The syntax for lane specifiers uses a vector element rather than a vector: fmls v0.2s, v1.2s, v1.s[1] // rather than v1.2s[2]
Fix all the lane specifiers to use Vetype which uses the correct element type. Regress&bootstrap pass. ChangeLog: 2020-03-06 Wilco Dijkstra <wdijk...@arm.com> * aarch64/aarch64-simd.md (aarch64_mla_elt<mode>): Correct lane syntax. (aarch64_mla_elt_<vswap_width_name><mode>): Likewise. (aarch64_mls_elt<mode>): Likewise. (aarch64_mls_elt_<vswap_width_name><mode>): Likewise. (aarch64_fma4_elt<mode>): Likewise. (aarch64_fma4_elt_<vswap_width_name><mode>): Likewise. (aarch64_fma4_elt_to_64v2df): Likewise. (aarch64_fnma4_elt<mode>): Likewise. (aarch64_fnma4_elt_<vswap_width_name><mode>): Likewise. (aarch64_fnma4_elt_to_64v2df): Likewise. * gcc.target/aarch64/fmla_intrinsic_1.c: Check for correct lane syntax. * gcc.target/aarch64/fmls_intrinsic_1.c: Likewise. * gcc.target/aarch64/mla_intrinsic_1.c: Likewise. * gcc.target/aarch64/mls_intrinsic_1.c: Likewise. --- diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md index 89aaf8c018e3340dd2d53fc2a6538d3d1220b103..999d80667b7cf06040515958c747d8bca0728acc 100644 --- a/gcc/config/aarch64/aarch64-simd.md +++ b/gcc/config/aarch64/aarch64-simd.md @@ -1350,7 +1350,7 @@ (define_insn "*aarch64_mla_elt<mode>" "TARGET_SIMD" { operands[2] = aarch64_endian_lane_rtx (<MODE>mode, INTVAL (operands[2])); - return "mla\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]"; + return "mla\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]"; } [(set_attr "type" "neon_mla_<Vetype>_scalar<q>")] ) @@ -1368,7 +1368,7 @@ (define_insn "*aarch64_mla_elt_<vswap_width_name><mode>" "TARGET_SIMD" { operands[2] = aarch64_endian_lane_rtx (<VSWAP_WIDTH>mode, INTVAL (operands[2])); - return "mla\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]"; + return "mla\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]"; } [(set_attr "type" "neon_mla_<Vetype>_scalar<q>")] ) @@ -1408,7 +1408,7 @@ (define_insn "*aarch64_mls_elt<mode>" "TARGET_SIMD" { operands[2] = aarch64_endian_lane_rtx (<MODE>mode, INTVAL (operands[2])); - return "mls\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]"; + return "mls\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]"; } [(set_attr "type" "neon_mla_<Vetype>_scalar<q>")] ) @@ -1426,7 +1426,7 @@ (define_insn "*aarch64_mls_elt_<vswap_width_name><mode>" "TARGET_SIMD" { operands[2] = aarch64_endian_lane_rtx (<VSWAP_WIDTH>mode, INTVAL (operands[2])); - return "mls\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]"; + return "mls\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]"; } [(set_attr "type" "neon_mla_<Vetype>_scalar<q>")] ) @@ -2003,7 +2003,7 @@ (define_insn "*aarch64_fma4_elt<mode>" "TARGET_SIMD" { operands[2] = aarch64_endian_lane_rtx (<MODE>mode, INTVAL (operands[2])); - return "fmla\\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]"; + return "fmla\\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]"; } [(set_attr "type" "neon_fp_mla_<Vetype>_scalar<q>")] ) @@ -2020,7 +2020,7 @@ (define_insn "*aarch64_fma4_elt_<vswap_width_name><mode>" "TARGET_SIMD" { operands[2] = aarch64_endian_lane_rtx (<VSWAP_WIDTH>mode, INTVAL (operands[2])); - return "fmla\\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]"; + return "fmla\\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]"; } [(set_attr "type" "neon_fp_mla_<Vetype>_scalar<q>")] ) @@ -2048,7 +2048,7 @@ (define_insn "*aarch64_fma4_elt_to_64v2df" "TARGET_SIMD" { operands[2] = aarch64_endian_lane_rtx (V2DFmode, INTVAL (operands[2])); - return "fmla\\t%0.2d, %3.2d, %1.2d[%2]"; + return "fmla\\t%0.2d, %3.2d, %1.d[%2]"; } [(set_attr "type" "neon_fp_mla_d_scalar_q")] ) @@ -2077,7 +2077,7 @@ (define_insn "*aarch64_fnma4_elt<mode>" "TARGET_SIMD" { operands[2] = aarch64_endian_lane_rtx (<MODE>mode, INTVAL (operands[2])); - return "fmls\\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]"; + return "fmls\\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]"; } [(set_attr "type" "neon_fp_mla_<Vetype>_scalar<q>")] ) @@ -2095,7 +2095,7 @@ (define_insn "*aarch64_fnma4_elt_<vswap_width_name><mode>" "TARGET_SIMD" { operands[2] = aarch64_endian_lane_rtx (<VSWAP_WIDTH>mode, INTVAL (operands[2])); - return "fmls\\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]"; + return "fmls\\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]"; } [(set_attr "type" "neon_fp_mla_<Vetype>_scalar<q>")] ) @@ -2125,7 +2125,7 @@ (define_insn "*aarch64_fnma4_elt_to_64v2df" "TARGET_SIMD" { operands[2] = aarch64_endian_lane_rtx (V2DFmode, INTVAL (operands[2])); - return "fmls\\t%0.2d, %3.2d, %1.2d[%2]"; + return "fmls\\t%0.2d, %3.2d, %1.d[%2]"; } [(set_attr "type" "neon_fp_mla_d_scalar_q")] ) diff --git a/gcc/testsuite/gcc.target/aarch64/fmla_intrinsic_1.c b/gcc/testsuite/gcc.target/aarch64/fmla_intrinsic_1.c index 5b348827002dcfef1f589900a4cf5ff7ada26697..59ad41ed0471b17418c395f31fbe666b60ec3623 100644 --- a/gcc/testsuite/gcc.target/aarch64/fmla_intrinsic_1.c +++ b/gcc/testsuite/gcc.target/aarch64/fmla_intrinsic_1.c @@ -98,11 +98,11 @@ main (int argc, char **argv) /* vfma_laneq_f32. vfma_lane_f32. */ -/* { dg-final { scan-assembler-times "fmla\\tv\[0-9\]+\.2s, v\[0-9\]+\.2s, v\[0-9\]+\.2s\\\[\[0-9\]+\\\]" 2 } } */ +/* { dg-final { scan-assembler-times "fmla\\tv\[0-9\]+\.2s, v\[0-9\]+\.2s, v\[0-9\]+\.s\\\[\[0-9\]+\\\]" 2 } } */ /* vfmaq_lane_f32. vfmaq_laneq_f32. */ -/* { dg-final { scan-assembler-times "fmla\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.4s\\\[\[0-9\]+\\\]" 2 } } */ +/* { dg-final { scan-assembler-times "fmla\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.s\\\[\[0-9\]+\\\]" 2 } } */ /* vfma_lane_f64. */ /* { dg-final { scan-assembler-times "fmadd\\td\[0-9\]+\, d\[0-9\]+\, d\[0-9\]+\, d\[0-9\]+" 1 } } */ @@ -110,6 +110,6 @@ main (int argc, char **argv) /* vfmaq_lane_f64. vfma_laneq_f64. vfmaq_laneq_f64. */ -/* { dg-final { scan-assembler-times "fmla\\tv\[0-9\]+\.2d, v\[0-9\]+\.2d, v\[0-9\]+\.2?d\\\[\[0-9\]+\\\]" 3 } } */ +/* { dg-final { scan-assembler-times "fmla\\tv\[0-9\]+\.2d, v\[0-9\]+\.2d, v\[0-9\]+\.d\\\[\[0-9\]+\\\]" 3 } } */ diff --git a/gcc/testsuite/gcc.target/aarch64/fmls_intrinsic_1.c