> -----Original Message-----
> From: Christophe Lyon <[email protected]>
> Sent: Thursday, September 29, 2022 4:24 PM
> To: Kyrylo Tkachov <[email protected]>; [email protected]
> Cc: Andre Simoes Dias Vieira <[email protected]>
> Subject: Re: [PATCH] testsuite: [arm] Relax expected register names in MVE
> tests
> 
> 
> 
> On 9/29/22 17:01, Kyrylo Tkachov wrote:
> > Hi Christophe,
> >
> >> -----Original Message-----
> >> From: Christophe Lyon <[email protected]>
> >> Sent: Thursday, September 29, 2022 3:57 PM
> >> To: [email protected]
> >> Cc: Kyrylo Tkachov <[email protected]>; Andre Simoes Dias Vieira
> >> <[email protected]>; Christophe Lyon
> >> <[email protected]>
> >> Subject: [PATCH] testsuite: [arm] Relax expected register names in MVE
> tests
> >>
> >> These two tests have hardcoded q0 as destination/source of load/store
> >> instructions, but it is actually used only under
> >> -mfloat-abi=hard. When using -mfloat-abi=softfp, other registers
> >> (eg. q3) can be used to transfer function arguments from core
> >> registers to MVE registers, making the expected regexp fail.
> >>
> >> This small patch replaces q0 with q[0-7] to accept any 'q' register.
> >>
> >> OK for trunk?
> >>
> >> Thanks,
> >>
> >> Christophe
> >>
> >> gcc/testsuite/ChangeLog:
> >>
> >>    * gcc.target/arm/mve/mve_load_memory_modes.c: Update
> >> expected
> >>    registers.
> >>    * gcc.target/arm/mve/mve_store_memory_modes.c: Likewise.
> >> ---
> >>   .../arm/mve/mve_load_memory_modes.c           | 58 +++++++++----------
> >>   .../arm/mve/mve_store_memory_modes.c          | 58 +++++++++----------
> >>   2 files changed, 58 insertions(+), 58 deletions(-)
> >>
> >> diff --git a/gcc/testsuite/gcc.target/arm/mve/mve_load_memory_modes.c
> >> b/gcc/testsuite/gcc.target/arm/mve/mve_load_memory_modes.c
> >> index e35eb1108aa..fa05fdcefec 100644
> >> --- a/gcc/testsuite/gcc.target/arm/mve/mve_load_memory_modes.c
> >> +++ b/gcc/testsuite/gcc.target/arm/mve/mve_load_memory_modes.c
> >> @@ -7,7 +7,7 @@
> >>   /*
> >>   **off_load8_0:
> >>   **       ...
> >> -**        vldrb.8 q0, \[r0, #16\]
> >> +**        vldrb.8 q[0-7], \[r0, #16\]
> >>   **       ...
> >>   */
> >>   int8x16_t off_load8_0 (int8_t * a)
> >> @@ -18,7 +18,7 @@ int8x16_t off_load8_0 (int8_t * a)
> >>   /*
> >>   **off_load8_1:
> >>   **       ...
> >> -**        vldrb.u16       q0, \[r0, #1\]
> >> +**        vldrb.u16       q[0-7], \[r0, #1\]
> >>   **       ...
> >>   */
> >>   uint16x8_t off_load8_1 (uint8_t * a)
> >> @@ -29,7 +29,7 @@ uint16x8_t off_load8_1 (uint8_t * a)
> >>   /*
> >>   **off_load8_2:
> >>   **       ...
> >> -**        vldrb.s32       q0, \[r0, #127\]
> >> +**        vldrb.s32       q[0-7], \[r0, #127\]
> >>   **       ...
> >>   */
> >>   int32x4_t off_load8_2 (int8_t * a)
> >> @@ -40,7 +40,7 @@ int32x4_t off_load8_2 (int8_t * a)
> >>   /*
> >>   **off_load8_3:
> >>   **       ...
