commit bab38d9271ce3f26cb64b8cb712351eb3fedd559 Author: Kewen Lin Date: Wed Jun 26 02:16:17 2024 -0500 rs6000: Fix wrong RTL patterns for vector merge high/low short on LE Commit r12-4496 changes some define_expands and define_insns for vector merge high/low short, which are altivec_vmrg[hl]h. These defines are mainly for built-in function vec_merge{h,l} and some internal gen function needs. These functions should consider endianness, taking vec_mergeh as example, as PVIPR defines, vec_mergeh "Merges the first halves (in element order) of two vectors", it does note it's in element order. So it's mapped into vmrghh on BE while vmrglh on LE respectively. Although the mapped insns are different, as the discussion in PR106069, the RTL pattern should be still the same, it is conformed before commit r12-4496, but gets changed into different patterns on BE and LE starting from commit r12-4496. Similar to 32-bit element case in commit log of r15-1504, this 16-bit element pattern on LE doesn't actually match what the underlying insn is intended to represent, once some optimization like combine does some changes basing on it, it would cause the unexpected consequence. The newly constructed test case pr106069-2.c is a typical example for this issue on element type short. So this patch is to fix the wrong RTL pattern, ensure the associated RTL patterns become the same as before which can have the same semantic as their mapped insns. With the proposed patch, the expanders like altivec_vmrghh expands into altivec_vmrghh_direct_be or altivec_vmrglh_direct_le depending on endianness, "direct" can easily show which insn would be generated, _be and _le are mainly for the different RTL patterns as endianness. Co-authored-by: Xionghu Luo PR target/106069 PR target/115355 gcc/ChangeLog: * config/rs6000/altivec.md (altivec_vmrghh_direct): Rename to ... (altivec_vmrghh_direct_be): ... this. Add condition BYTES_BIG_ENDIAN. (altivec_vmrghh_direct_le): New define_insn. (altivec_vmrglh_direct): Rename to ... (altivec_vmrglh_direct_be): ... this. Add condition BYTES_BIG_ENDIAN. (altivec_vmrglh_direct_le): New define_insn. (altivec_vmrghh): Adjust by calling gen_altivec_vmrghh_direct_be for BE and gen_altivec_vmrglh_direct_le for LE. (altivec_vmrglh): Adjust by calling gen_altivec_vmrglh_direct_be for BE and gen_altivec_vmrghh_direct_le for LE. (vec_widen_umult_hi_v16qi): Adjust the call to gen_altivec_vmrghh_direct by gen_altivec_vmrghh for BE and by gen_altivec_vmrglh for LE. (vec_widen_smult_hi_v16qi): Likewise. (vec_widen_umult_lo_v16qi): Adjust the call to gen_altivec_vmrglh_direct by gen_altivec_vmrglh for BE and by gen_altivec_vmrghh for LE. (vec_widen_smult_lo_v16qi): Likewise. * config/rs6000/rs6000.cc (altivec_expand_vec_perm_const): Replace CODE_FOR_altivec_vmrghh_direct by CODE_FOR_altivec_vmrghh_direct_be for BE and CODE_FOR_altivec_vmrghh_direct_le for LE. And replace CODE_FOR_altivec_vmrglh_direct by CODE_FOR_altivec_vmrglh_direct_be for BE and CODE_FOR_altivec_vmrglh_direct_le for LE. gcc/testsuite/ChangeLog: * gcc.target/powerpc/pr106069-2.c: New test. (cherry picked from commit 812c70bf4981958488331d4ea5af8709b5321da1) diff --git a/gcc/config/rs6000/altivec.md b/gcc/config/rs6000/altivec.md index 47664204bc5..6557393a97c 100644 --- a/gcc/config/rs6000/altivec.md +++ b/gcc/config/rs6000/altivec.md @@ -1203,17 +1203,18 @@ (define_expand "altivec_vmrghh" (use (match_operand:V8HI 2 "register_operand"))] "TARGET_ALTIVEC" { - rtx (*fun) (rtx, rtx, rtx) = BYTES_BIG_ENDIAN ? gen_altivec_vmrghh_direct - : gen_altivec_vmrglh_direct; - if (!BYTES_BIG_ENDIAN) - std::swap (operands[1], operands[2]); - emit_insn (fun (operands[0], operands[1], operands[2])); + if (BYTES_BIG_ENDIAN) + emit_insn ( + gen_altivec_vmrghh_direct_be (operands[0], operands[1], operands[2])); + else + emit_insn ( + gen_altivec_vmrglh_direct_le (operands[0], operands[2], operands[1])); DONE; }) -(define_insn "altivec_vmrghh_direct" +(define_insn "altivec_vmrghh_direct_be" [(set (match_operand:V8HI 0 "register_operand" "=v") - (vec_select:V8HI + (vec_select:V8HI (vec_concat:V16HI (match_operand:V8HI 1 "register_operand" "v") (match_operand:V8HI 2 "register_operand" "v")) @@ -1221,7 +1222,21 @@ (define_insn "altivec_vmrghh_direct" (const_int 1) (const_int 9) (const_int 2) (const_int 10) (const_int 3) (const_int 11)])))] - "TARGET_ALTIVEC" + "TARGET_ALTIVEC && BYTES_BIG_ENDIAN" + "vmrghh %0,%1,%2" + [(set_attr "type" "vecperm")]) + +(define_insn "altivec_vmrghh_direct_le" + [(set (match_operand:V8HI 0 "register_operand" "=v") + (vec_select:V8HI + (vec_concat:V16HI + (match_operand:V8HI 2 "register_operand" "v") + (match_operand:V8HI 1 "register_operand" "v")) + (parallel [(const_int 4) (const_int 12) + (const_int 5) (const_int 13) + (const_int 6) (const_int 14) + (const_int 7) (const_int 15)])))] + "TARGET_ALTIVEC && !BYTES_BIG_ENDIAN" "vmrghh %0,%1,%2" [(set_attr "type" "vecperm")]) @@ -1344,15 +1359,16 @@ (define_expand "altivec_vmrglh" (use (match_operand:V8HI 2 "register_operand"))] "TARGET_ALTIVEC" { - rtx (*fun) (rtx, rtx, rtx) = BYTES_BIG_ENDIAN ? gen_altivec_vmrglh_direct - : gen_altivec_vmrghh_direct; - if (!BYTES_BIG_ENDIAN) - std::swap (operands[1], operands[2]); - emit_insn (fun (operands[0], operands[1], operands[2])); + if (BYTES_BIG_ENDIAN) + emit_insn ( + gen_altivec_vmrglh_direct_be (operands[0], operands[1], operands[2])); + else + emit_insn ( + gen_altivec_vmrghh_direct_le (operands[0], operands[2], operands[1])); DONE; }) -(define_insn "altivec_vmrglh_direct" +(define_insn "altivec_vmrglh_direct_be" [(set (match_operand:V8HI 0 "register_operand" "=v") (vec_select:V8HI (vec_concat:V16HI @@ -1362,7 +1378,21 @@ (define_insn "altivec_vmrglh_direct" (const_int 5) (const_int 13) (const_int 6) (const_int 14) (const_int 7) (const_int 15)])))] - "TARGET_ALTIVEC" + "TARGET_ALTIVEC && BYTES_BIG_ENDIAN" + "vmrglh %0,%1,%2" + [(set_attr "type" "vecperm")]) + +(define_insn "altivec_vmrglh_direct_le" + [(set (match_operand:V8HI 0 "register_operand" "=v") + (vec_select:V8HI + (vec_concat:V16HI + (match_operand:V8HI 2 "register_operand" "v") + (match_operand:V8HI 1 "register_operand" "v")) + (parallel [(const_int 0) (const_int 8) + (const_int 1) (const_int 9) + (const_int 2) (const_int 10) + (const_int 3) (const_int 11)])))] + "TARGET_ALTIVEC && !BYTES_BIG_ENDIAN" "vmrglh %0,%1,%2" [(set_attr "type" "vecperm")]) @@ -3777,13 +3807,13 @@ (define_expand "vec_widen_umult_hi_v16qi" { emit_insn (gen_altivec_vmuleub (ve, operands[1], operands[2])); emit_insn (gen_altivec_vmuloub (vo, operands[1], operands[2])); - emit_insn (gen_altivec_vmrghh_direct (operands[0], ve, vo)); + emit_insn (gen_altivec_vmrghh (operands[0], ve, vo)); } else { emit_insn (gen_altivec_vmuloub (ve, operands[1], operands[2])); emit_insn (gen_altivec_vmuleub (vo, operands[1], operands[2])); - emit_insn (gen_altivec_vmrghh_direct (operands[0], vo, ve)); + emit_insn (gen_altivec_vmrglh (operands[0], ve, vo)); } DONE; }) @@ -3802,13 +3832,13 @@ (define_expand "vec_widen_umult_lo_v16qi" { emit_insn (gen_altivec_vmuleub (ve, operands[1], operands[2])); emit_insn (gen_altivec_vmuloub (vo, operands[1], operands[2])); - emit_insn (gen_altivec_vmrglh_direct (operands[0], ve, vo)); + emit_insn (gen_altivec_vmrglh (operands[0], ve, vo)); } else { emit_insn (gen_altivec_vmuloub (ve, operands[1], operands[2])); emit_insn (gen_altivec_vmuleub (vo, operands[1], operands[2])); - emit_insn (gen_altivec_vmrglh_direct (operands[0], vo, ve)); + emit_insn (gen_altivec_vmrghh (operands[0], ve, vo)); } DONE; }) @@ -3827,13 +3857,13 @@ (define_expand "vec_widen_smult_hi_v16qi" { emit_insn (gen_altivec_vmulesb (ve, operands[1], operands[2])); emit_insn (gen_altivec_vmulosb (vo, operands[1], operands[2])); - emit_insn (gen_altivec_vmrghh_direct (operands[0], ve, vo)); + emit_insn (gen_altivec_vmrghh (operands[0], ve, vo)); } else { emit_insn (gen_altivec_vmulosb (ve, operands[1], operands[2])); emit_insn (gen_altivec_vmulesb (vo, operands[1], operands[2])); - emit_insn (gen_altivec_vmrghh_direct (operands[0], vo, ve)); + emit_insn (gen_altivec_vmrglh (operands[0], ve, vo)); } DONE; }) @@ -3852,13 +3882,13 @@ (define_expand "vec_widen_smult_lo_v16qi" { emit_insn (gen_altivec_vmulesb (ve, operands[1], operands[2])); emit_insn (gen_altivec_vmulosb (vo, operands[1], operands[2])); - emit_insn (gen_altivec_vmrglh_direct (operands[0], ve, vo)); + emit_insn (gen_altivec_vmrglh (operands[0], ve, vo)); } else { emit_insn (gen_altivec_vmulosb (ve, operands[1], operands[2])); emit_insn (gen_altivec_vmulesb (vo, operands[1], operands[2])); - emit_insn (gen_altivec_vmrglh_direct (operands[0], vo, ve)); + emit_insn (gen_altivec_vmrghh (operands[0], ve, vo)); } DONE; }) diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc index 10088033aa1..76eb89ad529 100644 --- a/gcc/config/rs6000/rs6000.cc +++ b/gcc/config/rs6000/rs6000.cc @@ -23170,8 +23170,8 @@ altivec_expand_vec_perm_const (rtx target, rtx op0, rtx op1, : CODE_FOR_altivec_vmrglb_direct_le, {0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23}}, {OPTION_MASK_ALTIVEC, - BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrghh_direct - : CODE_FOR_altivec_vmrglh_direct, + BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrghh_direct_be + : CODE_FOR_altivec_vmrglh_direct_le, {0, 1, 16, 17, 2, 3, 18, 19, 4, 5, 20, 21, 6, 7, 22, 23}}, {OPTION_MASK_ALTIVEC, BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrghw_direct_v4si_be @@ -23182,8 +23182,8 @@ altivec_expand_vec_perm_const (rtx target, rtx op0, rtx op1, : CODE_FOR_altivec_vmrghb_direct_le, {8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31}}, {OPTION_MASK_ALTIVEC, - BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrglh_direct - : CODE_FOR_altivec_vmrghh_direct, + BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrglh_direct_be + : CODE_FOR_altivec_vmrghh_direct_le, {8, 9, 24, 25, 10, 11, 26, 27, 12, 13, 28, 29, 14, 15, 30, 31}}, {OPTION_MASK_ALTIVEC, BYTES_BIG_ENDIAN ? CODE_FOR_altivec_vmrglw_direct_v4si_be diff --git a/gcc/testsuite/gcc.target/powerpc/pr106069-2.c b/gcc/testsuite/gcc.target/powerpc/pr106069-2.c new file mode 100644 index 00000000000..283e3290fb3 --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/pr106069-2.c @@ -0,0 +1,37 @@ +/* { dg-do run } */ +/* { dg-options "-O2" } */ +/* { dg-require-effective-target vmx_hw } */ + +/* Test vector merge for 16-bit element size, + it will abort if the RTL pattern isn't expected. */ + +#include "altivec.h" + +__attribute__((noipa)) +signed short elem_2 (vector signed short a, vector signed short b) +{ + vector signed short c = vec_mergeh (a,b); + return vec_extract (c, 2); +} + +__attribute__((noipa)) +unsigned short elem_7 (vector unsigned short a, vector unsigned short b) +{ + vector unsigned short c = vec_mergel (a,b); + return vec_extract (c, 7); +} + +int +main () +{ + vector unsigned short v1 = {3, 22, 12, 34, 5, 25, 30, 11}; + vector unsigned short v2 = {84, 168, 267, 966, 65, 399, 999, 99}; + signed short x1 = elem_2 ((vector signed short) v1, (vector signed short) v2); + unsigned short x2 = elem_7 (v1, v2); + + if (x1 != 22 || x2 != 99) + __builtin_abort (); + + return 0; +} +