From: Michael Meissner Date: Wed, 7 Jul 2021 16:01:37 +0000 (-0400) Subject: Backport IEEE 128-bit min/max code. X-Git-Tag: releases/gcc-11.2.0~101 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=2d09824484a8bf9c6d101c9b8402d233e32b96c0;p=thirdparty%2Fgcc.git Backport IEEE 128-bit min/max code. This patch back ports 2 IEEE 128-bit min/max patches from the trunk to GCC 11. One patch is from June 30th, 2021, and the other from July 1st, 2021. 2021-07-07 Michael Meissner gcc/ * config/rs6000/rs6000.c (rs6000_maybe_emit_fp_cmove): Add IEEE 128-bit floating point conditional move support. (have_compare_and_set_mask): Add IEEE 128-bit floating point types. * config/rs6000/rs6000.md (movcc, IEEE128 iterator): New insn. (movcc_p10, IEEE128 iterator): New insn. (movcc_invert_p10, IEEE128 iterator): New insn. (fpmask, IEEE128 iterator): New insn. (xxsel, IEEE128 iterator): New insn. Backported from master: 2021-07-01 Michael Meissner gcc/testsuite/ * gcc.target/powerpc/float128-cmove.c: New test. * gcc.target/powerpc/float128-minmax-3.c: New test. Backported from master: 2021-07-01 Michael Meissner gcc/testsuite/ * gcc.target/powerpc/float128-minmax.c: Adjust expected code for power10. * lib/target-supports.exp (check_effective_target_has_arch_pwr10): New. Backported from master: 2021-06-30 Michael Meissner --- diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c index 964777349b37..91cd31cc95f3 100644 --- a/gcc/config/rs6000/rs6000.c +++ b/gcc/config/rs6000/rs6000.c @@ -15725,8 +15725,8 @@ rs6000_emit_vector_cond_expr (rtx dest, rtx op_true, rtx op_false, return 1; } -/* Possibly emit the xsmaxcdp and xsmincdp instructions to emit a maximum or - minimum with "C" semantics. +/* Possibly emit the xsmaxc{dp,qp} and xsminc{dp,qp} instructions to emit a + maximum or minimum with "C" semantics. Unless you use -ffast-math, you can't use these instructions to replace conditions that implicitly reverse the condition because the comparison @@ -15802,6 +15802,7 @@ rs6000_maybe_emit_fp_cmove (rtx dest, rtx op, rtx true_cond, rtx false_cond) enum rtx_code code = GET_CODE (op); rtx op0 = XEXP (op, 0); rtx op1 = XEXP (op, 1); + machine_mode compare_mode = GET_MODE (op0); machine_mode result_mode = GET_MODE (dest); rtx compare_rtx; rtx cmove_rtx; @@ -15810,6 +15811,29 @@ rs6000_maybe_emit_fp_cmove (rtx dest, rtx op, rtx true_cond, rtx false_cond) if (!can_create_pseudo_p ()) return 0; + /* We allow the comparison to be either SFmode/DFmode and the true/false + condition to be either SFmode/DFmode. I.e. we allow: + + float a, b; + double c, d, r; + + r = (a == b) ? c : d; + + and: + + double a, b; + float c, d, r; + + r = (a == b) ? c : d; + + but we don't allow intermixing the IEEE 128-bit floating point types with + the 32/64-bit scalar types. */ + + if (!