RE: [PATCH 23/35] arm: improve tests for viwdupq*

Kyrylo Tkachov via Gcc-patches Tue, 22 Nov 2022 08:54:56 -0800

> -----Original Message-----
> From: Andrea Corallo <andrea.cora...@arm.com>
> Sent: Thursday, November 17, 2022 4:38 PM
> To: gcc-patches@gcc.gnu.org
> Cc: Kyrylo Tkachov <kyrylo.tkac...@arm.com>; Richard Earnshaw
> <richard.earns...@arm.com>; Andrea Corallo <andrea.cora...@arm.com>
> Subject: [PATCH 23/35] arm: improve tests for viwdupq*
> 
> gcc/testsuite/ChangeLog:
> 
>       * gcc.target/arm/mve/intrinsics/viwdupq_m_n_u16.c: Improve tests.
>       * gcc.target/arm/mve/intrinsics/viwdupq_m_n_u32.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_m_n_u8.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u16.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u32.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u8.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_n_u16.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_n_u32.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_n_u8.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_wb_u16.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_wb_u32.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_wb_u8.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_x_n_u16.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_x_n_u32.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_x_n_u8.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u16.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u32.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u8.c: Likewise.

Ok.
Thanks,
Kyrill

> ---
>  .../arm/mve/intrinsics/viwdupq_m_n_u16.c      | 46 ++++++++++++++---
>  .../arm/mve/intrinsics/viwdupq_m_n_u32.c      | 46 ++++++++++++++---
>  .../arm/mve/intrinsics/viwdupq_m_n_u8.c       | 46 ++++++++++++++---
>  .../arm/mve/intrinsics/viwdupq_m_wb_u16.c     | 46 ++++++++++++++---
>  .../arm/mve/intrinsics/viwdupq_m_wb_u32.c     | 46 ++++++++++++++---
>  .../arm/mve/intrinsics/viwdupq_m_wb_u8.c      | 46 ++++++++++++++---
>  .../arm/mve/intrinsics/viwdupq_n_u16.c        | 32 ++++++++++--
>  .../arm/mve/intrinsics/viwdupq_n_u32.c        | 32 ++++++++++--
>  .../arm/mve/intrinsics/viwdupq_n_u8.c         | 28 ++++++++++-
>  .../arm/mve/intrinsics/viwdupq_wb_u16.c       | 36 ++++++++++---
>  .../arm/mve/intrinsics/viwdupq_wb_u32.c       | 36 ++++++++++---
>  .../arm/mve/intrinsics/viwdupq_wb_u8.c        | 36 ++++++++++---
>  .../arm/mve/intrinsics/viwdupq_x_n_u16.c      | 46 ++++++++++++++---
>  .../arm/mve/intrinsics/viwdupq_x_n_u32.c      | 46 ++++++++++++++---
>  .../arm/mve/intrinsics/viwdupq_x_n_u8.c       | 46 ++++++++++++++---
>  .../arm/mve/intrinsics/viwdupq_x_wb_u16.c     | 50 ++++++++++++++++---
>  .../arm/mve/intrinsics/viwdupq_x_wb_u32.c     | 50 ++++++++++++++++---
>  .../arm/mve/intrinsics/viwdupq_x_wb_u8.c      | 50 ++++++++++++++++---
>  18 files changed, 658 insertions(+), 106 deletions(-)
> 
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_n_u16.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_n_u16.c
> index 0f999cc672b..67a2465f435 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_n_u16.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_n_u16.c
> @@ -1,23 +1,57 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u16     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint16x8_t
>  foo (uint16x8_t inactive, uint32_t a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_m_n_u16 (inactive, a, b, 2, p);
> +  return viwdupq_m_n_u16 (inactive, a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u16"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u16     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint16x8_t
>  foo1 (uint16x8_t inactive, uint32_t a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_m (inactive, a, b, 2, p);
> +  return viwdupq_m (inactive, a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u16"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u16     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint16x8_t
> +foo2 (uint16x8_t inactive, mve_pred16_t p)
> +{
> +  return viwdupq_m (inactive, 1, 1, 1, p);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_n_u32.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_n_u32.c
> index f79c91eaf4c..9fc2518acc5 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_n_u32.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_n_u32.c
> @@ -1,23 +1,57 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u32     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint32x4_t
>  foo (uint32x4_t inactive, uint32_t a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_m_n_u32 (inactive, a, b, 4, p);
> +  return viwdupq_m_n_u32 (inactive, a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u32"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u32     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint32x4_t
>  foo1 (uint32x4_t inactive, uint32_t a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_m (inactive, a, b, 4, p);
> +  return viwdupq_m (inactive, a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u32"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u32     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint32x4_t
> +foo2 (uint32x4_t inactive, mve_pred16_t p)
> +{
> +  return viwdupq_m (inactive, 1, 1, 1, p);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_n_u8.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_n_u8.c
> index c0fee9fa752..39f4071bfa1 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_n_u8.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_n_u8.c
> @@ -1,23 +1,57 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u8      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint8x16_t
>  foo (uint8x16_t inactive, uint32_t a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_m_n_u8 (inactive, a, b, 8, p);
> +  return viwdupq_m_n_u8 (inactive, a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u8"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u8      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint8x16_t