> >> -**        vldrb.8 q0, \[r0, #-127\]
> >> +**        vldrb.8 q[0-7], \[r0, #-127\]
> >>   **       ...
> >>   */
> >>   uint8x16_t off_load8_3 (uint8_t * a)
> >> @@ -51,7 +51,7 @@ uint8x16_t off_load8_3 (uint8_t * a)
> >>   /*
> >>   **not_off_load8_0:
> >>   **       ...
> >> -**        vldrb.8 q0, \[r[0-9]+\]
> >> +**        vldrb.8 q[0-7], \[r[0-7]+\]
> >>   **       ...
> >>   */
> >>   int8x16_t not_off_load8_0 (int8_t * a)
> >> @@ -62,7 +62,7 @@ int8x16_t not_off_load8_0 (int8_t * a)
> >>   /*
> >>   **off_loadfp16_0:
> >>   **       ...
> >> -**        vldrh.16        q0, \[r0, #-244\]
> >> +**        vldrh.16        q[0-7], \[r0, #-244\]
> >>   **       ...
> >>   */
> >>   float16x8_t off_loadfp16_0 (float16_t *a)
> >> @@ -73,7 +73,7 @@ float16x8_t off_loadfp16_0 (float16_t *a)
> >>   /*
> >>   **off_load16_0:
> >>   **       ...
> >> -**        vldrh.16        q0, \[r0, #-2\]
> >> +**        vldrh.16        q[0-7], \[r0, #-2\]
> >>   **       ...
> >>   */
> >>   uint16x8_t off_load16_0 (uint16_t * a)
> >> @@ -84,7 +84,7 @@ uint16x8_t off_load16_0 (uint16_t * a)
> >>   /*
> >>   **off_load16_1:
> >>   **       ...
> >> -**        vldrh.u32       q0, \[r0, #254\]
> >> +**        vldrh.u32       q[0-7], \[r0, #254\]
> >>   **       ...
> >>   */
> >>   uint32x4_t off_load16_1 (uint16_t * a)
> >> @@ -95,7 +95,7 @@ uint32x4_t off_load16_1 (uint16_t * a)
> >>   /*
> >>   **not_off_load16_0:
> >>   **       ...
> >> -**        vldrh.16        q0, \[r[0-9]+\]
> >> +**        vldrh.16        q[0-7], \[r[0-7]+\]
> >>   **       ...
> >>   */
> >>   int16x8_t not_off_load16_0 (int8_t * a)
> >> @@ -106,7 +106,7 @@ int16x8_t not_off_load16_0 (int8_t * a)
> >>   /*
> >>   **not_off_load16_1:
> >>   **       ...
> >> -**        vldrh.u32       q0, \[r[0-9]+\]
> >> +**        vldrh.u32       q[0-7], \[r[0-7]+\]
> >>   **       ...
> >>   */
> >>   uint32x4_t not_off_load16_1 (uint16_t * a)
> >> @@ -117,7 +117,7 @@ uint32x4_t not_off_load16_1 (uint16_t * a)
> >>   /*
> >>   **off_loadfp32_0:
> >>   **       ...
> >> -**        vldrw.32        q0, \[r0, #24\]
> >> +**        vldrw.32        q[0-7], \[r0, #24\]
> >>   **       ...
> >>   */
> >>   float32x4_t off_loadfp32_0 (float32_t *a)
> >> @@ -128,7 +128,7 @@ float32x4_t off_loadfp32_0 (float32_t *a)
> >>   /*
> >>   **off_load32_0:
> >>   **       ...
> >> -**        vldrw.32        q0, \[r0, #4\]
> >> +**        vldrw.32        q[0-7], \[r0, #4\]
> >>   **       ...
> >>   */
> >>   uint32x4_t off_load32_0 (uint32_t * a)
> >> @@ -139,7 +139,7 @@ uint32x4_t off_load32_0 (uint32_t * a)
> >>   /*
> >>   **off_load32_1:
> >>   **       ...
