Hi, This fixes PR target/54212.. The problem here was we were marking a number of patterns in neon.md as predicable. Advanced SIMD instructions are not predicable in ARM state, however are allowed to exist in Thumb2 in IT blocks ( though this is a feature that is deprecated and is documented in the latest ARM ARM Issue C.B ) . This therefore removes the predicable attribute from all such instructions in the Neon backend. This is currently undergoing regression testing on armv7-a cross, will apply if no regressions and I intend backporting this atleast to 4.7 branch as this is an issue in the backend since the original days of Advanced SIMD support and the bug report was reported on the 4.7 branch where it is reproducible.
I would like to take this back to 4.6 branch as well but would like to do so after it has lived for a while on trunk / 4.7 . regards, Ramana 2012-08-14 Ramana Radhakrishnan <ramana.radhakrish...@linaro.org> PR target/54212 * config/arm/neon.md (vec_set<mode>_internal VD,VQ): Do not mark as predicable. Adjust asm template. (vec_setv2di_internal): Likewise. (vec_extract<mode> VD, VQ): Likewise. (vec_extractv2di): Likewise. (neon_vget_lane<mode>_sext_internal VD, VQ): Likewise. (neon_vset_lane<mode>_sext_internal VD, VQ): Likewise. (neon_vdup_n<mode> VX, V32): Likewise. (neon_vdup_nv2di): Likewise.
diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md index 7142c98..12c7934 100644 --- a/gcc/config/arm/neon.md +++ b/gcc/config/arm/neon.md @@ -434,10 +434,9 @@ elt = GET_MODE_NUNITS (<MODE>mode) - 1 - elt; operands[2] = GEN_INT (elt); - return "vmov%?.<V_sz_elem>\t%P0[%c2], %1"; + return "vmov.<V_sz_elem>\t%P0[%c2], %1"; } - [(set_attr "predicable" "yes") - (set_attr "neon_type" "neon_mcr")]) + [(set_attr "neon_type" "neon_mcr")]) (define_insn "vec_set<mode>_internal" [(set (match_operand:VQ 0 "s_register_operand" "=w") @@ -460,10 +459,9 @@ operands[0] = gen_rtx_REG (<V_HALF>mode, regno + hi); operands[2] = GEN_INT (elt); - return "vmov%?.<V_sz_elem>\t%P0[%c2], %1"; + return "vmov.<V_sz_elem>\t%P0[%c2], %1"; } - [(set_attr "predicable" "yes") - (set_attr "neon_type" "neon_mcr")] + [(set_attr "neon_type" "neon_mcr")] ) (define_insn "vec_setv2di_internal" @@ -480,10 +478,9 @@ operands[0] = gen_rtx_REG (DImode, regno); - return "vmov%?\t%P0, %Q1, %R1"; + return "vmov\t%P0, %Q1, %R1"; } - [(set_attr "predicable" "yes") - (set_attr "neon_type" "neon_mcr_2_mcrr")] + [(set_attr "neon_type" "neon_mcr_2_mcrr")] ) (define_expand "vec_set<mode>" @@ -511,10 +508,9 @@ elt = GET_MODE_NUNITS (<MODE>mode) - 1 - elt; operands[2] = GEN_INT (elt); } - return "vmov%?.<V_uf_sclr>\t%0, %P1[%c2]"; + return "vmov.<V_uf_sclr>\t%0, %P1[%c2]"; } - [(set_attr "predicable" "yes") - (set_attr "neon_type" "neon_bp_simple")] + [(set_attr "neon_type" "neon_bp_simple")] ) (define_insn "vec_extract<mode>" @@ -535,10 +531,9 @@ operands[1] = gen_rtx_REG (<V_HALF>mode, regno + hi); operands[2] = GEN_INT (elt); - return "vmov%?.<V_uf_sclr>\t%0, %P1[%c2]"; + return "vmov.<V_uf_sclr>\t%0, %P1[%c2]"; } - [(set_attr "predicable" "yes") - (set_attr "neon_type" "neon_bp_simple")] + [(set_attr "neon_type" "neon_bp_simple")] ) (define_insn "vec_extractv2di" @@ -552,10 +547,9 @@ operands[1] = gen_rtx_REG (DImode, regno); - return "vmov%?