>  foo1 (uint8x16_t inactive, uint32_t a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_m (inactive, a, b, 8, p);
> +  return viwdupq_m (inactive, a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u8"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u8      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint8x16_t
> +foo2 (uint8x16_t inactive, mve_pred16_t p)
> +{
> +  return viwdupq_m (inactive, 1, 1, 1, p);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git
> a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u16.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u16.c
> index 468ba179f62..8bb680e0d77 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u16.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u16.c
> @@ -1,23 +1,57 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u16     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint16x8_t
>  foo (uint16x8_t inactive, uint32_t *a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_m_wb_u16 (inactive, a, b, 2, p);
> +  return viwdupq_m_wb_u16 (inactive, a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u16"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u16     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint16x8_t
>  foo1 (uint16x8_t inactive, uint32_t *a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_m (inactive, a, b, 2, p);
> +  return viwdupq_m (inactive, a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u16"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u16     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint16x8_t
> +foo2 (uint16x8_t inactive, mve_pred16_t p)
> +{
> +  return viwdupq_m (inactive, 1, 1, 1, p);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git
> a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u32.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u32.c
> index e9190302717..2dc8d5f3442 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u32.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u32.c
> @@ -1,23 +1,57 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u32     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint32x4_t
>  foo (uint32x4_t inactive, uint32_t *a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_m_wb_u32 (inactive, a, b, 4, p);
> +  return viwdupq_m_wb_u32 (inactive, a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u32"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u32     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint32x4_t
>  foo1 (uint32x4_t inactive, uint32_t *a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_m (inactive, a, b, 4, p);
> +  return viwdupq_m (inactive, a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u32"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u32     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint32x4_t
> +foo2 (uint32x4_t inactive, mve_pred16_t p)
> +{
> +  return viwdupq_m (inactive, 1, 1, 1, p);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u8.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u8.c
> index 309ce95a333..ff3a5f520e8 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u8.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_m_wb_u8.c
> @@ -1,23 +1,57 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u8      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint8x16_t
>  foo (uint8x16_t inactive, uint32_t *a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_m_wb_u8 (inactive, a, b, 8, p);
> +  return viwdupq_m_wb_u8 (inactive, a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u8"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u8      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint8x16_t
>  foo1 (uint8x16_t inactive, uint32_t *a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_m (inactive, a, b, 8, p);
> +  return viwdupq_m (inactive, a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u8"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u8      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint8x16_t
> +foo2 (uint8x16_t inactive, mve_pred16_t p)
> +{
> +  return viwdupq_m (inactive, 1, 1, 1, p);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_n_u16.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_n_u16.c
> index 599d9078464..5f37290759a 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_n_u16.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_n_u16.c
> @@ -1,21 +1,45 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   viwdup.u16      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint16x8_t
>  foo (uint32_t a, uint32_t b)
>  {
> -  return viwdupq_n_u16 (a, b, 2);
> +  return viwdupq_n_u16 (a, b, 1);
>  }
> 
> -/* { dg-final { scan-assembler "viwdup.u16"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   viwdup.u16      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint16x8_t
>  foo1 (uint32_t a, uint32_t b)
>  {
> -  return viwdupq_u16 (a, b, 2);
> +  return viwdupq_u16 (a, b, 1);
>  }
> 
> -/* { dg-final { scan-assembler "viwdup.u16"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   viwdup.u16      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint16x8_t
> +foo2 ()
> +{
> +  return viwdupq_u16 (1, 1, 1);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_n_u32.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_n_u32.c
> index 7c2af74b3f0..de93f8a7ec4 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_n_u32.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_n_u32.c
> @@ -1,21 +1,45 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   viwdup.u32      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint32x4_t
>  foo (uint32_t a, uint32_t b)
>  {
> -  return viwdupq_n_u32 (a, b, 4);
> +  return viwdupq_n_u32 (a, b, 1);
>  }
> 
> -/* { dg-final { scan-assembler "viwdup.u32"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   viwdup.u32      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint32x4_t
>  foo1 (uint32_t a, uint32_t b)
>  {
