe5edea..0004c80 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s8.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s8.c
@@ -10,12 +10,16 @@ foo (int8_t * addr, int8x16_t value)
   vst1q_s8 (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrb.8"  }  } */
-
 void
 foo1 (int8_t * addr, int8x16_t value)
 {
   vst1q (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrb.8"  }  } */
+/* { dg-final { scan-assembler-times "vstrb.8" 2 }  } */
+
+void
+foo2 (int8_t a, int8x16_t x)
+{
+  vst1q (&a, x);
+}
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_u16.c 
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_u16.c
index a4c8c1a..248e7ce 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_u16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_u16.c
@@ -10,12 +10,16 @@ foo (uint16_t * addr, uint16x8_t value)
   vst1q_u16 (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrh.16"  }  } */
-
 void
 foo1 (uint16_t * addr, uint16x8_t value)
 {
   vst1q (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrh.16"  }  } */
+/* { dg-final { scan

[PATCH v2][GCC] arm: Add +nomve and +nomve.fp options to -mcpu=cortex-m55

2020-08-19 Thread Joe Ramsay 
From: Joe Ramsay 

Hi all,

This patch rearranges feature bits for MVE and FP to implement the
following flags for -mcpu=cortex-m55.

  - +nomve:equivalent to armv8.1-m.main+fp.dp+dsp.
  - +nomve.fp: equivalent to armv8.1-m.main+mve+fp.dp (+dsp is implied by +mve).
  - +nofp: equivalent to armv8.1-m.main+mve (+dsp is implied by +mve).
  - +nodsp:equivalent to armv8.1-m.main+fp.dp.

Combinations of the above:

  - +nomve+nofp: equivalent to armv8.1-m.main+dsp.
  - +nodsp+nofp: equivalent to armv8.1-m.main.

Due to MVE and FP sharing vfp_base, some new syntax was required in the CPU
description to implement the concept of 'implied bits'. These are non-named
features added to the ISA late, depending on whether one or more features which
depend on them are present. This means vfp_base can be present when only one of
MVE and FP is removed, but absent when both are removed.

Bootstrapped and tested on arm-none-eabi. OK for master?

Thanks,
Joe

gcc/ChangeLog:

2020-07-31  Joe Ramsay  

* config/arm/arm-cpus.in:
(ALL_FPU_INTERNAL): Remove vfp_base.
(VFPv2): Remove vfp_base.
(MVE): Remove vfp_base.
(vfp_base): Redefine as implied bit dependent on MVE or FP
(cortex-m55): Add flags to disable MVE, MVE FP, FP and DSP extensions.
* config/arm/arm.c (arm_configure_build_target): Add implied bits to 
ISA.
* config/arm/parsecpu.awk:
(gen_isa): Print implied bits and their dependencies to ISA header.
(gen_data): Add parsing for implied feature bits.

gcc/testsuite/ChangeLog:

2020-07-31  Joe Ramsay  

* gcc.target/arm/multilib.exp: Add tests for -mcpu=cortex-m55.
* gcc.target/arm/cortex-m55-nodsp-flag.c: New test.
* gcc.target/arm/cortex-m55-nodsp-nofp-flag.c: New test.
* gcc.target/arm/cortex-m55-nofp-flag.c: New test.
* gcc.target/arm/cortex-m55-nofp-nomve-flag.c: New test.
* gcc.target/arm/cortex-m55-nomve-flag.c: New test.
* gcc.target/arm/cortex-m55-nomve.fp-flag.c: New test.
---
 gcc/config/arm/arm-cpus.in | 26 ---
 gcc/config/arm/arm.c   | 14 ++
 gcc/config/arm/parsecpu.awk| 51 ++
 .../gcc.target/arm/cortex-m55-nodsp-flag-hard.c| 15 +++
 .../gcc.target/arm/cortex-m55-nodsp-flag-softfp.c  | 15 +++
 .../arm/cortex-m55-nodsp-nofp-flag-softfp.c| 15 +++
 .../gcc.target/arm/cortex-m55-nofp-flag-hard.c | 15 +++
 .../gcc.target/arm/cortex-m55-nofp-flag-softfp.c   | 15 +++
 .../arm/cortex-m55-nofp-nomve-flag-softfp.c| 15 +++
 .../gcc.target/arm/cortex-m55-nomve-flag-hard.c| 15 +++
 .../gcc.target/arm/cortex-m55-nomve-flag-softfp.c  | 15 +++
 .../gcc.target/arm/cortex-m55-nomve.fp-flag-hard.c | 15 +++
 .../arm/cortex-m55-nomve.fp-flag-softfp.c  | 15 +++
 gcc/testsuite/gcc.target/arm/multilib.exp  | 16 +++
 14 files changed, 250 insertions(+), 7 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/arm/cortex-m55-nodsp-flag-hard.c
 create mode 100644 gcc/testsuite/gcc.target/arm/cortex-m55-nodsp-flag-softfp.c
 create mode 100644 
gcc/testsuite/gcc.target/arm/cortex-m55-nodsp-nofp-flag-softfp.c
 create mode 100644 gcc/testsuite/gcc.target/arm/cortex-m55-nofp-flag-hard.c
 create mode 100644 gcc/testsuite/gcc.target/arm/cortex-m55-nofp-flag-softfp.c
 create mode 100644 
gcc/testsuite/gcc.target/arm/cortex-m55-nofp-nomve-flag-softfp.c
 create mode 100644 gcc/testsuite/gcc.target/arm/cortex-m55-nomve-flag-hard.c
 create mode 100644 gcc/testsuite/gcc.target/arm/cortex-m55-nomve-flag-softfp.c
 create mode 100644 gcc/testsuite/gcc.target/arm/cortex-m55-nomve.fp-flag-hard.c
 create mode 100644 
gcc/testsuite/gcc.target/arm/cortex-m55-nomve.fp-flag-softfp.c

diff --git a/gcc/config/arm/arm-cpus.in b/gcc/config/arm/arm-cpus.in
index c98f8ed..5083028 100644
--- a/gcc/config/arm/arm-cpus.in
+++ b/gcc/config/arm/arm-cpus.in
@@ -135,10 +135,6 @@ define feature armv8_1m_main
 # Floating point and Neon extensions.
 # VFPv1 is not supported in GCC.
 
