RE: [PATCH 26/35] arm: improve tests for vmlasq*

[Kyrylo Tkachov via Gcc-patches]

> -----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 26/35] arm: improve tests for vmlasq*
> 
> gcc/testsuite/ChangeLog:
> 
>       * gcc.target/arm/mve/intrinsics/vmlasq_m_n_s16.c: Improve test.
>       * gcc.target/arm/mve/intrinsics/vmlasq_m_n_s32.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/vmlasq_m_n_s8.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/vmlasq_m_n_u16.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/vmlasq_m_n_u32.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/vmlasq_m_n_u8.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/vmlasq_n_s16.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/vmlasq_n_s32.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/vmlasq_n_s8.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/vmlasq_n_u16.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/vmlasq_n_u32.c: Likewise.
>       * gcc.target/arm/mve/intrinsics/vmlasq_n_u8.c: Likewise.

Ok.
Thanks,
Kyrill

> ---
>  .../arm/mve/intrinsics/vmlasq_m_n_s16.c       | 34 ++++++++++---
>  .../arm/mve/intrinsics/vmlasq_m_n_s32.c       | 34 ++++++++++---
>  .../arm/mve/intrinsics/vmlasq_m_n_s8.c        | 34 ++++++++++---
>  .../arm/mve/intrinsics/vmlasq_m_n_u16.c       | 50 ++++++++++++++++---
>  .../arm/mve/intrinsics/vmlasq_m_n_u32.c       | 50 ++++++++++++++++---
>  .../arm/mve/intrinsics/vmlasq_m_n_u8.c        | 50 ++++++++++++++++---
>  .../arm/mve/intrinsics/vmlasq_n_s16.c         | 24 ++++++---
>  .../arm/mve/intrinsics/vmlasq_n_s32.c         | 24 ++++++---
>  .../arm/mve/intrinsics/vmlasq_n_s8.c          | 24 ++++++---
>  .../arm/mve/intrinsics/vmlasq_n_u16.c         | 36 ++++++++++---
>  .../arm/mve/intrinsics/vmlasq_n_u32.c         | 36 ++++++++++---
>  .../arm/mve/intrinsics/vmlasq_n_u8.c          | 36 ++++++++++---
>  12 files changed, 348 insertions(+), 84 deletions(-)
> 
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_s16.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_s16.c
> index bf66e616ec7..af6e588adad 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_s16.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_s16.c
> @@ -1,23 +1,41 @@
>  /* { 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(?: @.*|)
> +**   ...
> +**   vmlast.s16      q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  int16x8_t
> -foo (int16x8_t a, int16x8_t b, int16_t c, mve_pred16_t p)
> +foo (int16x8_t m1, int16x8_t m2, int16_t add, mve_pred16_t p)
>  {
> -  return vmlasq_m_n_s16 (a, b, c, p);
> +  return vmlasq_m_n_s16 (m1, m2, add, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "vmlast.s16"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   vmlast.s16      q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  int16x8_t
> -foo1 (int16x8_t a, int16x8_t b, int16_t c, mve_pred16_t p)
> +foo1 (int16x8_t m1, int16x8_t m2, int16_t add, mve_pred16_t p)
>  {
> -  return vmlasq_m (a, b, c, p);
> +  return vmlasq_m (m1, m2, add, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "vmlast.s16"  }  } */
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_s32.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_s32.c
> index 53c21e2e5b6..9d0cc3076d9 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_s32.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_s32.c
> @@ -1,23 +1,41 @@
>  /* { 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(?: @.*|)
> +**   ...
