From 9ce780efc4a8f47cf1fbba8e0494e65e87b0749c Mon Sep 17 00:00:00 2001 From: Andre Simoes Dias Vieira Date: Tue, 7 Apr 2020 15:06:37 +0100 Subject: [PATCH] arm: MVE: Fix v[id]wdup's This patch fixes v[id]wdup intrinsics. They had two issues: 1) the predicated versions did not link the incoming inactive vector parameter to the output 2) The backend didn't enforce the wrap limit operand be in an odd register. 1) was fixed like we did for all other predicated intrinsics 2) requires a temporary hack where we pass the value in the top end of DImode operand. The proper fix would be to add a register CLASS but this interacted badly with other existing targets codegen. We will look to fix this properly in GCC 11. gcc/ChangeLog: 2020-04-07 Andre Vieira * config/arm/arm_mve.h: Fix v[id]wdup intrinsics. * config/arm/mve/md: Fix v[id]wdup patterns. --- gcc/ChangeLog | 5 ++ gcc/config/arm/arm_mve.h | 157 ++++++++++++++++++++++++--------------- gcc/config/arm/mve.md | 45 +++++------ 3 files changed, 125 insertions(+), 82 deletions(-) diff --git a/gcc/ChangeLog b/gcc/ChangeLog index b76a51a3758..48c9c48aad6 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,8 @@ +2020-04-07 Andre Vieira + + * config/arm/arm_mve.h: Fix v[id]wdup intrinsics. + * config/arm/mve/md: Fix v[id]wdup patterns. + 2020-04-07 Andre Vieira * config/arm/arm.c (output_move_neon): Deal with label + offset cases. diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h index e31c2e8fdc4..47eead71d95 100644 --- a/gcc/config/arm/arm_mve.h +++ b/gcc/config/arm/arm_mve.h @@ -13585,29 +13585,33 @@ __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_m_n_u8 (uint8x16_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - return __builtin_mve_vdwdupq_m_n_uv16qi (__inactive, __a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_vdwdupq_m_n_uv16qi (__inactive, __a, __c, __imm, __p); } __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_m_n_u32 (uint32x4_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - return __builtin_mve_vdwdupq_m_n_uv4si (__inactive, __a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_vdwdupq_m_n_uv4si (__inactive, __a, __c, __imm, __p); } __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_m_n_u16 (uint16x8_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - return __builtin_mve_vdwdupq_m_n_uv8hi (__inactive, __a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_vdwdupq_m_n_uv8hi (__inactive, __a, __c, __imm, __p); } __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_m_wb_u8 (uint8x16_t __inactive, uint32_t * __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - uint8x16_t __res = __builtin_mve_vdwdupq_m_n_uv16qi (__inactive, *__a, __b, __imm, __p); - *__a = __builtin_mve_vdwdupq_m_wb_uv16qi (__inactive, *__a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + uint8x16_t __res = __builtin_mve_vdwdupq_m_n_uv16qi (__inactive, *__a, __c, __imm, __p); + *__a = __builtin_mve_vdwdupq_m_wb_uv16qi (__inactive, *__a, __c, __imm, __p); return __res; } @@ -13615,8 +13619,9 @@ __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_m_wb_u32 (uint32x4_t __inactive, uint32_t * __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - uint32x4_t __res = __builtin_mve_vdwdupq_m_n_uv4si (__inactive, *__a, __b, __imm, __p); - *__a = __builtin_mve_vdwdupq_m_wb_uv4si (__inactive, *__a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + uint32x4_t __res = __builtin_mve_vdwdupq_m_n_uv4si (__inactive, *__a, __c, __imm, __p); + *__a = __builtin_mve_vdwdupq_m_wb_uv4si (__inactive, *__a, __c, __imm, __p); return __res; } @@ -13624,8 +13629,9 @@ __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_m_wb_u16 (uint16x8_t __inactive, uint32_t * __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - uint16x8_t __res = __builtin_mve_vdwdupq_m_n_uv8hi (__inactive, *__a, __b, __imm, __p); - *__a = __builtin_mve_vdwdupq_m_wb_uv8hi (__inactive, *__a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + uint16x8_t __res = __builtin_mve_vdwdupq_m_n_uv8hi (__inactive, *__a, __c, __imm, __p); + *__a = __builtin_mve_vdwdupq_m_wb_uv8hi (__inactive, *__a, __c, __imm, __p); return __res; } @@ -13633,29 +13639,33 @@ __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_n_u8 (uint32_t __a, uint32_t __b, const int __imm) { - return __builtin_mve_vdwdupq_n_uv16qi (__a, __b, __imm); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_vdwdupq_n_uv16qi (__a, __c, __imm); } __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_n_u32 (uint32_t __a, uint32_t __b, const int __imm) { - return __builtin_mve_vdwdupq_n_uv4si (__a, __b, __imm); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_vdwdupq_n_uv4si (__a, __c, __imm); } __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_n_u16 (uint32_t __a, uint32_t __b, const int __imm) { - return __builtin_mve_vdwdupq_n_uv8hi (__a, __b, __imm); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_vdwdupq_n_uv8hi (__a, __c, __imm); } __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_wb_u8 (uint32_t * __a, uint32_t __b, const int __imm) { - uint8x16_t __res = __builtin_mve_vdwdupq_n_uv16qi (*__a, __b, __imm); - *__a = __builtin_mve_vdwdupq_wb_uv16qi (*__a, __b, __imm); + uint64_t __c = ((uint64_t) __b) << 32; + uint8x16_t __res = __builtin_mve_vdwdupq_n_uv16qi (*__a, __c, __imm); + *__a = __builtin_mve_vdwdupq_wb_uv16qi (*__a, __c, __imm); return __res; } @@ -13663,8 +13673,9 @@ __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_wb_u32 (uint32_t * __a, uint32_t __b, const int __imm) { - uint32x4_t __res = __builtin_mve_vdwdupq_n_uv4si (*__a, __b, __imm); - *__a = __builtin_mve_vdwdupq_wb_uv4si (*__a, __b, __imm); + uint64_t __c = ((uint64_t) __b) << 32; + uint32x4_t __res = __builtin_mve_vdwdupq_n_uv4si (*__a, __c, __imm); + *__a = __builtin_mve_vdwdupq_wb_uv4si (*__a, __c, __imm); return __res; } @@ -13672,8 +13683,9 @@ __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_wb_u16 (uint32_t * __a, uint32_t __b, const int __imm) { - uint16x8_t __res = __builtin_mve_vdwdupq_n_uv8hi (*__a, __b, __imm); - *__a = __builtin_mve_vdwdupq_wb_uv8hi (*__a, __b, __imm); + uint64_t __c = ((uint64_t) __b) << 32; + uint16x8_t __res = __builtin_mve_vdwdupq_n_uv8hi (*__a, __c, __imm); + *__a = __builtin_mve_vdwdupq_wb_uv8hi (*__a, __c, __imm); return __res; } @@ -13804,29 +13816,33 @@ __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_m_n_u8 (uint8x16_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - return __builtin_mve_viwdupq_m_n_uv16qi (__inactive, __a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_viwdupq_m_n_uv16qi (__inactive, __a, __c, __imm, __p); } __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_m_n_u32 (uint32x4_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - return __builtin_mve_viwdupq_m_n_uv4si (__inactive, __a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_viwdupq_m_n_uv4si (__inactive, __a, __c, __imm, __p); } __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_m_n_u16 (uint16x8_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - return __builtin_mve_viwdupq_m_n_uv8hi (__inactive, __a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_viwdupq_m_n_uv8hi (__inactive, __a, __c, __imm, __p); } __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_m_wb_u8 (uint8x16_t __inactive, uint32_t * __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - uint8x16_t __res = __builtin_mve_viwdupq_m_n_uv16qi (__inactive, *__a, __b, __imm, __p); - *__a = __builtin_mve_viwdupq_m_wb_uv16qi (__inactive, *__a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + uint8x16_t __res = __builtin_mve_viwdupq_m_n_uv16qi (__inactive, *__a, __c, __imm, __p); + *__a = __builtin_mve_viwdupq_m_wb_uv16qi (__inactive, *__a, __c, __imm, __p); return __res; } @@ -13834,8 +13850,9 @@ __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_m_wb_u32 (uint32x4_t __inactive, uint32_t * __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - uint32x4_t __res = __builtin_mve_viwdupq_m_n_uv4si (__inactive, *__a, __b, __imm, __p); - *__a = __builtin_mve_viwdupq_m_wb_uv4si (__inactive, *__a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + uint32x4_t __res = __builtin_mve_viwdupq_m_n_uv4si (__inactive, *__a, __c, __imm, __p); + *__a = __builtin_mve_viwdupq_m_wb_uv4si (__inactive, *__a, __c, __imm, __p); return __res; } @@ -13843,8 +13860,9 @@ __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_m_wb_u16 (uint16x8_t __inactive, uint32_t * __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - uint16x8_t __res = __builtin_mve_viwdupq_m_n_uv8hi (__inactive, *__a, __b, __imm, __p); - *__a = __builtin_mve_viwdupq_m_wb_uv8hi (__inactive, *__a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + uint16x8_t __res = __builtin_mve_viwdupq_m_n_uv8hi (__inactive, *__a, __c, __imm, __p); + *__a = __builtin_mve_viwdupq_m_wb_uv8hi (__inactive, *__a, __c, __imm, __p); return __res; } @@ -13852,29 +13870,33 @@ __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_n_u8 (uint32_t __a, uint32_t __b, const int __imm) { - return __builtin_mve_viwdupq_n_uv16qi (__a, __b, __imm); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_viwdupq_n_uv16qi (__a, __c, __imm); } __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_n_u32 (uint32_t __a, uint32_t __b, const int __imm) { - return __builtin_mve_viwdupq_n_uv4si (__a, __b, __imm); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_viwdupq_n_uv4si (__a, __c, __imm); } __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_n_u16 (uint32_t __a, uint32_t __b, const int __imm) { - return __builtin_mve_viwdupq_n_uv8hi (__a, __b, __imm); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_viwdupq_n_uv8hi (__a, __c, __imm); } __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_wb_u8 (uint32_t * __a, uint32_t __b, const int __imm) { - uint8x16_t __res = __builtin_mve_viwdupq_n_uv16qi (*__a, __b, __imm); - *__a = __builtin_mve_viwdupq_wb_uv16qi (*__a, __b, __imm); + uint64_t __c = ((uint64_t) __b) << 32; + uint8x16_t __res = __builtin_mve_viwdupq_n_uv16qi (*__a, __c, __imm); + *__a = __builtin_mve_viwdupq_wb_uv16qi (*__a, __c, __imm); return __res; } @@ -13882,8 +13904,9 @@ __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_wb_u32 (uint32_t * __a, uint32_t __b, const int __imm) { - uint32x4_t __res = __builtin_mve_viwdupq_n_uv4si (*__a, __b, __imm); - *__a = __builtin_mve_viwdupq_wb_uv4si (*__a, __b, __imm); + uint64_t __c = ((uint64_t) __b) << 32; + uint32x4_t __res = __builtin_mve_viwdupq_n_uv4si (*__a, __c, __imm); + *__a = __builtin_mve_viwdupq_wb_uv4si (*__a, __c, __imm); return __res; } @@ -13891,11 +13914,13 @@ __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_wb_u16 (uint32_t * __a, uint32_t __b, const int __imm) { - uint16x8_t __res = __builtin_mve_viwdupq_n_uv8hi (*__a, __b, __imm); - *__a = __builtin_mve_viwdupq_wb_uv8hi (*__a, __b, __imm); + uint64_t __c = ((uint64_t) __b) << 32; + uint16x8_t __res = __builtin_mve_viwdupq_n_uv8hi (*__a, __c, __imm); + *__a = __builtin_mve_viwdupq_wb_uv8hi (*__a, __c, __imm); return __res; } + __extension__ extern __inline int64x2_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vldrdq_gather_base_wb_s64 (uint64x2_t * __addr, const int __offset) @@ -14095,30 +14120,34 @@ __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_x_n_u8 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - return __builtin_mve_vdwdupq_m_n_uv16qi (vuninitializedq_u8 (), __a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_vdwdupq_m_n_uv16qi (__arm_vuninitializedq_u8 (), __a, __c, __imm, __p); } __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_x_n_u16 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - return __builtin_mve_vdwdupq_m_n_uv8hi (vuninitializedq_u16 (), __a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_vdwdupq_m_n_uv8hi (__arm_vuninitializedq_u16 (), __a, __c, __imm, __p); } __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_x_n_u32 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - return __builtin_mve_vdwdupq_m_n_uv4si (vuninitializedq_u32 (), __a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_vdwdupq_m_n_uv4si (__arm_vuninitializedq_u32 (), __a, __c, __imm, __p); } __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_x_wb_u8 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16_t __p) { - uint8x16_t __arg1 = vuninitializedq_u8 (); - uint8x16_t __res = __builtin_mve_vdwdupq_m_n_uv16qi (__arg1, *__a, __b, __imm, __p); - *__a = __builtin_mve_vdwdupq_m_wb_uv16qi (__arg1, *__a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + uint8x16_t __arg1 = __arm_vuninitializedq_u8 (); + uint8x16_t __res = __builtin_mve_vdwdupq_m_n_uv16qi (__arg1, *__a, __c, __imm, __p); + *__a = __builtin_mve_vdwdupq_m_wb_uv16qi (__arg1, *__a, __c, __imm, __p); return __res; } @@ -14126,9 +14155,10 @@ __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_x_wb_u16 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16_t __p) { - uint16x8_t __arg1 = vuninitializedq_u16 (); - uint16x8_t __res = __builtin_mve_vdwdupq_m_n_uv8hi (__arg1, *__a, __b, __imm, __p); - *__a = __builtin_mve_vdwdupq_m_wb_uv8hi (__arg1, *__a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + uint16x8_t __arg1 = __arm_vuninitializedq_u16 (); + uint16x8_t __res = __builtin_mve_vdwdupq_m_n_uv8hi (__arg1, *__a, __c, __imm, __p); + *__a = __builtin_mve_vdwdupq_m_wb_uv8hi (__arg1, *__a, __c, __imm, __p); return __res; } @@ -14136,9 +14166,10 @@ __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_x_wb_u32 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16_t __p) { - uint32x4_t __arg1 = vuninitializedq_u32 (); - uint32x4_t __res = __builtin_mve_vdwdupq_m_n_uv4si (__arg1, *__a, __b, __imm, __p); - *__a = __builtin_mve_vdwdupq_m_wb_uv4si (__arg1, *__a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + uint32x4_t __arg1 = __arm_vuninitializedq_u32 (); + uint32x4_t __res = __builtin_mve_vdwdupq_m_n_uv4si (__arg1, *__a, __c, __imm, __p); + *__a = __builtin_mve_vdwdupq_m_wb_uv4si (__arg1, *__a, __c, __imm, __p); return __res; } @@ -14197,30 +14228,34 @@ __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_x_n_u8 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - return __builtin_mve_viwdupq_m_n_uv16qi (vuninitializedq_u8 (), __a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_viwdupq_m_n_uv16qi (__arm_vuninitializedq_u8 (), __a, __c, __imm, __p); } __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_x_n_u16 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - return __builtin_mve_viwdupq_m_n_uv8hi (vuninitializedq_u16 (), __a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_viwdupq_m_n_uv8hi (__arm_vuninitializedq_u16 (), __a, __c, __imm, __p); } __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_x_n_u32 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) { - return __builtin_mve_viwdupq_m_n_uv4si (vuninitializedq_u32 (), __a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + return __builtin_mve_viwdupq_m_n_uv4si (__arm_vuninitializedq_u32 (), __a, __c, __imm, __p); } __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_x_wb_u8 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16_t __p) { - uint8x16_t __arg1 = vuninitializedq_u8 (); - uint8x16_t __res = __builtin_mve_viwdupq_m_n_uv16qi (__arg1, *__a, __b, __imm, __p); - *__a = __builtin_mve_viwdupq_m_wb_uv16qi (__arg1, *__a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + uint8x16_t __arg1 = __arm_vuninitializedq_u8 (); + uint8x16_t __res = __builtin_mve_viwdupq_m_n_uv16qi (__arg1, *__a, __c, __imm, __p); + *__a = __builtin_mve_viwdupq_m_wb_uv16qi (__arg1, *__a, __c, __imm, __p); return __res; } @@ -14228,9 +14263,10 @@ __extension__ extern __inline uint16x8_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_x_wb_u16 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16_t __p) { - uint16x8_t __arg1 = vuninitializedq_u16 (); - uint16x8_t __res = __builtin_mve_viwdupq_m_n_uv8hi (__arg1, *__a, __b, __imm, __p); - *__a = __builtin_mve_viwdupq_m_wb_uv8hi (__arg1, *__a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + uint16x8_t __arg1 = __arm_vuninitializedq_u16 (); + uint16x8_t __res = __builtin_mve_viwdupq_m_n_uv8hi (__arg1, *__a, __c, __imm, __p); + *__a = __builtin_mve_viwdupq_m_wb_uv8hi (__arg1, *__a, __c, __imm, __p); return __res; } @@ -14238,9 +14274,10 @@ __extension__ extern __inline uint32x4_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_x_wb_u32 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16_t __p) { - uint32x4_t __arg1 = vuninitializedq_u32 (); - uint32x4_t __res = __builtin_mve_viwdupq_m_n_uv4si (__arg1, *__a, __b, __imm, __p); - *__a = __builtin_mve_viwdupq_m_wb_uv4si (__arg1, *__a, __b, __imm, __p); + uint64_t __c = ((uint64_t) __b) << 32; + uint32x4_t __arg1 = __arm_vuninitializedq_u32 (); + uint32x4_t __res = __builtin_mve_viwdupq_m_n_uv4si (__arg1, *__a, __c, __imm, __p); + *__a = __builtin_mve_viwdupq_m_wb_uv4si (__arg1, *__a, __c, __imm, __p); return __res; } diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md index 10abc3fae37..4a506cc3861 100644 --- a/gcc/config/arm/mve.md +++ b/gcc/config/arm/mve.md @@ -9853,7 +9853,7 @@ (define_expand "mve_vdwdupq_n_u" [(match_operand:MVE_2 0 "s_register_operand") (match_operand:SI 1 "s_register_operand") - (match_operand:SI 2 "s_register_operand") + (match_operand:DI 2 "s_register_operand") (match_operand:SI 3 "mve_imm_selective_upto_8")] "TARGET_HAVE_MVE" { @@ -9870,7 +9870,7 @@ (define_expand "mve_vdwdupq_wb_u" [(match_operand:SI 0 "s_register_operand") (match_operand:SI 1 "s_register_operand") - (match_operand:SI 2 "s_register_operand") + (match_operand:DI 2 "s_register_operand") (match_operand:SI 3 "mve_imm_selective_upto_8") (unspec:MVE_2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)] "TARGET_HAVE_MVE" @@ -9888,16 +9888,16 @@ (define_insn "mve_vdwdupq_wb_u_insn" [(set (match_operand:MVE_2 0 "s_register_operand" "=w") (unspec:MVE_2 [(match_operand:SI 2 "s_register_operand" "1") - (match_operand:SI 3 "s_register_operand" "r") + (subreg:SI (match_operand:DI 3 "s_register_operand" "r") 4) (match_operand:SI 4 "mve_imm_selective_upto_8" "Rg")] VDWDUPQ)) (set (match_operand:SI 1 "s_register_operand" "=e") (unspec:SI [(match_dup 2) - (match_dup 3) + (subreg:SI (match_dup 3) 4) (match_dup 4)] VDWDUPQ))] "TARGET_HAVE_MVE" - "vdwdup.u%#\t%q0, %2, %3, %4" + "vdwdup.u%#\t%q0, %2, %R3, %4" ) ;; @@ -9907,7 +9907,7 @@ [(match_operand:MVE_2 0 "s_register_operand") (match_operand:MVE_2 1 "s_register_operand") (match_operand:SI 2 "s_register_operand") - (match_operand:SI 3 "s_register_operand") + (match_operand:DI 3 "s_register_operand") (match_operand:SI 4 "mve_imm_selective_upto_8") (match_operand:HI 5 "vpr_register_operand")] "TARGET_HAVE_MVE" @@ -9927,7 +9927,7 @@ [(match_operand:SI 0 "s_register_operand") (match_operand:MVE_2 1 "s_register_operand") (match_operand:SI 2 "s_register_operand") - (match_operand:SI 3 "s_register_operand") + (match_operand:DI 3 "s_register_operand") (match_operand:SI 4 "mve_imm_selective_upto_8") (match_operand:HI 5 "vpr_register_operand")] "TARGET_HAVE_MVE" @@ -9945,22 +9945,22 @@ ;; (define_insn "mve_vdwdupq_m_wb_u_insn" [(set (match_operand:MVE_2 0 "s_register_operand" "=w") - (unspec:MVE_2 [(match_operand:MVE_2 2 "s_register_operand" "w") + (unspec:MVE_2 [(match_operand:MVE_2 2 "s_register_operand" "0") (match_operand:SI 3 "s_register_operand" "1") - (match_operand:SI 4 "s_register_operand" "r") + (subreg:SI (match_operand:DI 4 "s_register_operand" "r") 4) (match_operand:SI 5 "mve_imm_selective_upto_8" "Rg") (match_operand:HI 6 "vpr_register_operand" "Up")] VDWDUPQ_M)) (set (match_operand:SI 1 "s_register_operand" "=e") (unspec:SI [(match_dup 2) (match_dup 3) - (match_dup 4) + (subreg:SI (match_dup 4) 4) (match_dup 5) (match_dup 6)] VDWDUPQ_M)) ] "TARGET_HAVE_MVE" - "vpst\;\tvdwdupt.u%#\t%q2, %3, %4, %5" + "vpst\;\tvdwdupt.u%#\t%q2, %3, %R4, %5" [(set_attr "type" "mve_move") (set_attr "length""8")]) @@ -9970,7 +9970,7 @@ (define_expand "mve_viwdupq_n_u" [(match_operand:MVE_2 0 "s_register_operand") (match_operand:SI 1 "s_register_operand") - (match_operand:SI 2 "s_register_operand") + (match_operand:DI 2 "s_register_operand") (match_operand:SI 3 "mve_imm_selective_upto_8")] "TARGET_HAVE_MVE" { @@ -9987,7 +9987,7 @@ (define_expand "mve_viwdupq_wb_u" [(match_operand:SI 0 "s_register_operand") (match_operand:SI 1 "s_register_operand") - (match_operand:SI 2 "s_register_operand") + (match_operand:DI 2 "s_register_operand") (match_operand:SI 3 "mve_imm_selective_upto_8") (unspec:MVE_2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)] "TARGET_HAVE_MVE" @@ -10005,16 +10005,16 @@ (define_insn "mve_viwdupq_wb_u_insn" [(set (match_operand:MVE_2 0 "s_register_operand" "=w") (unspec:MVE_2 [(match_operand:SI 2 "s_register_operand" "1") - (match_operand:SI 3 "s_register_operand" "r") + (subreg:SI (match_operand:DI 3 "s_register_operand" "r") 4) (match_operand:SI 4 "mve_imm_selective_upto_8" "Rg")] VIWDUPQ)) (set (match_operand:SI 1 "s_register_operand" "=e") (unspec:SI [(match_dup 2) - (match_dup 3) + (subreg:SI (match_dup 3) 4) (match_dup 4)] VIWDUPQ))] "TARGET_HAVE_MVE" - "viwdup.u%#\t%q0, %2, %3, %4" + "viwdup.u%#\t%q0, %2, %R3, %4" ) ;; @@ -10024,7 +10024,7 @@ [(match_operand:MVE_2 0 "s_register_operand") (match_operand:MVE_2 1 "s_register_operand") (match_operand:SI 2 "s_register_operand") - (match_operand:SI 3 "s_register_operand") + (match_operand:DI 3 "s_register_operand") (match_operand:SI 4 "mve_imm_selective_upto_8") (match_operand:HI 5 "vpr_register_operand")] "TARGET_HAVE_MVE" @@ -10044,7 +10044,7 @@ [(match_operand:SI 0 "s_register_operand") (match_operand:MVE_2 1 "s_register_operand") (match_operand:SI 2 "s_register_operand") - (match_operand:SI 3 "s_register_operand") + (match_operand:DI 3 "s_register_operand") (match_operand:SI 4 "mve_imm_selective_upto_8") (match_operand:HI 5 "vpr_register_operand")] "TARGET_HAVE_MVE" @@ -10062,24 +10062,25 @@ ;; (define_insn "mve_viwdupq_m_wb_u_insn" [(set (match_operand:MVE_2 0 "s_register_operand" "=w") - (unspec:MVE_2 [(match_operand:MVE_2 2 "s_register_operand" "w") + (unspec:MVE_2 [(match_operand:MVE_2 2 "s_register_operand" "0") (match_operand:SI 3 "s_register_operand" "1") - (match_operand:SI 4 "s_register_operand" "r") + (subreg:SI (match_operand:DI 4 "s_register_operand" "r") 4) (match_operand:SI 5 "mve_imm_selective_upto_8" "Rg") (match_operand:HI 6 "vpr_register_operand" "Up")] VIWDUPQ_M)) (set (match_operand:SI 1 "s_register_operand" "=e") (unspec:SI [(match_dup 2) (match_dup 3) - (match_dup 4) + (subreg:SI (match_dup 4) 4) (match_dup 5) (match_dup 6)] VIWDUPQ_M)) ] "TARGET_HAVE_MVE" - "vpst\;\tviwdupt.u%#\t%q2, %3, %4, %5" + "vpst\;\tviwdupt.u%#\t%q2, %3, %R4, %5" [(set_attr "type" "mve_move") (set_attr "length""8")]) + (define_expand "mve_vstrwq_scatter_base_wb_v4si" [(match_operand:V4SI 0 "s_register_operand" "=w") (match_operand:SI 1 "mve_vldrd_immediate" "Ri")