> >> -**        vldrw.32        q0, \[r0, #-508\]
> >> +**        vldrw.32        q[0-7], \[r0, #-508\]
> >>   **       ...
> >>   */
> >
> > These make sense....
> >
> >>   int32x4_t off_load32_1 (int32_t * a)
> >> @@ -149,7 +149,7 @@ int32x4_t off_load32_1 (int32_t * a)
> >>   /*
> >>   **pre_load8_0:
> >>   **       ...
> >> -**        vldrb.8 q[0-9]+, \[r0, #16\]!
> >> +**        vldrb.8 q[0-7]+, \[r0, #16\]!
> >>   **       ...
> >>   */
> >
> >
> > ... but what is the reason for these changes?
> 
> oops, good catch.
> I originally replaced all q0 with q[0-9], then realized q[0-7] was
> probably better/safer, looks like I also changed pre-existing 0-9 and
> didn't notice.
> 
> So since I have to re-submit this patch, what's the best choice?
> q[0-9] or q[0-7]?

I just remembered that MVE has only Q0-Q7 (unlike Neon) so q[0-7] would be 
correct here, without the '+'
Thanks,
Kyrill

> 
> Thanks,
> 
> Christophe
> 
> > Thanks,
> > Kyrill
> >
> >>   int8_t* pre_load8_0 (int8_t * a, int8x16_t *v)
> >> @@ -162,7 +162,7 @@ int8_t* pre_load8_0 (int8_t * a, int8x16_t *v)
> >>   /*
> >>   **pre_load8_1:
> >>   **       ...
> >> -**        vldrb.u16       q[0-9]+, \[r0, #4\]!
> >> +**        vldrb.u16       q[0-7]+, \[r0, #4\]!
> >>   **       ...
> >>   */
> >>   uint8_t* pre_load8_1 (uint8_t * a, uint16x8_t *v)
> >> @@ -175,7 +175,7 @@ uint8_t* pre_load8_1 (uint8_t * a, uint16x8_t *v)
> >>   /*
> >>   **pre_loadfp16_0:
> >>   **       ...
> >> -**        vldrh.16        q[0-9]+, \[r0, #128\]!
> >> +**        vldrh.16        q[0-7]+, \[r0, #128\]!
> >>   **       ...
> >>   */
> >>   float16_t* pre_loadfp16_0 (float16_t *a, float16x8_t *v)
> >> @@ -188,7 +188,7 @@ float16_t* pre_loadfp16_0 (float16_t *a,
> float16x8_t
> >> *v)
> >>   /*
> >>   **pre_load16_0:
> >>   **       ...
> >> -**        vldrh.16        q[0-9]+, \[r0, #-254\]!
> >> +**        vldrh.16        q[0-7]+, \[r0, #-254\]!
> >>   **       ...
> >>   */
> >>   int16_t* pre_load16_0 (int16_t * a, int16x8_t *v)
> >> @@ -201,7 +201,7 @@ int16_t* pre_load16_0 (int16_t * a, int16x8_t *v)
> >>   /*
> >>   **pre_load16_1:
> >>   **       ...
> >> -**        vldrh.s32       q[0-9]+, \[r0, #52\]!
> >> +**        vldrh.s32       q[0-7]+, \[r0, #52\]!
> >>   **       ...
> >>   */
> >>   int16_t* pre_load16_1 (int16_t * a, int32x4_t *v)
> >> @@ -214,7 +214,7 @@ int16_t* pre_load16_1 (int16_t * a, int32x4_t *v)
> >>   /*
> >>   **pre_loadfp32_0:
> >>   **       ...
> >> -**        vldrw.32        q[0-9]+, \[r0, #-72\]!
> >> +**        vldrw.32        q[0-7]+, \[r0, #-72\]!
> >>   **       ...
