Hi, Gentle ping this: https://gcc.gnu.org/pipermail/gcc-patches/2022-June/597020.html Thanks.
On 4/7/2022 下午 2:33, HAO CHEN GUI wrote: > Hi, > Gentle ping this: > https://gcc.gnu.org/pipermail/gcc-patches/2022-June/597020.html > Thanks. > > On 22/6/2022 下午 4:26, HAO CHEN GUI wrote: >> Hi, >> This patch uses CC instead of CCFP for all BCD operations. Thus, infinite >> math flag has no impact on BCD operations. To support BCD overflow and >> invalid coding, an UNSPEC is defined to move the bit to a general register. >> The patterns of condition branch and return with overflow bit are defined as >> the UNSPEC and branch/return can be combined to one jump insn. The split >> pattern of overflow bit extension is define for optimization. >> >> This patch also replaces bcdadd with bcdsub for BCD invaliding coding >> expand. >> >> ChangeLog >> 2022-06-22 Haochen Gui <guih...@linux.ibm.com> >> >> gcc/ >> PR target/100736 >> * config/rs6000/altivec.md (BCD_TEST): Remove unordered. >> (bcd<bcd_add_sub>_<mode>): Replace CCFP with CC. >> (*bcd<bcd_add_sub>_test_<mode>): Replace CCFP with CC. Generate >> condition insn with CC mode. >> (bcd<bcd_add_sub>_overflow_<mode>): New. >> (*bcdoverflow_<mode>): New. >> (*bcdinvalid_<mode>): Removed. >> (bcdinvalid_<mode>): Implement by UNSPEC_BCDSUB and UNSPEC_BCD_OVERFLOW. >> (nuun): New. >> (*overflow_cbranch): New. >> (*overflow_creturn): New. >> (*overflow_extendsidi): New. >> (bcdshift_v16qi): Replace CCFP with CC. >> (bcdmul10_v16qi): Likewise. >> (bcddiv10_v16qi): Likewise. >> (peephole for bcd_add/sub): Likewise. >> * config/rs6000/rs6000-builtins.def (__builtin_bcdadd_ov_v1ti): Set >> pattern to bcdadd_overflow_v1ti. >> (__builtin_bcdadd_ov_v16qi): Set pattern to bcdadd_overflow_v16qi. >> (__builtin_bcdsub_ov_v1ti): Set pattern to bcdsub_overflow_v1ti. >> (__builtin_bcdsub_ov_v16qi): Set pattern to bcdsub_overflow_v16qi. >> >> gcc/testsuite/ >> PR target/100736 >> * gcc.target/powerpc/bcd-4.c: Adjust number of bcdadd and bcdsub. >> Scan no cror insns. >> >> patch.diff >> diff --git a/gcc/config/rs6000/altivec.md b/gcc/config/rs6000/altivec.md >> index efc8ae35c2e..26f131e61ea 100644 >> --- a/gcc/config/rs6000/altivec.md >> +++ b/gcc/config/rs6000/altivec.md >> @@ -4370,7 +4370,7 @@ (define_int_iterator UNSPEC_BCD_ADD_SUB [UNSPEC_BCDADD >> UNSPEC_BCDSUB]) >> (define_int_attr bcd_add_sub [(UNSPEC_BCDADD "add") >> (UNSPEC_BCDSUB "sub")]) >> >> -(define_code_iterator BCD_TEST [eq lt le gt ge unordered]) >> +(define_code_iterator BCD_TEST [eq lt le gt ge]) >> (define_mode_iterator VBCD [V1TI V16QI]) >> >> (define_insn "bcd<bcd_add_sub>_<mode>" >> @@ -4379,7 +4379,7 @@ (define_insn "bcd<bcd_add_sub>_<mode>" >> (match_operand:VBCD 2 "register_operand" "v") >> (match_operand:QI 3 "const_0_to_1_operand" "n")] >> UNSPEC_BCD_ADD_SUB)) >> - (clobber (reg:CCFP CR6_REGNO))] >> + (clobber (reg:CC CR6_REGNO))] >> "TARGET_P8_VECTOR" >> "bcd<bcd_add_sub>. %0,%1,%2,%3" >> [(set_attr "type" "vecsimple")]) >> @@ -4389,9 +4389,9 @@ (define_insn "bcd<bcd_add_sub>_<mode>" >> ;; UNORDERED test on an integer type (like V1TImode) is not defined. The >> type >> ;; probably