-# This feature bit is enabled for all VFP, MVE and
-# MVE with floating point extensions.
-define feature vfp_base
-
 # Vector floating point v2.
 define feature vfpv2
 
@@ -251,7 +247,7 @@ define fgroup ALL_SIMD  ALL_SIMD_INTERNAL 
ALL_SIMD_EXTERNAL
 
 # List of all FPU bits to strip out if -mfpu is used to override the
 # default.  fp16 is deliberately missing from this list.
-define fgroup ALL_FPU_INTERNAL vfp_base vfpv2 vfpv3 vfpv4 fpv5 fp16conv fp_dbl 
ALL_SIMD_INTERNAL
+define fgroup ALL_FPU_INTERNAL vfpv2 vfpv3 vfpv4 fpv5 fp16conv fp_dbl 
ALL_SIMD_INTERNAL
 # Similarly, but including fp16 and other extensions that aren't part of
 # -mfpu support.
 define fgroup ALL_FPU_EXTERNAL fp16 bf16
@@ -296,11 +292,11 @@ define fgroup ARMv8r  ARMv8a
 define fgroup ARMv8_1m_main ARMv8m_main armv8_1m_main
 
 # Useful combinations.
-defi

Re: [PATCH] arm: Require MVE memory operand for destination of vst1q intrinsic

2020-08-20 Thread Joe Ramsay 
Hi Ramana,

Thanks for the review.

On 18/08/2020, 18:37, "Ramana Radhakrishnan"  wrote:

On Thu, Aug 13, 2020 at 2:18 PM Joe Ramsay  wrote:
>
    > From: Joe Ramsay 
>
> Hi,
>
> Previously, the machine description patterns for vst1q accepted a generic 
memory
> operand for the destination, which could lead to an unrecognised builtin 
when
> expanding vst1q* intrinsics. This change fixes the patterns to only 
accept MVE
> memory operands.

This is OK though I suspect this needs a PR and a backport request for GCC 
10.

There's now a PR for this, 96683. I've attached an updated patch file, the only 
change is
that I've included the PR number in the changelog. Please let me know if this 
is OK for
trunk.

Thanks,
Joe

regards
Ramana

>
> Thanks,
    > Joe
>
> gcc/ChangeLog:
>
> 2020-08-13  Joe Ramsay 
>
> * config/arm/mve.md (mve_vst1q_f): Require MVE memory 
operand for
> destination.
> (mve_vst1q_): Likewise.
>
> gcc/testsuite/ChangeLog:
>
> 2020-08-13  Joe Ramsay 
>
> * gcc.target/arm/mve/intrinsics/vst1q_f16.c: Add test that only 
MVE
> memory operand is accepted.
> * gcc.target/arm/mve/intrinsics/vst1q_s16.c: Likewise.
> * gcc.target/arm/mve/intrinsics/vst1q_s8.c: Likewise.
> * gcc.target/arm/mve/intrinsics/vst1q_u16.c: Likewise.
> * gcc.target/arm/mve/intrinsics/vst1q_u8.c: Likewise.
> ---
>  gcc/config/arm/mve.md   |  4 ++--
>  gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c | 10 +++---
>  gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c | 10 +++---
>  gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s8.c  | 10 +++---
>  gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_u16.c | 10 +++---
>  gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_u8.c  | 10 +++---
>  6 files changed, 37 insertions(+), 17 deletions(-)
>
> diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
> index 9758862..465b39a 100644
> --- a/gcc/config/arm/mve.md
> +++ b/gcc/config/arm/mve.md
> @@ -9330,7 +9330,7 @@
>[(set_attr "length" "4")])
>
>  (define_expand "mve_vst1q_f"
> -  [(match_operand: 0 "memory_operand")
> +  [(match_operand: 0 "mve_memory_operand")
> (unspec: [(match_operand:MVE_0 1 "s_register_operand")] 
VST1Q_F)
>]
>"TARGET_HAVE_MVE || TARGET_HAVE_MVE_FLOAT"
> @@ -9340,7 +9340,7 @@
>  })
>
>  (define_expand "mve_vst1q_"
> -  [(match_operand:MVE_2 0 "memory_operand")
> +  [(match_operand:MVE_2 0 "mve_memory_operand")
> (unspec:MVE_2 [(match_operand:MVE_2 1 "s_register_operand")] VST1Q)
>]
>"TARGET_HAVE_MVE"
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c 
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c
> index 363b4ca..312b746 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c
> @@ -10,12 +10,16 @@ foo (float16_t * addr, float16x8_t value)
>vst1q_f16 (addr, value);
>  }
>
> -/* { dg-final { scan-assembler "vstrh.16"  }  } */
> -
>  void
>  foo1 (float16_t * addr, float16x8_t value)
>  {
>vst1q (addr, value);
>  }
>
> -/* { dg-final { scan-assembler "vstrh.16"  }  } */
> +/* { dg-final { scan-assembler-times "vstrh.16" 2 }  } */
> +
> +void
> +foo2 (float16_t a, float16x8_t x)
> +{
> +  vst1q (&a, x);
> +}
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c 
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c
> index 37c4713..cd14e2c 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c
> @@ -10,12 +10,16 @@ foo (int16_t * addr, int16x8_t value)
>vst1q_s16 (addr, value);
>  }
>
> -/* { dg-final { scan-assembler "vstrh.16"  }  } */
> -
>  void
>  foo1 (int16_t * addr, int16x8_t value)
>  {
>vst1q (addr, value);
>  }
>
> -/* { dg-final { scan-assembler "vstrh.16"  }  } */
> +/* { dg-final { scan-assembler-times "vstrh.16" 2 }  } */
> +
> +void
> +f

[PATCH][GCC][GCC-10 backport] arm: Require MVE memory operand for destination of vst1q intrinsic

2020-08-21 Thread Joe Ramsay 
From: Joe Ramsay 

Hi,

Previously, the machine description patterns for vst1q accepted a generic memory
operand for the destination, which could lead to an unrecognised builtin when
expanding vst1q* intrinsics. This change fixes the pattern to only accept MVE
memory operands.

Tested on arm-none-eabi, clean w.r.t. gcc and CMSIS-DSP testsuites. Backports
cleanly onto gcc-10 branch. OK for backport?

Thanks,
Joe

gcc/ChangeLog:

PR target/96683
* config/arm/mve.md (mve_vst1q_f): Require MVE memory operand for
destination.
(mve_vst1q_): Likewise.

gcc/testsuite/ChangeLog:

PR target/96683
* gcc.target/arm/mve/intrinsics/vst1q_f16.c: New test.
* gcc.target/arm/mve/intrinsics/vst1q_s16.c: New test.
* gcc.target/arm/mve/intrinsics/vst1q_s8.c: New test.
* gcc.target/arm/mve/intrinsics/vst1q_u16.c: New test.
* gcc.target/arm/mve/intrinsics/vst1q_u8.c: New test.