> >>   */
> >>   float32_t* pre_loadfp32_0 (float32_t *a, float32x4_t *v)
> >> @@ -228,7 +228,7 @@ float32_t* pre_loadfp32_0 (float32_t *a,
> float32x4_t
> >> *v)
> >>   /*
> >>   **pre_load32_0:
> >>   **       ...
> >> -**        vldrw.32        q[0-9]+, \[r0, #-4\]!
> >> +**        vldrw.32        q[0-7]+, \[r0, #-4\]!
> >>   **       ...
> >>   */
> >>   uint32_t* pre_load32_0 (uint32_t * a, uint32x4_t *v)
> >> @@ -242,7 +242,7 @@ uint32_t* pre_load32_0 (uint32_t * a, uint32x4_t
> *v)
> >>   /*
> >>   **post_load8_0:
> >>   **       ...
> >> -**        vldrb.8 q[0-9]+, \[r0\], #26
> >> +**        vldrb.8 q[0-7]+, \[r0\], #26
> >>   **       ...
> >>   */
> >>   uint8_t* post_load8_0 (uint8_t * a, uint8x16_t *v)
> >> @@ -255,7 +255,7 @@ uint8_t* post_load8_0 (uint8_t * a, uint8x16_t *v)
> >>   /*
> >>   **post_load8_1:
> >>   **       ...
> >> -**        vldrb.s16       q[0-9]+, \[r0\], #-1
> >> +**        vldrb.s16       q[0-7]+, \[r0\], #-1
> >>   **       ...
> >>   */
> >>   int8_t* post_load8_1 (int8_t * a, int16x8_t *v)
> >> @@ -268,7 +268,7 @@ int8_t* post_load8_1 (int8_t * a, int16x8_t *v)
> >>   /*
> >>   **post_load8_2:
> >>   **       ...
> >> -**        vldrb.8 q[0-9]+, \[r0\], #26
> >> +**        vldrb.8 q[0-7]+, \[r0\], #26
> >>   **       ...
> >>   */
> >>   uint8_t* post_load8_2 (uint8_t * a, uint8x16_t *v)
> >> @@ -281,7 +281,7 @@ uint8_t* post_load8_2 (uint8_t * a, uint8x16_t *v)
> >>   /*
> >>   **post_load8_3:
> >>   **       ...
> >> -**        vldrb.s16       q[0-9]+, \[r0\], #-1
> >> +**        vldrb.s16       q[0-7]+, \[r0\], #-1
> >>   **       ...
> >>   */
> >>   int8_t* post_load8_3 (int8_t * a, int16x8_t *v)
> >> @@ -294,7 +294,7 @@ int8_t* post_load8_3 (int8_t * a, int16x8_t *v)
> >>   /*
> >>   **post_loadfp16_0:
> >>   **       ...
> >> -**        vldrh.16        q[0-9]+, \[r0\], #-24
> >> +**        vldrh.16        q[0-7]+, \[r0\], #-24
> >>   **       ...
> >>   */
> >>   float16_t* post_loadfp16_0 (float16_t *a, float16x8_t *v)
> >> @@ -307,7 +307,7 @@ float16_t* post_loadfp16_0 (float16_t *a,
> float16x8_t
> >> *v)
> >>   /*
> >>   **post_load16_0:
> >>   **       ...
> >> -**        vldrh.16        q[0-9]+, \[r0\], #-126
> >> +**        vldrh.16        q[0-7]+, \[r0\], #-126
> >>   **       ...
> >>   */
> >>   uint16_t* post_load16_0 (uint16_t * a, uint16x8_t *v)
> >> @@ -320,7 +320,7 @@ uint16_t* post_load16_0 (uint16_t * a, uint16x8_t
> >> *v)
> >>   /*
> >>   **post_load16_1:
> >>   **       ...
> >> -**        vldrh.u32       q[0-9]+, \[r0\], #16
> >> +**        vldrh.u32       q[0-7]+, \[r0\], #16
> >>   **       ...