> -  return viwdupq_u32 (a, b, 4);
> +  return viwdupq_u32 (a, b, 1);
>  }
> 
> -/* { dg-final { scan-assembler "viwdup.u32"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   viwdup.u32      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint32x4_t
> +foo2 ()
> +{
> +  return viwdupq_u32 (1, 1, 1);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_n_u8.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_n_u8.c
> index 4ff60791f3b..089025c3401 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_n_u8.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_n_u8.c
> @@ -1,21 +1,45 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   viwdup.u8       q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint8x16_t
>  foo (uint32_t a, uint32_t b)
>  {
>    return viwdupq_n_u8 (a, b, 1);
>  }
> 
> -/* { dg-final { scan-assembler "viwdup.u8"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   viwdup.u8       q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint8x16_t
>  foo1 (uint32_t a, uint32_t b)
>  {
>    return viwdupq_u8 (a, b, 1);
>  }
> 
> -/* { dg-final { scan-assembler "viwdup.u8"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   viwdup.u8       q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint8x16_t
> +foo2 ()
> +{
> +  return viwdupq_u8 (1, 1, 1);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_wb_u16.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_wb_u16.c
> index 1e5ce88dcca..fc3e9c6fac4 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_wb_u16.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_wb_u16.c
> @@ -1,21 +1,45 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   viwdup.u16      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint16x8_t
> -foo (uint32_t * a, uint32_t b)
> +foo (uint32_t *a, uint32_t b)
>  {
> -  return viwdupq_wb_u16 (a, b, 4);
> +  return viwdupq_wb_u16 (a, b, 1);
>  }
> 
> -/* { dg-final { scan-assembler "viwdup.u16"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   viwdup.u16      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint16x8_t
> -foo1 (uint32_t * a, uint32_t b)
> +foo1 (uint32_t *a, uint32_t b)
>  {
> -  return viwdupq_u16 (a, b, 4);
> +  return viwdupq_u16 (a, b, 1);
>  }
> 
> -/* { dg-final { scan-assembler "viwdup.u16"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   viwdup.u16      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint16x8_t
> +foo2 ()
> +{
> +  return viwdupq_u16 (1, 1, 1);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_wb_u32.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_wb_u32.c
> index 0c076f7b751..4c098dd8f02 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_wb_u32.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_wb_u32.c
> @@ -1,21 +1,45 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   viwdup.u32      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint32x4_t
> -foo (uint32_t * a, uint32_t b)
> +foo (uint32_t *a, uint32_t b)
>  {
> -  return viwdupq_wb_u32 (a, b, 8);
> +  return viwdupq_wb_u32 (a, b, 1);
>  }
> 
> -/* { dg-final { scan-assembler "viwdup.u32"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   viwdup.u32      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint32x4_t
> -foo1 (uint32_t * a, uint32_t b)
> +foo1 (uint32_t *a, uint32_t b)
>  {
> -  return viwdupq_u32 (a, b, 8);
> +  return viwdupq_u32 (a, b, 1);
>  }
> 
> -/* { dg-final { scan-assembler "viwdup.u32"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   viwdup.u32      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint32x4_t
> +foo2 ()
> +{
> +  return viwdupq_u32 (1, 1, 1);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_wb_u8.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_wb_u8.c
> index 9e5118ba2b6..44cb53fe344 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_wb_u8.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_wb_u8.c
> @@ -1,21 +1,45 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   viwdup.u8       q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint8x16_t
> -foo (uint32_t * a, uint32_t b)
> +foo (uint32_t *a, uint32_t b)
>  {
> -  return viwdupq_wb_u8 (a, b, 2);
> +  return viwdupq_wb_u8 (a, b, 1);
>  }
> 
> -/* { dg-final { scan-assembler "viwdup.u8"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   viwdup.u8       q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint8x16_t
> -foo1 (uint32_t * a, uint32_t b)
> +foo1 (uint32_t *a, uint32_t b)
>  {
> -  return viwdupq_u8 (a, b, 2);
> +  return viwdupq_u8 (a, b, 1);
>  }
> 
> -/* { dg-final { scan-assembler "viwdup.u8"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   viwdup.u8       q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint8x16_t
> +foo2 ()
> +{
> +  return viwdupq_u8 (1, 1, 1);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_n_u16.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_n_u16.c
> index fdaf6be282d..2242877881f 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_n_u16.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_n_u16.c
> @@ -1,23 +1,57 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u16     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint16x8_t
>  foo (uint32_t a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_x_n_u16 (a, b, 2, p);
> +  return viwdupq_x_n_u16 (a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u16"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u16     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint16x8_t
>  foo1 (uint32_t a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_x_u16 (a, b, 2, p);
> +  return viwdupq_x_u16 (a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u16"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u16     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint16x8_t
> +foo2 (mve_pred16_t p)
> +{
> +  return viwdupq_x_u16 (1, 1, 1, p);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_n_u32.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_n_u32.c