(cherry picked from commit 91d206adfe39ce063f6a5731b92a03c05e82e94a)
---
 gcc/config/arm/mve.md   |  4 ++--
 gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c | 10 +++---
 gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c | 10 +++---
 gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s8.c  | 10 +++---
 gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_u16.c | 10 +++---
 gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_u8.c  | 10 +++---
 6 files changed, 37 insertions(+), 17 deletions(-)

diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
index 9758862..465b39a 100644
--- a/gcc/config/arm/mve.md
+++ b/gcc/config/arm/mve.md
@@ -9330,7 +9330,7 @@
   [(set_attr "length" "4")])
 
 (define_expand "mve_vst1q_f"
-  [(match_operand: 0 "memory_operand")
+  [(match_operand: 0 "mve_memory_operand")
(unspec: [(match_operand:MVE_0 1 "s_register_operand")] VST1Q_F)
   ]
   "TARGET_HAVE_MVE || TARGET_HAVE_MVE_FLOAT"
@@ -9340,7 +9340,7 @@
 })
 
 (define_expand "mve_vst1q_"
-  [(match_operand:MVE_2 0 "memory_operand")
+  [(match_operand:MVE_2 0 "mve_memory_operand")
(unspec:MVE_2 [(match_operand:MVE_2 1 "s_register_operand")] VST1Q)
   ]
   "TARGET_HAVE_MVE"
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c 
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c
index 363b4ca..312b746 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_f16.c
@@ -10,12 +10,16 @@ foo (float16_t * addr, float16x8_t value)
   vst1q_f16 (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrh.16"  }  } */
-
 void
 foo1 (float16_t * addr, float16x8_t value)
 {
   vst1q (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrh.16"  }  } */
+/* { dg-final { scan-assembler-times "vstrh.16" 2 }  } */
+
+void
+foo2 (float16_t a, float16x8_t x)
+{
+  vst1q (&a, x);
+}
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c 
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c
index 37c4713..cd14e2c 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s16.c
@@ -10,12 +10,16 @@ foo (int16_t * addr, int16x8_t value)
   vst1q_s16 (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrh.16"  }  } */
-
 void
 foo1 (int16_t * addr, int16x8_t value)
 {
   vst1q (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrh.16"  }  } */
+/* { dg-final { scan-assembler-times "vstrh.16" 2 }  } */
+
+void
+foo2 (int16_t a, int16x8_t x)
+{
+  vst1q (&a, x);
+}
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s8.c 
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s8.c
index fe5edea..0004c80 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s8.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_s8.c
@@ -10,12 +10,16 @@ foo (int8_t * addr, int8x16_t value)
   vst1q_s8 (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrb.8"  }  } */
-
 void
 foo1 (int8_t * addr, int8x16_t value)
 {
   vst1q (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrb.8"  }  } */
+/* { dg-final { scan-assembler-times "vstrb.8" 2 }  } */
+
+void
+foo2 (int8_t a, int8x16_t x)
+{
+  vst1q (&a, x);
+}
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_u16.c 
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_u16.c
index a4c8c1a..248e7ce 100644
--- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_u16.c
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vst1q_u16.c
@@ -10,12 +10,16 @@ foo (uint16_t * addr, uint16x8_t value)
   vst1q_u16 (addr, value);
 }
 
-/* { dg-final { scan-assembler "vstrh.16"  }  } */
-
 void
 foo1 (uint16_t * addr, uint16x8_t value)
 {
   vst1q (addr, value);
 }
 
-/* { dg-final { scan-assemb

[PATCH]: Optimize a >= 0 && b >= 0 to (a | b) >= 0 [PR95731]

2020-07-10 Thread Joe Ramsay 
Hi!

This is a fix for PR95731, which adds a new pattern to simplify a >= 0 && b >= 
0 to (a | b) >= 0. Bootstrapped and tested on x86_linux and aarch64_linux. Any 
comments are appreciated.

Thanks,
Joe

gcc/ChangeLog:

2020-05-20  Joe Ramsay  

* match.pd: New pattern to optimize a >= 0 && b >= 0 to (a | b) >= 0

gcc/testsuite/ChangeLog:

2020-05-20  Joe Ramsay  

* gcc.dg/tree-ssa/pr95731-1.c: New test.
* gcc.dg/tree-ssa/pr95731-2.c: New test.



pr95731.diff
Description: pr95731.diff

[PATCH v2]: Optimize a >= 0 && b >= 0 to (a | b) >= 0 [PR95731]

2020-07-10 Thread Joe Ramsay 
Hi!

Apologies, resending as I previously attached the wrong patch file. This is a 
fix for PR95731, which adds a new pattern to simplify a >= 0 && b >= 0 to (a | 
b) >= 0. Bootstrapped and tested on x86_linux and aarch64_linux. Any comments 
are appreciated.

Thanks,
Joe

gcc/ChangeLog:

2020-05-20  Joe Ramsay  mailto:joe.ram...@arm.com>>

* match.pd: New simplication.

gcc/testsuite/ChangeLog:

2020-05-20  Joe Ramsay  mailto:joe.ram...@arm.com>>

* gcc.dg/tree-ssa/pr95731-1.c: New test.
* gcc.dg/tree-ssa/pr95731-2.c: New test.



pr95731.diff
Description: pr95731.diff

[PATCH] [PATCH][GCC] arm: Enable no-writeback vldr.16/vstr.16.

2020-07-27 Thread Joe Ramsay 
Hi,

There was previously no way to specify that a register operand cannot
have any writeback modifiers, and as a result the argument to vldr.16
and vstr.16 could be erroneously output with post-increment. This
change adds an operand specifier which forbids all writeback, and
selects it in the relevant case for vldr.16 and vstr.16

Bootstrapped on arm-linux, gcc and CMSIS-DSP testsuites are clean.
Is this patch OK for trunk? If yes, please commit on my behalf as I don't
have commit rights.

Thanks,
Joe

gcc/ChangeLog:

2020-05-20  Joe Ramsay  

* config/arm/arm-protos.h (arm_coproc_mem_operand_no_writeback): 
Declare prototype.
(arm_mve_mode_and_operands_type_check): Declare prototype.
* config/arm/arm.c (arm_coproc_mem_operand): Refactor to use 
_arm_coproc_mem_operand.
(arm_coproc_mem_operand_wb): New function to cover full, limited and no 
writeback.
(arm_coproc_mem_operand_no_writeback): New constraint for memory 
operand with no writeback.
(arm_print_operand): Implement 'j' specifier for memory operand that 
does not support
writeback.
(arm_mve_mode_and_operands_type_check): New constraint check for MVE 
memory operands.
* config/arm/constraints.md: Add Uj constraint for VFP vldr.16 and 
vstr.16.
* config/arm/vfp.md (*mov_load_vfp_hf16): New pattern for vldr.16.
(*mov_store_vfp_hf16): New pattern for vstr.16.
(*mov_vfp_16): Remove MVE moves.

gcc/testsuite/ChangeLog:

2020-05-20  Joe Ramsay  

* gcc.target/arm/mve/intrinsics/mve-vldstr16-no-writeback.c: New test.