> >>   */
> >>   uint16_t* post_load16_1 (uint16_t * a, uint32x4_t *v)
> >> @@ -333,7 +333,7 @@ uint16_t* post_load16_1 (uint16_t * a, uint32x4_t
> >> *v)
> >>   /*
> >>   **post_loadfp32_0:
> >>   **       ...
> >> -**        vldrw.32        q[0-9]+, \[r0\], #4
> >> +**        vldrw.32        q[0-7]+, \[r0\], #4
> >>   **       ...
> >>   */
> >>   float32_t* post_loadfp32_0 (float32_t *a, float32x4_t *v)
> >> @@ -346,7 +346,7 @@ float32_t* post_loadfp32_0 (float32_t *a,
> float32x4_t
> >> *v)
> >>   /*
> >>   **post_load32_0:
> >>   **       ...
> >> -**        vldrw.32        q[0-9]+, \[r0\], #-16
> >> +**        vldrw.32        q[0-7]+, \[r0\], #-16
> >>   **       ...
> >>   */
> >>   int32_t* post_load32_0 (int32_t * a, int32x4_t *v)
> >> diff --git
> a/gcc/testsuite/gcc.target/arm/mve/mve_store_memory_modes.c
> >> b/gcc/testsuite/gcc.target/arm/mve/mve_store_memory_modes.c
> >> index 632f5b44f0b..2fc62916657 100644
> >> --- a/gcc/testsuite/gcc.target/arm/mve/mve_store_memory_modes.c
> >> +++ b/gcc/testsuite/gcc.target/arm/mve/mve_store_memory_modes.c
> >> @@ -7,7 +7,7 @@
> >>   /*
> >>   **off_store8_0:
> >>   **       ...
> >> -**        vstrb.8 q0, \[r0, #16\]
> >> +**        vstrb.8 q[0-7], \[r0, #16\]
> >>   **       ...
> >>   */
> >>   uint8_t *off_store8_0 (uint8_t * a, uint8x16_t v)
> >> @@ -19,7 +19,7 @@ uint8_t *off_store8_0 (uint8_t * a, uint8x16_t v)
> >>   /*
> >>   **off_store8_1:
> >>   **       ...
> >> -**        vstrb.16        q0, \[r0, #-1\]
> >> +**        vstrb.16        q[0-7], \[r0, #-1\]
> >>   **       ...
> >>   */
> >>   int8_t *off_store8_1 (int8_t * a, int16x8_t v)
> >> @@ -31,7 +31,7 @@ int8_t *off_store8_1 (int8_t * a, int16x8_t v)
> >>   /*
> >>   **off_store8_2:
> >>   **       ...
> >> -**        vstrb.32        q0, \[r0, #-127\]
> >> +**        vstrb.32        q[0-7], \[r0, #-127\]
> >>   **       ...
> >>   */
> >>   uint8_t *off_store8_2 (uint8_t * a, uint32x4_t v)
> >> @@ -43,7 +43,7 @@ uint8_t *off_store8_2 (uint8_t * a, uint32x4_t v)
> >>   /*
> >>   **off_store8_3:
> >>   **       ...
> >> -**        vstrb.8 q0, \[r0, #127\]
> >> +**        vstrb.8 q[0-7], \[r0, #127\]
> >>   **       ...
> >>   */
> >>   int8_t *off_store8_3 (int8_t * a, int8x16_t v)
> >> @@ -55,7 +55,7 @@ int8_t *off_store8_3 (int8_t * a, int8x16_t v)
> >>   /*
> >>   **not_off_store8_0:
> >>   **       ...
> >> -**        vstrb.8 q0, \[r[0-9]+\]
> >> +**        vstrb.8 q[0-7], \[r[0-7]+\]
> >>   **       ...
