diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c index 18196b3..1ccb796 100644 --- a/gcc/config/arm/arm.c +++ b/gcc/config/arm/arm.c @@ -19890,8 +19890,12 @@ arm_emit_vfp_multi_reg_pop (int first_reg, int num_regs, rtx base_reg) par = emit_insn (par); REG_NOTES (par) = dwarf; - arm_add_cfa_adjust_cfa_note (par, 2 * UNITS_PER_WORD * num_regs, - base_reg, base_reg); + /* REG_CFA_ADJUST_CFA NOTE is added to handle dwarf info issue when + shrink-wrap is enabled. So when shrink-wrap is not enabled, we should + not add the note. */ + if (flag_shrink_wrap) + arm_add_cfa_adjust_cfa_note (par, 2 * UNITS_PER_WORD * num_regs, + base_reg, base_reg); } /* Generate and emit a pattern that will be recognized as LDRD pattern. If even diff --git a/gcc/testsuite/gcc.target/arm/pr59837.c b/gcc/testsuite/gcc.target/arm/pr59837.c new file mode 100644 index 0000000..9057f64 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/pr59837.c @@ -0,0 +1,79 @@ +/* { dg-do compile { target arm_neon } } */ +/* { dg-options " -Os -fno-omit-frame-pointer -mapcs -mabi=aapcs-linux -marm -mfloat-abi=softfp -g " } */ + +#include + +typedef uint8x16_t unative_t; +static inline unative_t SHLBYTE(unative_t v) +{ + return vshlq_n_u8(v, 1); +} + +static inline unative_t MASK(unative_t v) +{ + const uint8x16_t temp = ((unative_t){0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0}); + return (unative_t)vcltq_s8((int8x16_t)v, (int8x16_t)temp); +} + +void raid6_neon4_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs) +{ + uint8_t **dptr = (uint8_t **)ptrs; + uint8_t *p, *q; + int d, z, z0; + + register unative_t wd0, wq0, wp0, w10, w20; + register unative_t wd1, wq1, wp1, w11, w21; + register unative_t wd2, wq2, wp2, w12, w22; + register unative_t wd3, wq3, wp3, w13, w23; + const unative_t x1d = ((unative_t){0x1d,0x1d,0x1d,0x1d, 0x1d,0x1d,0x1d,0x1d, 0x1d,0x1d,0x1d,0x1d, 0x1d,0x1d,0x1d,0x1d}); + + z0 = disks - 3; + p = dptr[z0+1]; + q = dptr[z0+2]; + + for ( d = 0 ; d < bytes ; d += sizeof(unative_t)*4 ) { + wq0 = wp0 = vld1q_u8(&dptr[z0][d+0*sizeof(unative_t)]); + wq1 = wp1 = vld1q_u8(&dptr[z0][d+1*sizeof(unative_t)]); + wq2 = wp2 = vld1q_u8(&dptr[z0][d+2*sizeof(unative_t)]); + wq3 = wp3 = vld1q_u8(&dptr[z0][d+3*sizeof(unative_t)]); + for ( z = z0-1 ; z >= 0 ; z-- ) { + wd0 = vld1q_u8(&dptr[z][d+0*sizeof(unative_t)]); + wd1 = vld1q_u8(&dptr[z][d+1*sizeof(unative_t)]); + wd2 = vld1q_u8(&dptr[z][d+2*sizeof(unative_t)]); + wd3 = vld1q_u8(&dptr[z][d+3*sizeof(unative_t)]); + wp0 = veorq_u8(wp0, wd0); + wp1 = veorq_u8(wp1, wd1); + wp2 = veorq_u8(wp2, wd2); + wp3 = veorq_u8(wp3, wd3); + w20 = MASK(wq0); + w21 = MASK(wq1); + w22 = MASK(wq2); + w23 = MASK(wq3); + w10 = SHLBYTE(wq0); + w11 = SHLBYTE(wq1); + w12 = SHLBYTE(wq2); + w13 = SHLBYTE(wq3); + + w20 = vandq_u8(w20, x1d); + w21 = vandq_u8(w21, x1d); + w22 = vandq_u8(w22, x1d); + w23 = vandq_u8(w23, x1d); + w10 = veorq_u8(w10, w20); + w11 = veorq_u8(w11, w21); + w12 = veorq_u8(w12, w22); + w13 = veorq_u8(w13, w23); + wq0 = veorq_u8(w10, wd0); + wq1 = veorq_u8(w11, wd1); + wq2 = veorq_u8(w12, wd2); + wq3 = veorq_u8(w13, wd3); + } + vst1q_u8(&p[d+sizeof(unative_t)*0], wp0); + vst1q_u8(&p[d+sizeof(unative_t)*1], wp1); + vst1q_u8(&p[d+sizeof(unative_t)*2], wp2); + vst1q_u8(&p[d+sizeof(unative_t)*3], wp3); + vst1q_u8(&q[d+sizeof(unative_t)*0], wq0); + vst1q_u8(&q[d+sizeof(unative_t)*1], wq1); + vst1q_u8(&q[d+sizeof(unative_t)*2], wq2); + vst1q_u8(&q[d+sizeof(unative_t)*3], wq3); + } +}