---
 gcc/config/arm/arm-protos.h|   3 +
 gcc/config/arm/arm.c   | 100 ++---
 gcc/config/arm/constraints.md  |   7 ++
 gcc/config/arm/vfp.md  |  28 --
 .../arm/mve/intrinsics/mve-vldstr16-no-writeback.c |  17 
 5 files changed, 135 insertions(+), 20 deletions(-)
 create mode 100644 
gcc/testsuite/gcc.target/arm/mve/intrinsics/mve-vldstr16-no-writeback.c

diff --git a/gcc/config/arm/arm-protos.h b/gcc/config/arm/arm-protos.h
index 33d162c..e811da4 100644
--- a/gcc/config/arm/arm-protos.h
+++ b/gcc/config/arm/arm-protos.h
@@ -115,8 +115,11 @@ extern enum reg_class coproc_secondary_reload_class 
(machine_mode, rtx,
 extern bool arm_tls_referenced_p (rtx);
 
 extern int arm_coproc_mem_operand (rtx, bool);
+extern int arm_coproc_mem_operand_no_writeback (rtx);
+extern int arm_coproc_mem_operand_wb (rtx, int);
 extern int neon_vector_mem_operand (rtx, int, bool);
 extern int mve_vector_mem_operand (machine_mode, rtx, bool);
+bool arm_mve_mode_and_operands_type_check (machine_mode, rtx, rtx);
 extern int neon_struct_mem_operand (rtx);
 
 extern rtx *neon_vcmla_lane_prepare_operands (rtx *);
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index 6b7ca82..ed080d2 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -13217,13 +13217,14 @@ neon_element_bits (machine_mode mode)
 /* Predicates for `match_operand' and `match_operator'.  */
 
 /* Return TRUE if OP is a valid coprocessor memory address pattern.
-   WB is true if full writeback address modes are allowed and is false
+   WB level is 2 if full writeback address modes are allowed, 1
if limited writeback address modes (POST_INC and PRE_DEC) are
-   allowed.  */
+   allowed and 0 if no writeback at all is supported.  */
 
 int
-arm_coproc_mem_operand (rtx op, bool wb)
+arm_coproc_mem_operand_wb (rtx op, int wb_level)
 {
+  gcc_assert (wb_level == 0 || wb_level == 1 || wb_level == 2);
   rtx ind;
 
   /* Reject eliminable registers.  */
@@ -13256,16 +13257,18 @@ arm_coproc_mem_operand (rtx op, bool wb)
 
   /* Autoincremment addressing modes.  POST_INC and PRE_DEC are
  acceptable in any case (subject to verification by
- arm_address_register_rtx_p).  We need WB to be true to accept
+ arm_address_register_rtx_p).  We need full writeback to accept
+ PRE_INC and POST_DEC, and at least restricted writeback for
  PRE_INC and POST_DEC.  */
-  if (GET_CODE (ind) == POST_INC
-  || GET_CODE (ind) == PRE_DEC
-  || (wb
- && (GET_CODE (ind) == PRE_INC
- || GET_CODE (ind) == POST_DEC)))
+  if (wb_level > 0
+  && (GET_CODE (ind) == POST_INC
+ || GET_CODE (ind) == PRE_DEC
+ || (wb_level > 1
+ && (GET_CODE (ind) == PRE_INC
+ || GET_CODE (ind) == POST_DEC
 return arm_address_register_rtx_p (XEXP (ind, 0), 0);
 
-  if (wb
+  if (wb_level > 1
   && (GET_CODE (ind) == POST_MODIFY || GET_CODE (ind) == PRE_MODIFY)
   && arm_address_register_rtx_p (XEXP (ind, 0), 0)
   && GET_CODE (XEXP (ind, 1)) == PLUS
@@ -13287,6 +13290,25 @@ arm_coproc_mem_operand (rtx op, bool wb)
   return FALSE;
 }
 
+/* Return TRUE if OP is a valid coprocessor memory address pattern.
+   WB is true

Re: [PATCH] [PATCH][GCC] arm: Enable no-writeback vldr.16/vstr.16.

2020-07-28 Thread Joe Ramsay 
Thanks for the feedback Kyrill.

On 28/07/2020, 10:16, "Kyrylo Tkachov"  wrote:

Hi Joe,

> -Original Message-
> From: Gcc-patches  On Behalf Of Joe
> Ramsay
> Sent: 27 July 2020 15:08
> To: Jakub Jelinek via Gcc-patches 
> Subject: [PATCH] [PATCH][GCC] arm: Enable no-writeback vldr.16/vstr.16.
> 
> Hi,
> 
> There was previously no way to specify that a register operand cannot
> have any writeback modifiers, and as a result the argument to vldr.16
> and vstr.16 could be erroneously output with post-increment. This
> change adds an operand specifier which forbids all writeback, and
> selects it in the relevant case for vldr.16 and vstr.16
> 
> Bootstrapped on arm-linux, gcc and CMSIS-DSP testsuites are clean.
> Is this patch OK for trunk? If yes, please commit on my behalf as I don't
> have commit rights.
> 
> Thanks,
> Joe
> 
> gcc/ChangeLog:
> 
> 2020-05-20  Joe Ramsay  
> 
> * config/arm/arm-protos.h (arm_coproc_mem_operand_no_writeback):
> Declare prototype.
> (arm_mve_mode_and_operands_type_check): Declare prototype.
> * config/arm/arm.c (arm_coproc_mem_operand): Refactor to use
> _arm_coproc_mem_operand.
> (arm_coproc_mem_operand_wb): New function to cover full, limited
> and no writeback.
> (arm_coproc_mem_operand_no_writeback): New constraint for
> memory operand with no writeback.
> (arm_print_operand): Implement 'j' specifier for memory operand 
that
> does not support
> writeback.
> (arm_mve_mode_and_operands_type_check): New constraint check for
> MVE memory operands.
> * config/arm/constraints.md: Add Uj constraint for VFP vldr.16 and
> vstr.16.
> * config/arm/vfp.md (*mov_load_vfp_hf16): New pattern for vldr.16.
> (*mov_store_vfp_hf16): New pattern for vstr.16.
> (*mov_vfp_16): Remove MVE moves.
> 
> gcc/testsuite/ChangeLog:
> 
> 2020-05-20  Joe Ramsay  
> 
> * gcc.target/arm/mve/intrinsics/mve-vldstr16-no-writeback.c: New 
test.
> 
> ---
>  gcc/config/arm/arm-protos.h|   3 +
>  gcc/config/arm/arm.c   | 100 
++---
>  gcc/config/arm/constraints.md  |   7 ++
>  gcc/config/arm/vfp.md  |  28 --
>  .../arm/mve/intrinsics/mve-vldstr16-no-writeback.c |  17 
>  5 files changed, 135 insertions(+), 20 deletions(-)
>  create mode 100644 gcc/testsuite/gcc.target/arm/mve/intrinsics/mve-
> vldstr16-no-writeback.c
> 
> diff --git a/gcc/config/arm/arm-protos.h b/gcc/config/arm/arm-protos.h
> index 33d162c..e811da4 100644
> --- a/gcc/config/arm/arm-protos.h
> +++ b/gcc/config/arm/arm-protos.h
> @@ -115,8 +115,11 @@ extern enum reg_class
> coproc_secondary_reload_class (machine_mode, rtx,
>  extern bool arm_tls_referenced_p (rtx);
> 
>  extern int arm_coproc_mem_operand (rtx, bool);
> +extern int arm_coproc_mem_operand_no_writeback (rtx);
> +extern int arm_coproc_mem_operand_wb (rtx, int);
>  extern int neon_vector_mem_operand (rtx, int, bool);
>  extern int mve_vector_mem_operand (machine_mode, rtx, bool);
> +bool arm_mve_mode_and_operands_type_check (machine_mode, rtx, rtx);
>  extern int neon_struct_mem_operand (rtx);
> 
>  extern rtx *neon_vcmla_lane_prepare_operands (rtx *);
> diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
> index 6b7ca82..ed080d2 100644
> --- a/gcc/config/arm/arm.c
> +++ b/gcc/config/arm/arm.c
> @@ -13217,13 +13217,14 @@ neon_element_bits (machine_mode mode)
>  /* Predicates for `match_operand' and `match_operator'.  */
> 
>  /* Return TRUE if OP is a valid coprocessor memory address pattern.
> -   WB is true if full writeback address modes are allowed and is false
> +   WB level is 2 if full writeback address modes are allowed, 1
> if limited writeback address modes (POST_INC and PRE_DEC) are
> -   allowed.  */
> +   allowed and 0 if no writeback at all is supported.  */
> 
>  int
> -arm_coproc_mem_operand (rtx op, bool wb)
> +arm_coproc_mem_operand_wb (rtx op, int wb_level)
>  {
> +  gcc_assert (wb_level == 0 || wb_level == 1 || wb_level == 2);
>rtx ind;
> 
>/* Reject eliminable registers.  */
> @@ -13256,16 +13257,18 @@ arm_coproc_mem_operand (rtx op, bool wb)
> 
>