> >>   */
> >>   uint8_t *not_off_store8_0 (uint8_t * a, uint8x16_t v)
> >> @@ -67,7 +67,7 @@ uint8_t *not_off_store8_0 (uint8_t * a, uint8x16_t v)
> >>   /*
> >>   **off_storefp16_0:
> >>   **       ...
> >> -**        vstrh.16        q0, \[r0, #250\]
> >> +**        vstrh.16        q[0-7], \[r0, #250\]
> >>   **       ...
> >>   */
> >>   float16_t *off_storefp16_0 (float16_t *a, float16x8_t v)
> >> @@ -79,7 +79,7 @@ float16_t *off_storefp16_0 (float16_t *a, float16x8_t
> v)
> >>   /*
> >>   **off_store16_0:
> >>   **       ...
> >> -**        vstrh.16        q0, \[r0, #4\]
> >> +**        vstrh.16        q[0-7], \[r0, #4\]
> >>   **       ...
> >>   */
> >>   int16_t *off_store16_0 (int16_t * a, int16x8_t v)
> >> @@ -91,7 +91,7 @@ int16_t *off_store16_0 (int16_t * a, int16x8_t v)
> >>   /*
> >>   **off_store16_1:
> >>   **       ...
> >> -**        vstrh.32        q0, \[r0, #-254\]
> >> +**        vstrh.32        q[0-7], \[r0, #-254\]
> >>   **       ...
> >>   */
> >>   int16_t *off_store16_1 (int16_t * a, int32x4_t v)
> >> @@ -103,7 +103,7 @@ int16_t *off_store16_1 (int16_t * a, int32x4_t v)
> >>   /*
> >>   **not_off_store16_0:
> >>   **       ...
> >> -**        vstrh.16        q0, \[r[0-9]+\]
> >> +**        vstrh.16        q[0-7], \[r[0-7]+\]
> >>   **       ...
> >>   */
> >>   uint8_t *not_off_store16_0 (uint8_t * a, uint16x8_t v)
> >> @@ -115,7 +115,7 @@ uint8_t *not_off_store16_0 (uint8_t * a,
> uint16x8_t
> >> v)
> >>   /*
> >>   **not_off_store16_1:
> >>   **       ...
> >> -**        vstrh.32        q0, \[r[0-9]+\]
> >> +**        vstrh.32        q[0-7], \[r[0-7]+\]
> >>   **       ...
> >>   */
> >>   int16_t *not_off_store16_1 (int16_t * a, int32x4_t v)
> >> @@ -127,7 +127,7 @@ int16_t *not_off_store16_1 (int16_t * a, int32x4_t
> v)
> >>   /*
> >>   **off_storefp32_0:
> >>   **       ...
> >> -**        vstrw.32        q0, \[r0, #-412\]
> >> +**        vstrw.32        q[0-7], \[r0, #-412\]
> >>   **       ...
> >>   */
> >>   float32_t *off_storefp32_0 (float32_t *a, float32x4_t v)
> >> @@ -139,7 +139,7 @@ float32_t *off_storefp32_0 (float32_t *a,
> float32x4_t
> >> v)
> >>   /*
> >>   **off_store32_0:
> >>   **       ...
> >> -**        vstrw.32        q0, \[r0, #-4\]
> >> +**        vstrw.32        q[0-7], \[r0, #-4\]
> >>   **       ...
> >>   */
> >>   int32_t *off_store32_0 (int32_t * a, int32x4_t v)
> >> @@ -151,7 +151,7 @@ int32_t *off_store32_0 (int32_t * a, int32x4_t v)
> >>   /*
> >>   **off_store32_1:
> >>   **       ...
> >> -**        vstrw.32        q0, \[r0, #508\]
> >> +**        vstrw.32        q[0-7], \[r0, #508\]
> >>   **       ...
> >>   */
> >>   uint32_t *off_store32_1 (uint32_t * a, uint32x4_t v)
> >> @@ -163,7 +163,7 @@ uint32_t *off_store32_1 (uint32_t * a, uint32x4_t
> v)
> >>   /*
> >>   **pre_store8_0:
> >>   **       ...