> +**   vmlast.s32      q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  int32x4_t
> -foo (int32x4_t a, int32x4_t b, int32_t c, mve_pred16_t p)
> +foo (int32x4_t m1, int32x4_t m2, int32_t add, mve_pred16_t p)
>  {
> -  return vmlasq_m_n_s32 (a, b, c, p);
> +  return vmlasq_m_n_s32 (m1, m2, add, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "vmlast.s32"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   vmlast.s32      q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  int32x4_t
> -foo1 (int32x4_t a, int32x4_t b, int32_t c, mve_pred16_t p)
> +foo1 (int32x4_t m1, int32x4_t m2, int32_t add, mve_pred16_t p)
>  {
> -  return vmlasq_m (a, b, c, p);
> +  return vmlasq_m (m1, m2, add, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "vmlast.s32"  }  } */
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_s8.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_s8.c
> index ac08b15fdbe..772ad8b1e76 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_s8.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_s8.c
> @@ -1,23 +1,41 @@
>  /* { 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(?: @.*|)
> +**   ...
> +**   vmlast.s8       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  int8x16_t
> -foo (int8x16_t a, int8x16_t b, int8_t c, mve_pred16_t p)
> +foo (int8x16_t m1, int8x16_t m2, int8_t add, mve_pred16_t p)
>  {
> -  return vmlasq_m_n_s8 (a, b, c, p);
> +  return vmlasq_m_n_s8 (m1, m2, add, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "vmlast.s8"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   vmlast.s8       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  int8x16_t
> -foo1 (int8x16_t a, int8x16_t b, int8_t c, mve_pred16_t p)
> +foo1 (int8x16_t m1, int8x16_t m2, int8_t add, mve_pred16_t p)
>  {
> -  return vmlasq_m (a, b, c, p);
> +  return vmlasq_m (m1, m2, add, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "vmlast.s8"  }  } */
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_u16.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_u16.c
> index 99f1e28c7d5..b02dc64a31b 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_u16.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_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(?: @.*|)
> +**   ...
> +**   vmlast.u16      q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  uint16x8_t
> -foo (uint16x8_t a, uint16x8_t b, uint16_t c, mve_pred16_t p)
> +foo (uint16x8_t m1, uint16x8_t m2, uint16_t add, mve_pred16_t p)
>  {
> -  return vmlasq_m_n_u16 (a, b, c, p);
> +  return vmlasq_m_n_u16 (m1, m2, add, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "vmlast.u16"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   vmlast.u16      q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  uint16x8_t
> -foo1 (uint16x8_t a, uint16x8_t b, uint16_t c, mve_pred16_t p)
> +foo1 (uint16x8_t m1, uint16x8_t m2, uint16_t add, mve_pred16_t p)
>  {
> -  return vmlasq_m (a, b, c, p);
> +  return vmlasq_m (m1, m2, add, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "vmlast.u16"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   vmlast.u16      q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
> +uint16x8_t
> +foo2 (uint16x8_t m1, uint16x8_t m2, mve_pred16_t p)
> +{
> +  return vmlasq_m (m1, m2, 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/vmlasq_m_n_u32.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_u32.c
> index 8d8edca6024..0214cf2136e 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_u32.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_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(?: @.*|)
> +**   ...
> +**   vmlast.u32      q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  uint32x4_t
> -foo (uint32x4_t a, uint32x4_t b, uint32_t c, mve_pred16_t p)
> +foo (uint32x4_t m1, uint32x4_t m2, uint32_t add, mve_pred16_t p)
>  {
> -  return vmlasq_m_n_u32 (a, b, c, p);
> +  return vmlasq_m_n_u32 (m1, m2, add, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "vmlast.u32"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   vmlast.u32      q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  uint32x4_t
> -foo1 (uint32x4_t a, uint32x4_t b, uint32_t c, mve_pred16_t p)
> +foo1 (uint32x4_t m1, uint32x4_t m2, uint32_t add, mve_pred16_t p)
>  {
> -  return vmlasq_m (a, b, c, p);
> +  return vmlasq_m (m1, m2, add, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "vmlast.u32"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   vmlast.u32      q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
> +uint32x4_t
> +foo2 (uint32x4_t m1, uint32x4_t m2, mve_pred16_t p)
> +{
> +  return vmlasq_m (m1, m2, 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/vmlasq_m_n_u8.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_u8.c
> index e7f685bbcaa..c9824e332f7 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_m_n_u8.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_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(?: @.*|)
> +**   ...