[PATCH v2][GCC] arm: Enable no-writeback vldr.16/vstr.16.

2020-07-29 Thread Joe Ramsay 
Hi,

There was previously no way to specify that a register operand cannot
have any writeback modifiers, and as a result the argument to vldr.16
and vstr.16 could be erroneously output with post-increment. This
change adds a constraint which forbids all writeback, and
selects it in the relevant case for vldr.16 and vstr.16

Bootstrapped on arm-linux, gcc and CMSIS-DSP testsuites are clean.
Is this patch OK for trunk? If yes, please commit on my behalf as I don't
have commit rights.

Thanks,
Joe

gcc/ChangeLog:

2020-05-20  Joe Ramsay  

* config/arm/arm-protos.h (arm_coproc_mem_operand_no_writeback): 
Declare prototype.
(arm_mve_mode_and_operands_type_check): Declare prototype.
* config/arm/arm.c (arm_coproc_mem_operand): Refactor to use 
_arm_coproc_mem_operand.
(arm_coproc_mem_operand_wb): New function to cover full, limited and no 
writeback.
(arm_coproc_mem_operand_no_writeback): New constraint for memory 
operand with no writeback.
(arm_print_operand): Extend 'E' specifier for memory operand that does 
not support
writeback.
(arm_mve_mode_and_operands_type_check): New constraint check for MVE 
memory operands.
* config/arm/constraints.md: Add Uj constraint for VFP vldr.16 and 
vstr.16.
* config/arm/vfp.md (*mov_load_vfp_hf16): New pattern for vldr.16.
(*mov_store_vfp_hf16): New pattern for vstr.16.
(*mov_vfp_16): Remove MVE moves.

gcc/testsuite/ChangeLog:

2020-05-20  Joe Ramsay  

* gcc.target/arm/mve/intrinsics/mve-vldstr16-no-writeback.c: New test.
---
 gcc/config/arm/arm-protos.h|  3 +
 gcc/config/arm/arm.c   | 74 ++
 gcc/config/arm/constraints.md  |  7 ++
 gcc/config/arm/vfp.md  | 26 +---
 .../arm/mve/intrinsics/mve-vldstr16-no-writeback.c | 17 +
 5 files changed, 105 insertions(+), 22 deletions(-)
 create mode 100644 
gcc/testsuite/gcc.target/arm/mve/intrinsics/mve-vldstr16-no-writeback.c

diff --git a/gcc/config/arm/arm-protos.h b/gcc/config/arm/arm-protos.h
index 33d162c..e811da4 100644
--- a/gcc/config/arm/arm-protos.h
+++ b/gcc/config/arm/arm-protos.h
@@ -115,8 +115,11 @@ extern enum reg_class coproc_secondary_reload_class 
(machine_mode, rtx,
 extern bool arm_tls_referenced_p (rtx);
 
 extern int arm_coproc_mem_operand (rtx, bool);
+extern int arm_coproc_mem_operand_no_writeback (rtx);
+extern int arm_coproc_mem_operand_wb (rtx, int);
 extern int neon_vector_mem_operand (rtx, int, bool);
 extern int mve_vector_mem_operand (machine_mode, rtx, bool);
+bool arm_mve_mode_and_operands_type_check (machine_mode, rtx, rtx);
 extern int neon_struct_mem_operand (rtx);
 
 extern rtx *neon_vcmla_lane_prepare_operands (rtx *);
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index 6b7ca82..63e052f 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -13217,13 +13217,14 @@ neon_element_bits (machine_mode mode)
 /* Predicates for `match_operand' and `match_operator'.  */
 
 /* Return TRUE if OP is a valid coprocessor memory address pattern.
-   WB is true if full writeback address modes are allowed and is false
+   WB level is 2 if full writeback address modes are allowed, 1
if limited writeback address modes (POST_INC and PRE_DEC) are
-   allowed.  */
+   allowed and 0 if no writeback at all is supported.  */
 
 int
-arm_coproc_mem_operand (rtx op, bool wb)
+arm_coproc_mem_operand_wb (rtx op, int wb_level)
 {
+  gcc_assert (wb_level == 0 || wb_level == 1 || wb_level == 2);
   rtx ind;
 
   /* Reject eliminable registers.  */
@@ -13256,16 +13257,18 @@ arm_coproc_mem_operand (rtx op, bool wb)
 