should be one that can go in the VMX (Altivec) registers, so we >> ;; can't use DDmode or DFmode. >> -(define_insn "*bcd<bcd_add_sub>_test_<mode>" >> - [(set (reg:CCFP CR6_REGNO) >> - (compare:CCFP >> +(define_insn "bcd<bcd_add_sub>_test_<mode>" >> + [(set (reg:CC CR6_REGNO) >> + (compare:CC >> (unspec:V2DF [(match_operand:VBCD 1 "register_operand" "v") >> (match_operand:VBCD 2 "register_operand" "v") >> (match_operand:QI 3 "const_0_to_1_operand" "i")] >> @@ -4408,8 +4408,8 @@ (define_insn "*bcd<bcd_add_sub>_test2_<mode>" >> (match_operand:VBCD 2 "register_operand" "v") >> (match_operand:QI 3 "const_0_to_1_operand" "i")] >> UNSPEC_BCD_ADD_SUB)) >> - (set (reg:CCFP CR6_REGNO) >> - (compare:CCFP >> + (set (reg:CC CR6_REGNO) >> + (compare:CC >> (unspec:V2DF [(match_dup 1) >> (match_dup 2) >> (match_dup 3)] >> @@ -4502,8 +4502,8 @@ (define_insn "vclrrb" >> [(set_attr "type" "vecsimple")]) >> >> (define_expand "bcd<bcd_add_sub>_<code>_<mode>" >> - [(parallel [(set (reg:CCFP CR6_REGNO) >> - (compare:CCFP >> + [(parallel [(set (reg:CC CR6_REGNO) >> + (compare:CC >> (unspec:V2DF [(match_operand:VBCD 1 "register_operand") >> (match_operand:VBCD 2 "register_operand") >> (match_operand:QI 3 "const_0_to_1_operand")] >> @@ -4511,46 +4511,138 @@ (define_expand "bcd<bcd_add_sub>_<code>_<mode>" >> (match_dup 4))) >> (clobber (match_scratch:VBCD 5))]) >> (set (match_operand:SI 0 "register_operand") >> - (BCD_TEST:SI (reg:CCFP CR6_REGNO) >> + (BCD_TEST:SI (reg:CC CR6_REGNO) >> (const_int 0)))] >> "TARGET_P8_VECTOR" >> { >> operands[4] = CONST0_RTX (V2DFmode); >> + emit_insn (gen_bcd<bcd_add_sub>_test_<mode> (operands[0], operands[1], >> + operands[2], operands[3], >> + operands[4])); >> + >> + rtx cr6 = gen_rtx_REG (CCmode, CR6_REGNO); >> + rtx condition_rtx = gen_rtx_<CODE> (SImode, cr6, const0_rtx); >> + >> + if (<CODE> == GE || <CODE> == LE) >> + { >> + rtx not_result = gen_reg_rtx (CCEQmode); >> + rtx not_op, rev_cond_rtx; >> + rev_cond_rtx = gen_rtx_fmt_ee (rs6000_reverse_condition (SImode, >> <CODE>), >> + SImode, XEXP (condition_rtx, 0), >> + const0_rtx); >> + not_op = gen_rtx_COMPARE (CCEQmode, rev_cond_rtx, const0_rtx); >> + emit_insn (gen_rtx_SET (not_result, not_op)); >> + condition_rtx = gen_rtx_EQ (SImode, not_result, const0_rtx); >> + } >> + >> + emit_insn (gen_rtx_SET (operands[0], condition_rtx)); >> + DONE; >> }) >> >> -(define_insn "*bcdinvalid_<mode>" >> - [(set (reg:CCFP CR6_REGNO) >> - (compare:CCFP >> - (unspec:V2DF [(match_operand:VBCD 1 "register_operand" "v")] >> - UNSPEC_BCDADD) >> - (match_operand:V2DF 2 "zero_constant" "j"))) >> - (clobber (match_scratch:VBCD 0 "=v"))] >> +(define_expand "bcd<bcd_add_sub>_overflow_<mode>" >> + [(parallel [(set (reg:CC CR6_REGNO) >> + (compare:CC >> + (unspec:V2DF [(match_operand:VBCD 1 "register_operand") >> + (match_operand:VBCD 2 "register_operand") >> + (match_operand:QI 3 "const_0_to_1_operand")] >> + UNSPEC_BCD_ADD_SUB) >> + (match_dup 4))) >> + (clobber (match_scratch:VBCD 5))]) >> + (set (match_operand:SI 0 "register_operand") >> + (unspec:SI [(reg:CC CR6_REGNO) >> + (const_int 0)] >> + UNSPEC_BCD_OVERFLOW))] >> "TARGET_P8_VECTOR" >> - "bcdadd. %0,%1,%1,0" >> +{ >> + operands[4] = CONST0_RTX (V2DFmode); >> +}) >> + >> +(define_insn "*bcdoverflow_<mode>" >> + [(set (match_operand:SDI 0 "register_operand" "=r") >> + (unspec:SDI [(reg:CC CR6_REGNO) >> + (const_int 0)] >> + UNSPEC_BCD_OVERFLOW))] >> + "TARGET_P8_VECTOR" >> + "mfcr %0,2\;rlwinm %0,%0,28,1" >> [(set_attr "type" "vecsimple")]) >> >> (define_expand "bcdinvalid_<mode>" >> - [(parallel [(set (reg:CCFP CR6_REGNO) >> - (compare:CCFP >> - (unspec:V2DF [(match_operand:VBCD 1 "register_operand")] >> - UNSPEC_BCDADD) >> + [(parallel [(set (reg:CC CR6_REGNO) >> + (compare:CC >> + (unspec:V2DF [(match_operand:VBCD 1 "register_operand") >> + (match_dup 1) >> + (const_int 0)] >> + UNSPEC_BCDSUB) >> (match_dup 2))) >> (clobber (match_scratch:VBCD 3))]) >> (set (match_operand:SI 0 "register_operand") >> - (unordered:SI (reg:CCFP CR6_REGNO) >> - (const_int 0)))] >> + (unspec:SI [(reg:CC CR6_REGNO) >> + (const_int 0)] >> + UNSPEC_BCD_OVERFLOW))] >> "TARGET_P8_VECTOR" >> { >> operands[2] = CONST0_RTX (V2DFmode); >> }) >> >> +(define_code_attr nuun [(eq "nu") >> + (ne "un")]) >> + >> +(define_insn "*overflow_cbranch" >> + [(set (pc) >> + (if_then_else (eqne >> + (unspec:SI [(reg:CC CR6_REGNO) >> + (const_int 0)] >> + UNSPEC_BCD_OVERFLOW) >> + (const_int 0)) >> + (label_ref (match_operand 0)) >> + (pc)))] >> + "TARGET_P8_VECTOR" >> + "b<nuun> 6,%l0" >> + [(set_attr "type" "branch") >> + (set (attr "length") >> + (if_then_else (and (ge (minus (match_dup 0) (pc)) >> + (const_int -32768)) >> + (lt (minus (match_dup 0) (pc)) >> + (const_int 32764))) >> + (const_int 4) >> + (const_int 8)))]) >> + >> +(define_insn "*overflow_creturn" >> + [(set (pc) >> + (if_then_else (eqne >> + (unspec:SI [(reg:CC CR6_REGNO) >> + (const_int 0)] >> + UNSPEC_BCD_OVERFLOW) >> + (const_int 0)) >> + (simple_return) >> + (pc)))] >> + "TARGET_P8_VECTOR" >> + "b<nuun>lr 6" >> + [(set_attr "type" "jmpreg")]) >> + >> +(define_insn_and_split "*overflow_extendsidi" >> + [(set (match_operand:DI 0 "gpc_reg_operand" "=r") >> + (sign_extend:DI >> + (unspec:SI [(reg:CC CR6_REGNO) >> + (const_int 0)] >> + UNSPEC_BCD_OVERFLOW)))] >> + "TARGET_P8_VECTOR" >> + "#" >> + "&& 1" >> + [(set (match_operand:DI 0 "gpc_reg_operand" "=r") >> + (unspec:DI [(reg:CC CR6_REGNO) >> + (const_int 0)] >> + UNSPEC_BCD_OVERFLOW))] >> + "" >> + [(set_attr "type" "vecsimple")]) >> + >> (define_insn "bcdshift_v16qi" >> [(set (match_operand:V16QI 0 "register_operand" "=v") >> (unspec:V16QI [(match_operand:V16QI 1 "register_operand" "v") >> (match_operand:V16QI 2 "register_operand" "v") >> (match_operand:QI 3 "const_0_to_1_operand" "n")] >> UNSPEC_BCDSHIFT)) >> - (clobber (reg:CCFP CR6_REGNO))] >> + (clobber (reg:CC CR6_REGNO))] >> "TARGET_P8_VECTOR" >> "bcds. %0,%1,%2,%3" >> [(set_attr "type" "vecsimple")]) >> @@ -4559,7 +4651,7 @@ (define_expand "bcdmul10_v16qi" >> [(set (match_operand:V16QI 0 "register_operand") >> (unspec:V16QI [(match_operand:V16QI 1 "register_operand")] >> UNSPEC_BCDSHIFT)) >> - (clobber (reg:CCFP CR6_REGNO))] >> + (clobber (reg:CC CR6_REGNO))] >> "TARGET_P9_VECTOR" >> { >> rtx one = gen_reg_rtx (V16QImode); >> @@ -4574,7 +4666,7 @@ (define_expand "bcddiv10_v16qi" >> [(set (match_operand:V16QI 0 "register_operand") >> (unspec:V16QI [(match_operand:V16QI 1 "register_operand")] >> UNSPEC_BCDSHIFT)) >> - (clobber (reg:CCFP CR6_REGNO))] >> + (clobber (reg:CC CR6_REGNO))] >> "TARGET_P9_VECTOR" >> { >> rtx one = gen_reg_rtx (V16QImode); >> @@ -4598,9 +4690,9 @@ (define_peephole2 >> (match_operand:V1TI 2 "register_operand") >> (match_operand:QI 3 "const_0_to_1_operand")] >> UNSPEC_BCD_ADD_SUB)) >> - (clobber (reg:CCFP CR6_REGNO))]) >> - (parallel [(set (reg:CCFP CR6_REGNO) >> - (compare:CCFP >> + (clobber (reg:CC CR6_REGNO))]) >> + (parallel [(set (reg:CC CR6_REGNO) >> + (compare:CC >> (unspec:V2DF [(match_dup 1) >> (match_dup 2) >> (match_dup 3)] >> @@ -4613,8 +4705,8 @@ (define_peephole2 >> (match_dup 2) >> (match_dup 3)] >> UNSPEC_BCD_ADD_SUB)) >> - (set (reg:CCFP CR6_REGNO) >> - (compare:CCFP >> + (set (reg:CC CR6_REGNO) >> + (compare:CC >> (unspec:V2DF [(match_dup 1) >> (match_dup 2) >> (match_dup 3)] >> diff --git a/gcc/config/rs6000/rs6000-builtins.def >> b/gcc/config/rs6000/rs6000-builtins.def >> index f4a9f24bcc5..8e94fe5c438 100644 >> --- a/gcc/config/rs6000/rs6000-builtins.def >> +++ b/gcc/config/rs6000/rs6000-builtins.def >> @@ -2371,10 +2371,10 @@ >> BCDADD_LT_V16QI bcdadd_lt_v16qi {} >> >> const signed int __builtin_bcdadd_ov_v1ti (vsq, vsq, const int<1>); >> - BCDADD_OV_V1TI bcdadd_unordered_v1ti {} >> + BCDADD_OV_V1TI bcdadd_overflow_v1ti {} >> >> const signed int __builtin_bcdadd_ov_v16qi (vsc, vsc, const int<1>); >> - BCDADD_OV_V16QI bcdadd_unordered_v16qi {} >> + BCDADD_OV_V16QI bcdadd_overflow_v16qi {} >> >> const signed int __builtin_bcdinvalid_v1ti (vsq); >> BCDINVALID_V1TI bcdinvalid_v1ti {} >> @@ -2419,10 +2419,10 @@ >> BCDSUB_LT_V16QI bcdsub_lt_v16qi {} >> >> const signed int __builtin_bcdsub_ov_v1ti (vsq, vsq, const int<1>); >> - BCDSUB_OV_V1TI bcdsub_unordered_v1ti {} >> + BCDSUB_OV_V1TI bcdsub_overflow_v1ti {} >> >> const signed int __builtin_bcdsub_ov_v16qi (vsc, vsc, const int<1>); >> - BCDSUB_OV_V16QI bcdsub_unordered_v16qi {} >> + BCDSUB_OV_V16QI bcdsub_overflow_v16qi {} >> >> const vuc __builtin_crypto_vpermxor_v16qi (vuc, vuc, vuc); >> VPERMXOR_V16QI crypto_vpermxor_v16qi {} >> diff --git a/gcc/testsuite/gcc.target/powerpc/bcd-4.c >> b/gcc/testsuite/gcc.target/powerpc/bcd-4.c >> index 2c8554dfe82..3c25ed60e17 100644 >> --- a/gcc/testsuite/gcc.target/powerpc/bcd-4.c >> +++ b/gcc/testsuite/gcc.target/powerpc/bcd-4.c >> @@ -2,10 +2,11 @@ >> /* { dg-require-effective-target int128 } */ >> /* { dg-require-effective-target power10_hw } */ >> /* { dg-options "-mdejagnu-cpu=power10 -O2 -save-temps" } */ >> -/* { dg-final { scan-assembler-times {\mbcdadd\M} 7 } } */ >> -/* { dg-final { scan-assembler-times {\mbcdsub\M} 18 } } */ >> +/* { dg-final { scan-assembler-times {\mbcdadd\M} 5 } } */ >> +/* { dg-final { scan-assembler-times {\mbcdsub\M} 20 } } */ >> /* { dg-final { scan-assembler-times {\mbcds\M} 2 } } */ >> /* { dg-final { scan-assembler-times {\mdenbcdq\M} 1 } } */ >> +/* { dg-final { scan-assembler-not {\mcror\M} 1 } } */ >> >> #include <altivec.h> >>