> +**   vmlast.u8       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  uint8x16_t
> -foo (uint8x16_t a, uint8x16_t b, uint8_t c, mve_pred16_t p)
> +foo (uint8x16_t m1, uint8x16_t m2, uint8_t add, mve_pred16_t p)
>  {
> -  return vmlasq_m_n_u8 (a, b, c, p);
> +  return vmlasq_m_n_u8 (m1, m2, add, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "vmlast.u8"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   vmlast.u8       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  uint8x16_t
> -foo1 (uint8x16_t a, uint8x16_t b, uint8_t c, mve_pred16_t p)
> +foo1 (uint8x16_t m1, uint8x16_t m2, uint8_t add, mve_pred16_t p)
>  {
> -  return vmlasq_m (a, b, c, p);
> +  return vmlasq_m (m1, m2, add, p);
>  }
> 
> -/* { dg-final { scan-assembler "vpst" } } */
> -/* { dg-final { scan-assembler "vmlast.u8"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmsr    p0, (?:ip|fp|r[0-9]+)(?:        @.*|)
> +**   ...
> +**   vpst(?: @.*|)
> +**   ...
> +**   vmlast.u8       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
> +uint8x16_t
> +foo2 (uint8x16_t m1, uint8x16_t m2, mve_pred16_t p)
> +{
> +  return vmlasq_m (m1, m2, 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/vmlasq_n_s16.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_s16.c
> index 8bfe3c31096..6708a741790 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_s16.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_s16.c
> @@ -1,21 +1,33 @@
>  /* { 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:
> +**   ...
> +**   vmlas.s16       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  int16x8_t
> -foo (int16x8_t a, int16x8_t b, int16_t c)
> +foo (int16x8_t m1, int16x8_t m2, int16_t add)
>  {
> -  return vmlasq_n_s16 (a, b, c);
> +  return vmlasq_n_s16 (m1, m2, add);
>  }
> 
> -/* { dg-final { scan-assembler "vmlas.s16"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmlas.s16       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  int16x8_t
> -foo1 (int16x8_t a, int16x8_t b, int16_t c)
> +foo1 (int16x8_t m1, int16x8_t m2, int16_t add)
>  {
> -  return vmlasq (a, b, c);
> +  return vmlasq (m1, m2, add);
>  }
> 
> -/* { dg-final { scan-assembler "vmlas.s16"  }  } */
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_s32.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_s32.c
> index db06182abec..4e8bf32e016 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_s32.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_s32.c
> @@ -1,21 +1,33 @@
>  /* { 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:
> +**   ...
> +**   vmlas.s32       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  int32x4_t
> -foo (int32x4_t a, int32x4_t b, int32_t c)
> +foo (int32x4_t m1, int32x4_t m2, int32_t add)
>  {
> -  return vmlasq_n_s32 (a, b, c);
> +  return vmlasq_n_s32 (m1, m2, add);
>  }
> 
> -/* { dg-final { scan-assembler "vmlas.s32"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmlas.s32       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  int32x4_t
> -foo1 (int32x4_t a, int32x4_t b, int32_t c)
> +foo1 (int32x4_t m1, int32x4_t m2, int32_t add)
>  {
> -  return vmlasq (a, b, c);
> +  return vmlasq (m1, m2, add);
>  }
> 
> -/* { dg-final { scan-assembler "vmlas.s32"  }  } */
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_s8.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_s8.c
> index 3a151650ef4..1cb1a31459c 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_s8.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_s8.c
> @@ -1,21 +1,33 @@
>  /* { 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:
> +**   ...
> +**   vmlas.s8        q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  int8x16_t
> -foo (int8x16_t a, int8x16_t b, int8_t c)
> +foo (int8x16_t m1, int8x16_t m2, int8_t add)
>  {
> -  return vmlasq_n_s8 (a, b, c);
> +  return vmlasq_n_s8 (m1, m2, add);
>  }
> 
> -/* { dg-final { scan-assembler "vmlas.s8"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmlas.s8        q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  int8x16_t
> -foo1 (int8x16_t a, int8x16_t b, int8_t c)
> +foo1 (int8x16_t m1, int8x16_t m2, int8_t add)
>  {
> -  return vmlasq (a, b, c);
> +  return vmlasq (m1, m2, add);
>  }
> 
> -/* { dg-final { scan-assembler "vmlas.s8"  }  } */
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_u16.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_u16.c
> index b9444f2f6a3..e03c91ef298 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_u16.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_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:
> +**   ...