   /* Autoincremment addressing modes.  POST_INC and PRE_DEC are
  acceptable in any case (subject to verification by
- arm_address_register_rtx_p).  We need WB to be true to accept
+ arm_address_register_rtx_p).  We need full writeback to accept
+ PRE_INC and POST_DEC, and at least restricted writeback for
  PRE_INC and POST_DEC.  */
-  if (GET_CODE (ind) == POST_INC
-  || GET_CODE (ind) == PRE_DEC
-  || (wb
- && (GET_CODE (ind) == PRE_INC
- || GET_CODE (ind) == POST_DEC)))
+  if (wb_level > 0
+  && (GET_CODE (ind) == POST_INC
+ || GET_CODE (ind) == PRE_DEC
+ || (wb_level > 1
+ && (GET_CODE (ind) == PRE_INC
+ || GET_CODE (ind) == POST_DEC
 return arm_address_register_rtx_p (XEXP (ind, 0), 0);
 
-  if (wb
+  if (wb_level > 1
   && (GET_CODE (ind) == POST_MODIFY || GET_CODE (ind) == PRE_MODIFY)
   && arm_address_register_rtx_p (XEXP (ind, 0), 0)
   && GET_CODE (XEXP (ind, 1)) == PLUS
@@ -13287,6 +13290,25 @@ arm_coproc_mem_operand (rtx op, bool wb)
   return FALSE;
 }
 
+/* Return TRUE if OP is a valid coprocessor memory address pattern.
+   WB is true if full write

[committed] MAINTAINERS: Add myself for write after approval

2020-07-30 Thread Joe Ramsay 
2020-07-30  Joe Ramsay  

* MAINTAINERS (Write After Approval): Add myself.
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 300c10e..0b825c7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -563,6 +563,7 @@ Vladimir Prus   

 Yao Qi 
 Jerry Quinn
 Easwaran Raman 
+Joe Ramsay 
 Rolf Rasmussen 
 Fritz Reese
 Volker Reichelt

-- 
2.7.4

[PATCH][GCC-10 Backport] arm: Enable no-writeback vldr.16/vstr.16.

2020-08-05 Thread Joe Ramsay 
From: Joe Ramsay 

Hi,

There was previously no way to specify that a register operand cannot
have any writeback modifiers, and as a result the argument to vldr.16
and vstr.16 could be erroneously output with post-increment. This
change adds a constraint which forbids all writeback, and
selects it in the relevant case for vldr.16 and vstr.16

Bootstrapped on arm-none-eabi. Patch backports cleanly onto gcc-10
branch with no regressions. OK for gcc-10 branch?

Thanks,
Joe

gcc/ChangeLog:

2020-08-04  Joe Ramsay  

Backported from master
2020-05-20  Joe Ramsay  

* config/arm/arm-protos.h (arm_coproc_mem_operand_no_writeback):
Declare prototype.
(arm_mve_mode_and_operands_type_check): Declare prototype.
* config/arm/arm.c (arm_coproc_mem_operand): Refactor to use
_arm_coproc_mem_operand.
(arm_coproc_mem_operand_wb): New function to cover full, limited
and no writeback.
(arm_coproc_mem_operand_no_writeback): New constraint for memory
operand with no writeback.
(arm_print_operand): Extend 'E' specifier for memory operand
that does not support writeback.
(arm_mve_mode_and_operands_type_check): New constraint check for
MVE memory operands.
* config/arm/constraints.md: Add Uj constraint for VFP vldr.16
and vstr.16.
* config/arm/vfp.md (*mov_load_vfp_hf16): New pattern for
vldr.16.
(*mov_store_vfp_hf16): New pattern for vstr.16.
(*mov_vfp_16): Remove MVE moves.

gcc/testsuite/ChangeLog:

2020-08-04  Joe Ramsay  

Backported from master
2020-05-20  Joe Ramsay  

* gcc.target/arm/mve/intrinsics/mve-vldstr16-no-writeback.c: New test.
---
 gcc/config/arm/arm-protos.h|  3 +
 gcc/config/arm/arm.c   | 74 ++
 gcc/config/arm/constraints.md  |  7 ++
 gcc/config/arm/vfp.md  | 26 +---
 .../arm/mve/intrinsics/mve-vldstr16-no-writeback.c | 17 +
 5 files changed, 105 insertions(+), 22 deletions(-)
 create mode 100644 
gcc/testsuite/gcc.target/arm/mve/intrinsics/mve-vldstr16-no-writeback.c

diff --git a/gcc/config/arm/arm-protos.h b/gcc/config/arm/arm-protos.h
index 33d162c..e811da4 100644
--- a/gcc/config/arm/arm-protos.h
+++ b/gcc/config/arm/arm-protos.h
@@ -115,8 +115,11 @@ extern enum reg_class coproc_secondary_reload_class 
(machine_mode, rtx,
 extern bool arm_tls_referenced_p (rtx);
 
 extern int arm_coproc_mem_operand (rtx, bool);
+extern int arm_coproc_mem_operand_no_writeback (rtx);
+extern int arm_coproc_mem_operand_wb (rtx, int);
 extern int neon_vector_mem_operand (rtx, int, bool);
 extern int mve_vector_mem_operand (machine_mode, rtx, bool);
+bool arm_mve_mode_and_operands_type_check (machine_mode, rtx, rtx);
 extern int neon_struct_mem_operand (rtx);
 
 extern rtx *neon_vcmla_lane_prepare_operands (rtx *);
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index a8825ee..d8da167 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -13192,13 +13192,14 @@ neon_element_bits (machine_mode mode)
 /* Predicates for `match_operand' and `match_operator'.  */
 
 /* Return TRUE if OP is a valid coprocessor memory address pattern.
-   WB is true if full writeback address modes are allowed and is false
+   WB level is 2 if full writeback address modes are allowed, 1
if limited writeback address modes (POST_INC and PRE_DEC) are
-   allowed.  */
+   allowed and 0 if no writeback at all is supported.  */
 
 int
-arm_coproc_mem_operand (rtx op, bool wb)
+arm_coproc_mem_operand_wb (rtx op, int wb_level)
 {
+  gcc_assert (wb_level == 0 || wb_level == 1 || wb_level == 2);
   rtx ind;
 
   /* Reject eliminable registers.  */
@@ -13231,16 +13232,18 @@ arm_coproc_mem_operand (rtx op, bool wb)
 
   /* Autoincremment addressing modes.  POST_INC and PRE_DEC are
  acceptable in any case (subject to verification by
- arm_address_register_rtx_p).  We need WB to be true to accept
+ arm_address_register_rtx_p).  We need full writeback to accept
+ PRE_INC and POST_DEC, and at least restricted writeback for
  PRE_INC and POST_DEC.  */
-  if (GET_CODE (ind) == POST_INC
-  || GET_CODE (ind) == PRE_DEC
-  || (wb
- && (GET_CODE (ind) == PRE_INC
- || GET_CODE (ind) == POST_DEC)))
+  if (wb_level > 0
+  && (GET_CODE (ind) == POST_INC
+ || GET_CODE (ind) == PRE_DEC
+ || (wb_level > 1
+ && (GET_CODE (ind) == PRE_INC
+ || GET_CODE (ind) == POST_DEC
 return arm_address_register_rtx_p (XEXP (ind, 0), 0);
 
-  if (wb
+  if (wb_level > 1
   && (GET_CODE (ind) == POST_MODIFY || GET_CODE (ind) == PRE_MODIFY)
   && arm_address_register_rtx_p (XEXP (ind, 0), 0)
   && GET_CODE (XEXP (ind, 1)) == PLUS
@@ -13262,6 +13265,25 @@ arm_coproc_m

[PATCH] aarch64: add support for unpacked EOR, ORR and AND

2020-05-27 Thread Joe Ramsay 
Hi!