b/gcc/testsuite/gcc.target/aarch64/fmls_intrinsic_1.c index 6c194a023d34ebafb4d732edc303985531f92a63..2d5a3d305360a08a9663cfd497cb1a5374b4b327 100644 --- a/gcc/testsuite/gcc.target/aarch64/fmls_intrinsic_1.c +++ b/gcc/testsuite/gcc.target/aarch64/fmls_intrinsic_1.c @@ -99,11 +99,11 @@ main (int argc, char **argv) /* vfms_laneq_f32. vfms_lane_f32. */ -/* { dg-final { scan-assembler-times "fmls\\tv\[0-9\]+\.2s, v\[0-9\]+\.2s, v\[0-9\]+\.2s\\\[\[0-9\]+\\\]" 2 } } */ +/* { dg-final { scan-assembler-times "fmls\\tv\[0-9\]+\.2s, v\[0-9\]+\.2s, v\[0-9\]+\.s\\\[\[0-9\]+\\\]" 2 } } */ /* vfmsq_lane_f32. vfmsq_laneq_f32. */ -/* { dg-final { scan-assembler-times "fmls\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.4s\\\[\[0-9\]+\\\]" 2 } } */ +/* { dg-final { scan-assembler-times "fmls\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.s\\\[\[0-9\]+\\\]" 2 } } */ /* vfms_lane_f64. */ /* { dg-final { scan-assembler-times "fmsub\\td\[0-9\]+\, d\[0-9\]+\, d\[0-9\]+\, d\[0-9\]+" 1 } } */ @@ -111,6 +111,6 @@ main (int argc, char **argv) /* vfmsq_lane_f64. vfms_laneq_f64. vfmsq_laneq_f64. */ -/* { dg-final { scan-assembler-times "fmls\\tv\[0-9\]+\.2d, v\[0-9\]+\.2d, v\[0-9\]+\.2?d\\\[\[0-9\]+\\\]" 3 } } */ +/* { dg-final { scan-assembler-times "fmls\\tv\[0-9\]+\.2d, v\[0-9\]+\.2d, v\[0-9\]+\.d\\\[\[0-9\]+\\\]" 3 } } */ diff --git a/gcc/testsuite/gcc.target/aarch64/mla_intrinsic_1.c b/gcc/testsuite/gcc.target/aarch64/mla_intrinsic_1.c index 4bdfac76f401c2b557e024542aa8091d985c0c1c..46b3c78c131ea92eae208d399ef25c71cd8446f7 100644 --- a/gcc/testsuite/gcc.target/aarch64/mla_intrinsic_1.c +++ b/gcc/testsuite/gcc.target/aarch64/mla_intrinsic_1.c @@ -78,6 +78,6 @@ main (int argc, char **argv) return 0; } -/* { dg-final { scan-assembler-times "mla\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.4s\\\[\[0-9\]+\\\]" 4 } } */ -/* { dg-final { scan-assembler-times "mla\\tv\[0-9\]+\.8h, v\[0-9\]+\.8h, v\[0-9\]+\.8h\\\[\[0-9\]+\\\]" 4 } } */ +/* { dg-final { scan-assembler-times "mla\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.s\\\[\[0-9\]+\\\]" 4 } } */ +/* { dg-final { scan-assembler-times "mla\\tv\[0-9\]+\.8h, v\[0-9\]+\.8h, v\[0-9\]+\.h\\\[\[0-9\]+\\\]" 4 } } */ diff --git a/gcc/testsuite/gcc.target/aarch64/mls_intrinsic_1.c b/gcc/testsuite/gcc.target/aarch64/mls_intrinsic_1.c index 4b13fafedcda813004abfc251b98bffeb6cb46e9..e01a4f6d0e1e83cac042a2cad4f02664b87e8c05 100644 --- a/gcc/testsuite/gcc.target/aarch64/mls_intrinsic_1.c +++ b/gcc/testsuite/gcc.target/aarch64/mls_intrinsic_1.c @@ -83,6 +83,6 @@ main (int argc, char **argv) return 0; } -/* { dg-final { scan-assembler-times "mls\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.4s\\\[\[0-9\]+\\\]" 4 } } */ -/* { dg-final { scan-assembler-times "mls\\tv\[0-9\]+\.8h, v\[0-9\]+\.8h, v\[0-9\]+\.8h\\\[\[0-9\]+\\\]" 4 } } */ +/* { dg-final { scan-assembler-times "mls\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.s\\\[\[0-9\]+\\\]" 4 } } */ +/* { dg-final { scan-assembler-times "mls\\tv\[0-9\]+\.8h, v\[0-9\]+\.8h, v\[0-9\]+\.h\\\[\[0-9\]+\\\]" 4 } } */