> +**   vmlas.u16       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  uint16x8_t
> -foo (uint16x8_t a, uint16x8_t b, uint16_t c)
> +foo (uint16x8_t m1, uint16x8_t m2, uint16_t add)
>  {
> -  return vmlasq_n_u16 (a, b, c);
> +  return vmlasq_n_u16 (m1, m2, add);
>  }
> 
> -/* { dg-final { scan-assembler "vmlas.u16"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmlas.u16       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  uint16x8_t
> -foo1 (uint16x8_t a, uint16x8_t b, uint16_t c)
> +foo1 (uint16x8_t m1, uint16x8_t m2, uint16_t add)
>  {
> -  return vmlasq (a, b, c);
> +  return vmlasq (m1, m2, add);
>  }
> 
> -/* { dg-final { scan-assembler "vmlas.u16"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmlas.u16       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
> +uint16x8_t
> +foo2 (uint16x8_t m1, uint16x8_t m2)
> +{
> +  return vmlasq (m1, m2, 1);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_u32.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_u32.c
> index 5708a0658a6..b80c3c7631f 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_u32.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_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:
> +**   ...
> +**   vmlas.u32       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  uint32x4_t
> -foo (uint32x4_t a, uint32x4_t b, uint32_t c)
> +foo (uint32x4_t m1, uint32x4_t m2, uint32_t add)
>  {
> -  return vmlasq_n_u32 (a, b, c);
> +  return vmlasq_n_u32 (m1, m2, add);
>  }
> 
> -/* { dg-final { scan-assembler "vmlas.u32"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmlas.u32       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  uint32x4_t
> -foo1 (uint32x4_t a, uint32x4_t b, uint32_t c)
> +foo1 (uint32x4_t m1, uint32x4_t m2, uint32_t add)
>  {
> -  return vmlasq (a, b, c);
> +  return vmlasq (m1, m2, add);
>  }
> 
> -/* { dg-final { scan-assembler "vmlas.u32"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmlas.u32       q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
> +uint32x4_t
> +foo2 (uint32x4_t m1, uint32x4_t m2)
> +{
> +  return vmlasq (m1, m2, 1);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_u8.c
> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_u8.c
> index d83940c7232..0f37550160e 100644
> --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_n_u8.c
> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vmlasq_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:
> +**   ...
> +**   vmlas.u8        q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  uint8x16_t
> -foo (uint8x16_t a, uint8x16_t b, uint8_t c)
> +foo (uint8x16_t m1, uint8x16_t m2, uint8_t add)
>  {
> -  return vmlasq_n_u8 (a, b, c);
> +  return vmlasq_n_u8 (m1, m2, add);
>  }
> 
> -/* { dg-final { scan-assembler "vmlas.u8"  }  } */
> 
> +/*
> +**foo1:
> +**   ...
> +**   vmlas.u8        q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
>  uint8x16_t
> -foo1 (uint8x16_t a, uint8x16_t b, uint8_t c)
> +foo1 (uint8x16_t m1, uint8x16_t m2, uint8_t add)
>  {
> -  return vmlasq (a, b, c);
> +  return vmlasq (m1, m2, add);
>  }
> 
> -/* { dg-final { scan-assembler "vmlas.u8"  }  } */
> +/*
> +**foo2:
> +**   ...
> +**   vmlas.u8        q[0-9]+, q[0-9]+, (?:ip|fp|r[0-9]+)(?:  @.*|)
> +**   ...
> +*/
> +uint8x16_t
> +foo2 (uint8x16_t m1, uint8x16_t m2)
> +{
> +  return vmlasq (m1, m2, 1);
> +}
> +
> +/* { dg-final { scan-assembler-not "__ARM_undef" } } */
> \ No newline at end of file
> --
> 2.25.1