This patch improves code generation for EOR, ORR and AND on unpacked vectors 
with SVE. The following function:
void f (unsigned int *x, unsigned short *y, unsigned short *z) {
  for (int i = 0; i < 7; ++i)
x[i] = (unsigned short) (y[i] & z[i]);
}

previously compiled to
ptrue   p1.d, vl3
ld1hz0.d, p1/z, [x1, #1, mul vl]
ptrue   p0.b, vl32
st1hz0.d, p0, [sp, #1, mul vl]
ld1hz0.d, p1/z, [x2, #1, mul vl]
st1hz0.d, p0, [sp]
ldr x3, [x2]
ldp x4, x2, [sp]
ldr x1, [x1]
and x1, x3, x1
and x2, x2, x4
str x2, [sp]
ld1hz0.d, p0/z, [sp]
str x1, [sp]
uxthz0.s, p0/m, z0.s
st1wz0.d, p1, [x0, #1, mul vl]
ld1hz0.d, p0/z, [sp]
uxthz0.s, p0/m, z0.s
st1wz0.d, p0, [x0]
add sp, sp, 16
ret

and now compiles to:

ptrue   p0.s, vl7

ptrue   p1.b, vl32

ld1hz1.s, p0/z, [x1]

ld1hz0.s, p0/z, [x2]

add z0.h, z0.h, z1.h

uxthz0.s, p1/m, z0.s

st1wz0.s, p0, [x0]

ret



Tested on aarch64-linux-gnu and x86_64-linux-gnu hosts.

Thanks,
Joe


2020-05-20  Joe Ramsay  



* config/aarch64/aarch64-sve.md (3): 
Add support for unpacked EOR, ORR, AND.



gcc/testsuite/ChangeLog



2020-05-20  Joe Ramsay  



* gcc.target/aarch64/sve/logical_unpacked_and_1.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_and_2.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_and_3.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_and_4.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_and_5.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_and_6.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_and_7.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_eor_1.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_eor_2.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_eor_3.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_eor_4.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_eor_5.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_eor_6.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_eor_7.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_orr_1.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_orr_2.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_orr_3.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_orr_4.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_orr_5.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_orr_6.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_orr_7.c: New test.
---

diff --git a/gcc/config/aarch64/aarch64-sve.md 
b/gcc/config/aarch64/aarch64-sve.md
index f7a0893..8f0944c 100644
--- a/gcc/config/aarch64/aarch64-sve.md
+++ b/gcc/config/aarch64/aarch64-sve.md
@@ -4211,10 +4211,10 @@
 ;; Unpredicated integer binary logical operations.
(define_insn "3"
-  [(set (match_operand:SVE_FULL_I 0 "register_operand" "=w, ?w, w")
-   (LOGICAL:SVE_FULL_I
- (match_operand:SVE_FULL_I 1 "register_operand" "%0, w, w")
- (match_operand:SVE_FULL_I 2 "aarch64_sve_logical_operand" 
"vsl, vsl, w")))]
+  [(set (match_operand:SVE_I 0 "register_operand" "=w, ?w, w")
+  (LOGICAL:SVE_I
+(match_operand:SVE_I 1 "register_operand" "%0, w, w")
+(match_operand:SVE_I 2 "aarch64_sve_logical_operand" "vsl, 
vsl, w")))]
   "TARGET_SVE"
   "@
\t%0., %0., #%C2
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_1.c 
b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_1.c
new file mode 100644
index 000..7840355
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_and_1.c
@@ -0,0 +1,16 @@
+/* { dg-options "-O3 -msve-vector-bits=256" } */
+
+#include 
+
+void
+f (uint32_t *restrict dst, uint16_t *restrict src1, uint8_t *restrict src2)
+{
+  for (int i = 0; i < 7; ++i)
+dst[i] = (uint16_t) (src1[i] & src2[i]);
+}
+
+/* { dg-final { scan-assembler-times {\tld1h\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tld1b\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tand\tz[0-9]+\.d, z[0-9]+\.d, 
z[0-9]+\.d\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tuxth\tz[0-9]+\.s,} 1 } } */
+/* { dg-final { scan-assembler-times {\tst1w\tz[0-9]+\.s,} 1 } } */
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
n

[PATCH]: aarch64: add support for unpacked EOR, ORR and AND

2020-05-28 Thread Joe Ramsay 


From: Joe Ramsay 
Date: Thursday, 28 May 2020 at 16:19
To: Gcc-patches 
Subject: [PATCH]: aarch64: add support for unpacked EOR, ORR and AND

Hi!

This patch improves code generation for EOR, ORR and AND on unpacked vectors 
with SVE. The following function:
void f (unsigned int *x, unsigned short *y, unsigned short *z) {
  for (int i = 0; i < 7; ++i)
x[i] = (unsigned short) (y[i] & z[i]);
}

previously compiled to
ptrue   p1.d, vl3
ld1hz0.d, p1/z, [x1, #1, mul vl]
ptrue   p0.b, vl32
st1hz0.d, p0, [sp, #1, mul vl]
ld1hz0.d, p1/z, [x2, #1, mul vl]
st1hz0.d, p0, [sp]
ldr x3, [x2]
ldp x4, x2, [sp]
ldr x1, [x1]
and x1, x3, x1
and x2, x2, x4
str x2, [sp]
ld1hz0.d, p0/z, [sp]
str x1, [sp]
uxthz0.s, p0/m, z0.s
st1wz0.d, p1, [x0, #1, mul vl]
ld1hz0.d, p0/z, [sp]
uxthz0.s, p0/m, z0.s
st1wz0.d, p0, [x0]
add sp, sp, 16
ret

and now compiles to:
ptrue   p0.s, vl7
ptrue   p1.b, vl32
ld1hz1.s, p0/z, [x1]
ld1hz0.s, p0/z, [x2]
add z0.h, z0.h, z1.h
uxthz0.s, p1/m, z0.s
st1wz0.s, p0, [x0]
ret

Tested on aarch64-linux-gnu and x86_64-linux-gnu hosts.