> >> -**        vstrb.8 q[0-9]+, \[r0, #-16\]!
> >> +**        vstrb.8 q[0-7]+, \[r0, #-16\]!
> >>   **       ...
> >>   */
> >>   uint8_t* pre_store8_0 (uint8_t * a, uint8x16_t v)
> >> @@ -176,7 +176,7 @@ uint8_t* pre_store8_0 (uint8_t * a, uint8x16_t v)
> >>   /*
> >>   **pre_store8_1:
> >>   **       ...
> >> -**        vstrb.16        q[0-9]+, \[r0, #4\]!
> >> +**        vstrb.16        q[0-7]+, \[r0, #4\]!
> >>   **       ...
> >>   */
> >>   int8_t* pre_store8_1 (int8_t * a, int16x8_t v)
> >> @@ -189,7 +189,7 @@ int8_t* pre_store8_1 (int8_t * a, int16x8_t v)
> >>   /*
> >>   **pre_storefp16_0:
> >>   **       ...
> >> -**        vstrh.16        q0, \[r0, #8\]!
> >> +**        vstrh.16        q[0-7], \[r0, #8\]!
> >>   **       ...
> >>   */
> >>   float16_t *pre_storefp16_0 (float16_t *a, float16x8_t v)
> >> @@ -202,7 +202,7 @@ float16_t *pre_storefp16_0 (float16_t *a,
> float16x8_t
> >> v)
> >>   /*
> >>   **pre_store16_0:
> >>   **       ...
> >> -**        vstrh.16        q[0-9]+, \[r0, #254\]!
> >> +**        vstrh.16        q[0-7]+, \[r0, #254\]!
> >>   **       ...
> >>   */
> >>   uint16_t* pre_store16_0 (uint16_t * a, uint16x8_t v)
> >> @@ -215,7 +215,7 @@ uint16_t* pre_store16_0 (uint16_t * a, uint16x8_t
> v)
> >>   /*
> >>   **pre_store16_1:
> >>   **       ...
> >> -**        vstrh.32        q[0-9]+, \[r0, #-52\]!
> >> +**        vstrh.32        q[0-7]+, \[r0, #-52\]!
> >>   **       ...
> >>   */
> >>   int16_t* pre_store16_1 (int16_t * a, int32x4_t v)
> >> @@ -228,7 +228,7 @@ int16_t* pre_store16_1 (int16_t * a, int32x4_t v)
> >>   /*
> >>   **pre_storefp32_0:
> >>   **       ...
> >> -**        vstrw.32        q0, \[r0, #-4\]!
> >> +**        vstrw.32        q[0-7], \[r0, #-4\]!
> >>   **       ...
> >>   */
> >>   float32_t *pre_storefp32_0 (float32_t *a, float32x4_t v)
> >> @@ -241,7 +241,7 @@ float32_t *pre_storefp32_0 (float32_t *a,
> float32x4_t
> >> v)
> >>   /*
> >>   **pre_store32_0:
> >>   **       ...
> >> -**        vstrw.32        q[0-9]+, \[r0, #4\]!
> >> +**        vstrw.32        q[0-7]+, \[r0, #4\]!
> >>   **       ...
> >>   */
> >>   int32_t* pre_store32_0 (int32_t * a, int32x4_t v)
> >> @@ -255,7 +255,7 @@ int32_t* pre_store32_0 (int32_t * a, int32x4_t v)
> >>   /*
> >>   **post_store8_0:
> >>   **       ...
> >> -**        vstrb.8 q[0-9]+, \[r0\], #-26
> >> +**        vstrb.8 q[0-7]+, \[r0\], #-26
> >>   **       ...