\t%Q0, %R0, %P1 @ v2di"; + return "vmov\t%Q0, %R0, %P1 @ v2di"; } - [(set_attr "predicable" "yes") - (set_attr "neon_type" "neon_int_1")] + [(set_attr "neon_type" "neon_int_1")] ) (define_expand "vec_init<mode>" @@ -2622,10 +2616,9 @@ elt = GET_MODE_NUNITS (<MODE>mode) - 1 - elt; operands[2] = GEN_INT (elt); } - return "vmov%?.s<V_sz_elem>\t%0, %P1[%c2]"; + return "vmov.s<V_sz_elem>\t%0, %P1[%c2]"; } - [(set_attr "predicable" "yes") - (set_attr "neon_type" "neon_bp_simple")] + [(set_attr "neon_type" "neon_bp_simple")] ) (define_insn "neon_vget_lane<mode>_zext_internal" @@ -2642,10 +2635,9 @@ elt = GET_MODE_NUNITS (<MODE>mode) - 1 - elt; operands[2] = GEN_INT (elt); } - return "vmov%?.u<V_sz_elem>\t%0, %P1[%c2]"; + return "vmov.u<V_sz_elem>\t%0, %P1[%c2]"; } - [(set_attr "predicable" "yes") - (set_attr "neon_type" "neon_bp_simple")] + [(set_attr "neon_type" "neon_bp_simple")] ) (define_insn "neon_vget_lane<mode>_sext_internal" @@ -2668,12 +2660,11 @@ ops[0] = operands[0]; ops[1] = gen_rtx_REG (<V_HALF>mode, regno + 2 * (elt / halfelts)); ops[2] = GEN_INT (elt_adj); - output_asm_insn ("vmov%?.s<V_sz_elem>\t%0, %P1[%c2]", ops); + output_asm_insn ("vmov.s<V_sz_elem>\t%0, %P1[%c2]", ops); return ""; } - [(set_attr "predicable" "yes") - (set_attr "neon_type" "neon_bp_simple")] + [(set_attr "neon_type" "neon_bp_simple")] ) (define_insn "neon_vget_lane<mode>_zext_internal" @@ -2696,12 +2687,11 @@ ops[0] = operands[0]; ops[1] = gen_rtx_REG (<V_HALF>mode, regno + 2 * (elt / halfelts)); ops[2] = GEN_INT (elt_adj); - output_asm_insn ("vmov%?.u<V_sz_elem>\t%0, %P1[%c2]", ops); + output_asm_insn ("vmov.u<V_sz_elem>\t%0, %P1[%c2]", ops); return ""; } - [(set_attr "predicable" "yes") - (set_attr "neon_type" "neon_bp_simple")] + [(set_attr "neon_type" "neon_bp_simple")] ) (define_expand "neon_vget_lane<mode>" @@ -2832,10 +2822,9 @@ [(set (match_operand:VX 0 "s_register_operand" "=w") (vec_duplicate:VX (match_operand:<V_elem> 1 "s_register_operand" "r")))] "TARGET_NEON" - "vdup%?.<V_sz_elem>\t%<V_reg>0, %1" + "vdup.<V_sz_elem>\t%<V_reg>0, %1" ;; Assume this schedules like vmov. - [(set_attr "predicable" "yes") - (set_attr "neon_type" "neon_bp_simple")] + [(set_attr "neon_type" "neon_bp_simple")] ) (define_insn "neon_vdup_n<mode>" @@ -2843,11 +2832,10 @@ (vec_duplicate:V32 (match_operand:<V_elem> 1 "s_register_operand" "r,t")))] "TARGET_NEON" "@ - vdup%?.<V_sz_elem>\t%<V_reg>0, %1 - vdup%?.<V_sz_elem>\t%<V_reg>0, %y1" + vdup.<V_sz_elem>\t%<V_reg>0, %1 + vdup.<V_sz_elem>\t%<V_reg>0, %y1" ;; Assume this schedules like vmov. - [(set_attr "predicable" "yes") - (set_attr "neon_type" "neon_bp_simple")] + [(set_attr "neon_type" "neon_bp_simple")] ) (define_expand "neon_vdup_ndi" @@ -2865,10 +2853,9 @@ (vec_duplicate:V2DI (match_operand:DI 1 "s_register_operand" "r,w")))] "TARGET_NEON" "@ - vmov%?\t%e0, %Q1, %R1\;vmov%?\t%f0, %Q1, %R1 - vmov%?\t%e0, %P1\;vmov%?\t%f0, %P1" - [(set_attr "predicable" "yes") - (set_attr "length" "8") + vmov\t%e0, %Q1, %R1\;vmov\t%f0, %Q1, %R1 + vmov\t%e0, %P1\;vmov\t%f0, %P1" + [(set_attr "length" "8") (set_attr "neon_type" "neon_bp_simple")] )