> index affc6162015..4b2b650e21a 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_n_u32.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_n_u32.c
> @@ -1,23 +1,57 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u32     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint32x4_t
>  foo (uint32_t a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_x_n_u32 (a, b, 4, p);
> +  return viwdupq_x_n_u32 (a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u32"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u32     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint32x4_t
>  foo1 (uint32_t a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_x_u32 (a, b, 4, p);
> +  return viwdupq_x_u32 (a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u32"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u32     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint32x4_t
> +foo2 (mve_pred16_t p)
> +{
> +  return viwdupq_x_u32 (1, 1, 1, p);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_n_u8.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_n_u8.c
> index 8137c623c2a..873952b6c2e 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_n_u8.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_n_u8.c
> @@ -1,23 +1,57 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u8      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint8x16_t
>  foo (uint32_t a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_x_n_u8 (a, b, 8, p);
> +  return viwdupq_x_n_u8 (a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u8"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u8      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint8x16_t
>  foo1 (uint32_t a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_x_u8 (a, b, 8, p);
> +  return viwdupq_x_u8 (a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u8"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u8      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint8x16_t
> +foo2 (mve_pred16_t p)
> +{
> +  return viwdupq_x_u8 (1, 1, 1, p);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u16.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u16.c
> index d7aa141f384..b6c94797380 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u16.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u16.c
> @@ -1,23 +1,57 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u16     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint16x8_t
> -foo (uint32_t * a, uint32_t b, mve_pred16_t p)
> +foo (uint32_t *a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_x_wb_u16 (a, b, 8, p);
> +  return viwdupq_x_wb_u16 (a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u16"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u16     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint16x8_t
> -foo1 (uint32_t * a, uint32_t b, mve_pred16_t p)
> +foo1 (uint32_t *a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_x_u16 (a, b, 8, p);
> +  return viwdupq_x_u16 (a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u16"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u16     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint16x8_t
> +foo2 (mve_pred16_t p)
> +{
> +  return viwdupq_x_u16 (1, 1, 1, p);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u32.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u32.c
> index 7fe56963452..5fd84963d01 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u32.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u32.c
> @@ -1,23 +1,57 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u32     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint32x4_t
> -foo (uint32_t * a, uint32_t b, mve_pred16_t p)
> +foo (uint32_t *a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_x_wb_u32 (a, b, 2, p);
> +  return viwdupq_x_wb_u32 (a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u32"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u32     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint32x4_t
> -foo1 (uint32_t * a, uint32_t b, mve_pred16_t p)
> +foo1 (uint32_t *a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_x_u32 (a, b, 2, p);
> +  return viwdupq_x_u32 (a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u32"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u32     q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint32x4_t
> +foo2 (mve_pred16_t p)
> +{
> +  return viwdupq_x_u32 (1, 1, 1, p);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u8.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u8.c
> index 8e3ecefdedb..abbb40fa8da 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u8.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/viwdupq_x_wb_u8.c
> @@ -1,23 +1,57 @@
>  /* { dg-require-effective-target arm_v8_1m_mve_ok } */
>  /* { dg-add-options arm_v8_1m_mve } */
>  /* { dg-additional-options "-O2" } */
> +/* { dg-final { check-function-bodies "**" "" } } */
> 
>  #include "arm_mve.h"
> 
> +/*
> +**foo:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u8      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint8x16_t
> -foo (uint32_t * a, uint32_t b, mve_pred16_t p)
> +foo (uint32_t *a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_x_wb_u8 (a, b, 4, p);
> +  return viwdupq_x_wb_u8 (a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u8"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u8      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
>  uint8x16_t
> -foo1 (uint32_t * a, uint32_t b, mve_pred16_t p)
> +foo1 (uint32_t *a, uint32_t b, mve_pred16_t p)
>  {
> -  return viwdupq_x_u8 (a, b, 4, p);
> +  return viwdupq_x_u8 (a, b, 1, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "viwdupt.u8"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   viwdupt.u8      q[0-9]+, (?:ip|fp|r[0-9]+), (?:ip|fp|r[0-9]+), 
> #[0-9]+(?:
>       @.*|)
> +**   ...
> +*/
> +uint8x16_t
> +foo2 (mve_pred16_t p)
> +{
> +  return viwdupq_x_u8 (1, 1, 1, p);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> --
> 2.25.1
RE: [PATCH 23/35] arm: improve tests for viwdupq*

Reply via email to