> >>   */
> >>   int8_t* post_store8_0 (int8_t * a, int8x16_t v)
> >> @@ -268,7 +268,7 @@ int8_t* post_store8_0 (int8_t * a, int8x16_t v)
> >>   /*
> >>   **post_store8_1:
> >>   **       ...
> >> -**        vstrb.16        q[0-9]+, \[r0\], #1
> >> +**        vstrb.16        q[0-7]+, \[r0\], #1
> >>   **       ...
> >>   */
> >>   uint8_t* post_store8_1 (uint8_t * a, uint16x8_t v)
> >> @@ -281,7 +281,7 @@ uint8_t* post_store8_1 (uint8_t * a, uint16x8_t v)
> >>   /*
> >>   **post_store8_2:
> >>   **       ...
> >> -**        vstrb.8 q[0-9]+, \[r0\], #-26
> >> +**        vstrb.8 q[0-7]+, \[r0\], #-26
> >>   **       ...
> >>   */
> >>   int8_t* post_store8_2 (int8_t * a, int8x16_t v)
> >> @@ -294,7 +294,7 @@ int8_t* post_store8_2 (int8_t * a, int8x16_t v)
> >>   /*
> >>   **post_store8_3:
> >>   **       ...
> >> -**        vstrb.16        q[0-9]+, \[r0\], #7
> >> +**        vstrb.16        q[0-7]+, \[r0\], #7
> >>   **       ...
> >>   */
> >>   uint8_t* post_store8_3 (uint8_t * a, uint16x8_t v)
> >> @@ -307,7 +307,7 @@ uint8_t* post_store8_3 (uint8_t * a, uint16x8_t v)
> >>   /*
> >>   **post_storefp16_0:
> >>   **       ...
> >> -**        vstrh.16        q[0-9]+, \[r0\], #-16
> >> +**        vstrh.16        q[0-7]+, \[r0\], #-16
> >>   **       ...
> >>   */
> >>   float16_t *post_storefp16_0 (float16_t *a, float16x8_t v)
> >> @@ -320,7 +320,7 @@ float16_t *post_storefp16_0 (float16_t *a,
> >> float16x8_t v)
> >>   /*
> >>   **post_store16_0:
> >>   **       ...
> >> -**        vstrh.16        q[0-9]+, \[r0\], #126
> >> +**        vstrh.16        q[0-7]+, \[r0\], #126
> >>   **       ...
> >>   */
> >>   int16_t* post_store16_0 (int16_t * a, int16x8_t v)
> >> @@ -333,7 +333,7 @@ int16_t* post_store16_0 (int16_t * a, int16x8_t v)
> >>   /*
> >>   **post_store16_1:
> >>   **       ...
> >> -**        vstrh.32        q[0-9]+, \[r0\], #-16
> >> +**        vstrh.32        q[0-7]+, \[r0\], #-16
> >>   **       ...
> >>   */
> >>   uint16_t* post_store16_1 (uint16_t * a, uint32x4_t v)
> >> @@ -346,7 +346,7 @@ uint16_t* post_store16_1 (uint16_t * a,
> uint32x4_t v)
> >>   /*
> >>   **post_storefp32_0:
> >>   **       ...
> >> -**        vstrw.32        q[0-9]+, \[r0\], #-16
> >> +**        vstrw.32        q[0-7]+, \[r0\], #-16
> >>   **       ...
> >>   */
> >>   float32_t* post_storefp32_0 (float32_t * a, float32x4_t v)
> >> @@ -359,7 +359,7 @@ float32_t* post_storefp32_0 (float32_t * a,
> >> float32x4_t v)
> >>   /*
> >>   **post_store32_0:
> >>   **       ...
> >> -**        vstrw.32        q[0-9]+, \[r0\], #16
> >> +**        vstrw.32        q[0-7]+, \[r0\], #16
> >>   **       ...
> >>   */
> >>   int32_t* post_store32_0 (int32_t * a, int32x4_t v)
> >> --
> >> 2.34.1
> >

Reply via email to