Thanks,
Joe



2020-05-20  Joe Ramsay  



* config/aarch64/aarch64-sve.md (3): 
Add support for unpacked EOR, ORR, AND.



gcc/testsuite/ChangeLog



2020-05-20  Joe Ramsay  



* gcc.target/aarch64/sve/load_const_offset_2.c: Force using packed 
vectors.

* gcc.target/aarch64/sve/logical_unpacked_and_1.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_and_2.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_and_3.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_and_4.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_and_5.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_and_6.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_and_7.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_eor_1.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_eor_2.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_eor_3.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_eor_4.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_eor_5.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_eor_6.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_eor_7.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_orr_1.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_orr_2.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_orr_3.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_orr_4.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_orr_5.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_orr_6.c: New test.

* gcc.target/aarch64/sve/logical_unpacked_orr_7.c: New test.

* gcc.target/aarch64/sve/scatter_store_6.c: Force using packed vectors.

* gcc.target/aarch64/sve/scatter_store_7.c: Force using packed vectors.

* gcc.target/aarch64/sve/strided_load_3.c: Force using packed vectors.

* gcc.target/aarch64/sve/strided_store_3.c: Force using packed vectors.

* gcc.target/aarch64/sve/unpack_signed_1.c: Force using packed vectors.




0001-Support-AND-ORR-EOR-on-unpacked-vectors.patch
Description: 0001-Support-AND-ORR-EOR-on-unpacked-vectors.patch

[PATCH] AArch64+SVE: Add support for unpacked unary ops and BIC

2020-06-08 Thread Joe Ramsay 
Hi!

MD patterns extended for unary ops ABS, CLS, CLZ, CNT, NEG and NOT
to support unpacked vectors. Also extended patterns for BIC to
support unpacked vectors where input elements are of the same width.

Tested on x86_64-linux and aarch64-linux hosts.

Thanks,
Joe

gcc/ChangeLog:

2020-05-27  Joe Ramsay  

* config/aarch64/aarch64-sve.md (2): Add support for 
unpacked vectors.
* config/aarch64/aarch64-sve.md (@aarch64_pred_): Add 
support for unpacked vectors.
* config/aarch64/aarch64-sve.md (@cond_): Add support for 
unpacked vectors.
* config/aarch64/aarch64-sve.md (@aarch64_bic): Enable unpacked 
BIC.
* config/aarch64/aarch64-sve-md (*bic3): Enable unpacked BIC.

gcc/testsuite/ChangeLog:

2020-05-27  Joe Ramsay  

* gcc.target/aarch64/sve/logical_unpacked_abs.c: New test.
* gcc.target/aarch64/sve/logical_unpacked_bic_1.c: New test.
* gcc.target/aarch64/sve/logical_unpacked_bic_2.c: New test.
* gcc.target/aarch64/sve/logical_unpacked_bic_3.c: New test.
* gcc.target/aarch64/sve/logical_unpacked_bic_4.c: New test.
* gcc.target/aarch64/sve/logical_unpacked_neg.c: New test.
* gcc.target/aarch64/sve/logical_unpacked_not.c: New test.
---
gcc/config/aarch64/aarch64-sve.md  | 48 +++---
.../gcc.target/aarch64/sve/logical_unpacked_abs.c  | 16 
.../aarch64/sve/logical_unpacked_bic_1.c   | 15 +++
.../aarch64/sve/logical_unpacked_bic_2.c   | 15 +++
.../aarch64/sve/logical_unpacked_bic_3.c   | 15 +++
.../aarch64/sve/logical_unpacked_bic_4.c   | 15 +++
.../gcc.target/aarch64/sve/logical_unpacked_neg.c  | 16 
.../gcc.target/aarch64/sve/logical_unpacked_not.c  | 16 
8 files changed, 132 insertions(+), 24 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_abs.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_1.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_2.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_3.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_bic_4.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_neg.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/logical_unpacked_not.c

diff --git a/gcc/config/aarch64/aarch64-sve.md 
b/gcc/config/aarch64/aarch64-sve.md
index 8f0944c..f7100a2 100644
--- a/gcc/config/aarch64/aarch64-sve.md
+++ b/gcc/config/aarch64/aarch64-sve.md
@@ -2822,11 +2822,11 @@

;; Unpredicated integer unary arithmetic.
(define_expand "2"
-  [(set (match_operand:SVE_FULL_I 0 "register_operand")
-   (unspec:SVE_FULL_I
+  [(set (match_operand:SVE_I 0 "register_operand")
+  (unspec:SVE_I
  [(match_dup 2)
-  (SVE_INT_UNARY:SVE_FULL_I
-(match_operand:SVE_FULL_I 1 "register_operand"))]
+ (SVE_INT_UNARY:SVE_I
+   (match_operand:SVE_I 1 "register_operand"))]
  UNSPEC_PRED_X))]
   "TARGET_SVE"
   {
@@ -2836,11 +2836,11 @@

;; Integer unary arithmetic predicated with a PTRUE.
(define_insn "@aarch64_pred_"
-  [(set (match_operand:SVE_FULL_I 0 "register_operand" "=w")
-   (unspec:SVE_FULL_I
+  [(set (match_operand:SVE_I 0 "register_operand" "=w")
+  (unspec:SVE_I
  [(match_operand: 1 "register_operand" "Upl")
-  (SVE_INT_UNARY:SVE_FULL_I
-(match_operand:SVE_FULL_I 2 "register_operand" "w"))]
+ (SVE_INT_UNARY:SVE_I
+   (match_operand:SVE_I 2 "register_operand" "w"))]
  UNSPEC_PRED_X))]
   "TARGET_SVE"
   "\t%0., %1/m, %2."
@@ -2848,12 +2848,12 @@

;; Predicated integer unary arithmetic with merging.
(define_expand "@cond_"
-  [(set (match_operand:SVE_FULL_I 0 "register_operand")
-   (unspec:SVE_FULL_I
+  [(set (match_operand:SVE_I 0 "register_operand")
+  (unspec:SVE_I
  [(match_operand: 1 "register_operand")
-  (SVE_INT_UNARY:SVE_FULL_I
-(match_operand:SVE_FULL_I 2 "register_operand"))
- (match_operand:SVE_FULL_I 3 "aarch64_simd_reg_or_zero")]
+ (SVE_INT_UNARY:SVE_I
+   (match_operand:SVE_I 2 "register_operand"))
+ (match_operand:SVE_I 3 "aarch64_simd_reg_or_zero")]
  UNSPEC_SEL))]
   "TARGET_SVE"
)
@@ -4234,13 +4234,13 @@

;; Unpredicated BIC.
(define_expand "@aarch64_bic"
-  [(set (match_operand:SVE_FULL_I 0 "register_operand&quo