| Message ID | 540D84ED.2030002@arm.com |
|---|---|
| State | New |
| Headers | show |
Must have slipped through the cracks. https://gcc.gnu.org/ml/gcc-patches/2014-09/msg00586.html Ping? Thanks, Kyrill On 08/09/14 11:29, Kyrill Tkachov wrote: > Hi all, > > The included testcase currently ICEs at -O0 because vget_lane_f64 is a function, so if it's properly called with a constant argument but without constant propagation it will not be recognised as constant, causing an ICE. > This patch changes it to use the macro version directly. > > I think there is work being done to fix this issue up as part of a more general rework, but until that comes this patch implements the concerned intrinsics using the __aarch64_vget_lane* macros like the other lane intrinsics around them. > > Tested aarch64-none-elf. > > Ok for trunk? > > Thanks, > Kyrill > > 2014-09-08 Kyrylo Tkachov <kyrylo.tkachov@arm.com> > > * config/aarch64/arm_neon.h (vmuld_lane_f64): Use macro for getting > the lane. > (vmuld_laneq_f64): Likewise. > (vmuls_lane_f32): Likewise. > (vmuls_laneq_f32): Likewise. > > 2014-09-08 Kyrylo Tkachov <kyrylo.tkachov@arm.com> > > * gcc.target/aarch64/simd/vmul_lane_const_lane_1.c: New test.
On 8 September 2014 11:29, Kyrill Tkachov <kyrylo.tkachov@arm.com> wrote: > Hi all, > > The included testcase currently ICEs at -O0 because vget_lane_f64 is a > function, so if it's properly called with a constant argument but without > constant propagation it will not be recognised as constant, causing an ICE. > This patch changes it to use the macro version directly. > > I think there is work being done to fix this issue up as part of a more > general rework, but until that comes this patch implements the concerned > intrinsics using the __aarch64_vget_lane* macros like the other lane > intrinsics around them. > > Tested aarch64-none-elf. > > Ok for trunk? > > Thanks, > Kyrill > > 2014-09-08 Kyrylo Tkachov <kyrylo.tkachov@arm.com> > > * config/aarch64/arm_neon.h (vmuld_lane_f64): Use macro for getting > the lane. > (vmuld_laneq_f64): Likewise. > (vmuls_lane_f32): Likewise. > (vmuls_laneq_f32): Likewise. > > 2014-09-08 Kyrylo Tkachov <kyrylo.tkachov@arm.com> > > * gcc.target/aarch64/simd/vmul_lane_const_lane_1.c: New test. OK /Marcus
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h index 0a86172..cf2b0b6 100644 --- a/gcc/config/aarch64/arm_neon.h +++ b/gcc/config/aarch64/arm_neon.h @@ -18970,13 +18970,13 @@ vmul_lane_u32 (uint32x2_t __a, uint32x2_t __b, const int __lane) __extension__ static __inline float64_t __attribute__ ((__always_inline__)) vmuld_lane_f64 (float64_t __a, float64x1_t __b, const int __lane) { - return __a * vget_lane_f64 (__b, __lane); + return __a * __aarch64_vget_lane_f64 (__b, __lane); } __extension__ static __inline float64_t __attribute__ ((__always_inline__)) vmuld_laneq_f64 (float64_t __a, float64x2_t __b, const int __lane) { - return __a * vgetq_lane_f64 (__b, __lane); + return __a * __aarch64_vgetq_lane_f64 (__b, __lane); } /* vmuls_lane */ @@ -18984,13 +18984,13 @@ vmuld_laneq_f64 (float64_t __a, float64x2_t __b, const int __lane) __extension__ static __inline float32_t __attribute__ ((__always_inline__)) vmuls_lane_f32 (float32_t __a, float32x2_t __b, const int __lane) { - return __a * vget_lane_f32 (__b, __lane); + return __a * __aarch64_vget_lane_f32 (__b, __lane); } __extension__ static __inline float32_t __attribute__ ((__always_inline__)) vmuls_laneq_f32 (float32_t __a, float32x4_t __b, const int __lane) { - return __a * vgetq_lane_f32 (__b, __lane); + return __a * __aarch64_vgetq_lane_f32 (__b, __lane); } /* vmul_laneq */ diff --git a/gcc/testsuite/gcc.target/aarch64/simd/vmul_lane_const_lane_1.c b/gcc/testsuite/gcc.target/aarch64/simd/vmul_lane_const_lane_1.c new file mode 100644 index 0000000..2455181 --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/simd/vmul_lane_const_lane_1.c @@ -0,0 +1,28 @@ +/* { dg-do compile } */ +/* { dg-options "-O0" } */ + +#include "arm_neon.h" + +float64_t +wrap_vmuld_lane_f64 (float64_t a, float64x1_t b) +{ + return vmuld_lane_f64 (a, b, 0); +} + +float64_t +wrap_vmuld_laneq_f64 (float64_t a, float64x2_t b) +{ + return vmuld_laneq_f64 (a, b, 0); +} + +float32_t +wrap_vmuls_lane_f32 (float32_t a, float32x2_t b) +{ + return vmuls_lane_f32 (a, b, 0); +} + +float32_t +wrap_vmuls_laneq_f32 (float32_t a, float32x4_t b) +{ + return vmuls_laneq_f32 (a, b, 0); +}