(compare_mode == result_mode + || (compare_mode == SFmode && result_mode == DFmode) + || (compare_mode == DFmode && result_mode == SFmode))) + return false; + switch (code) { case EQ: @@ -15862,6 +15886,10 @@ have_compare_and_set_mask (machine_mode mode) case E_DFmode: return TARGET_P9_MINMAX; + case E_KFmode: + case E_TFmode: + return TARGET_POWER10 && TARGET_FLOAT128_HW && FLOAT128_IEEE_P (mode); + default: break; } diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md index 66067abb78c0..18c4a96b4dda 100644 --- a/gcc/config/rs6000/rs6000.md +++ b/gcc/config/rs6000/rs6000.md @@ -5449,6 +5449,112 @@ "xxsel %x0,%x4,%x3,%x1" [(set_attr "type" "vecmove")]) +;; Support for ISA 3.1 IEEE 128-bit conditional move. The mode used in the +;; comparison must be the same as used in the move. +(define_expand "movcc" + [(set (match_operand:IEEE128 0 "gpc_reg_operand") + (if_then_else:IEEE128 (match_operand 1 "comparison_operator") + (match_operand:IEEE128 2 "gpc_reg_operand") + (match_operand:IEEE128 3 "gpc_reg_operand")))] + "TARGET_POWER10 && TARGET_FLOAT128_HW && FLOAT128_IEEE_P (mode)" +{ + if (rs6000_emit_cmove (operands[0], operands[1], operands[2], operands[3])) + DONE; + else + FAIL; +}) + +(define_insn_and_split "*movcc_p10" + [(set (match_operand:IEEE128 0 "altivec_register_operand" "=&v,v") + (if_then_else:IEEE128 + (match_operator:CCFP 1 "fpmask_comparison_operator" + [(match_operand:IEEE128 2 "altivec_register_operand" "v,v") + (match_operand:IEEE128 3 "altivec_register_operand" "v,v")]) + (match_operand:IEEE128 4 "altivec_register_operand" "v,v") + (match_operand:IEEE128 5 "altivec_register_operand" "v,v"))) + (clobber (match_scratch:V2DI 6 "=0,&v"))] + "TARGET_POWER10 && TARGET_FLOAT128_HW && FLOAT128_IEEE_P (mode)" + "#" + "&& 1" + [(set (match_dup 6) + (if_then_else:V2DI (match_dup 1) + (match_dup 7) + (match_dup 8))) + (set (match_dup 0) + (if_then_else:IEEE128 (ne (match_dup 6) + (match_dup 8)) + (match_dup 4) + (match_dup 5)))] +{ + if (GET_CODE (operands[6]) == SCRATCH) + operands[6] = gen_reg_rtx (V2DImode); + + operands[7] = CONSTM1_RTX (V2DImode); + operands[8] = CONST0_RTX (V2DImode); +} + [(set_attr "length" "8") + (set_attr "type" "vecperm")]) + +;; Handle inverting the fpmask comparisons. +(define_insn_and_split "*movcc_invert_p10" + [(set (match_operand:IEEE128 0 "altivec_register_operand" "=&v,v") + (if_then_else:IEEE128 + (match_operator:CCFP 1 "invert_fpmask_comparison_operator" + [(match_operand:IEEE128 2 "altivec_register_operand" "v,v") + (match_operand:IEEE128 3 "altivec_register_operand" "v,v")]) + (match_operand:IEEE128 4 "altivec_register_operand" "v,v") + (match_operand:IEEE128 5 "altivec_register_operand" "v,v"))) + (clobber (match_scratch:V2DI 6 "=0,&v"))] + "TARGET_POWER10 && TARGET_FLOAT128_HW && FLOAT128_IEEE_P (mode)" + "#" + "&& 1" + [(set (match_dup 6) + (if_then_else:V2DI (match_dup 9) + (match_dup 7) + (match_dup 8))) + (set (match_dup 0) + (if_then_else:IEEE128 (ne (match_dup 6) + (match_dup 8)) + (match_dup 5) + (match_dup 4)))] +{ + rtx op1 = operands[1]; + enum rtx_code cond = reverse_condition_maybe_unordered (GET_CODE (op1)); + + if (GET_CODE (operands[6]) == SCRATCH) + operands[6] = gen_reg_rtx (V2DImode); + + operands[7] = CONSTM1_RTX (V2DImode); + operands[8] = CONST0_RTX (V2DImode); + + operands[9] = gen_rtx_fmt_ee (cond, CCFPmode, operands[2], operands[3]); +} + [(set_attr "length" "8") + (set_attr "type" "vecperm")]) + +(define_insn "*fpmask" + [(set (match_operand:V2DI 0 "altivec_register_operand" "=v") + (if_then_else:V2DI + (match_operator:CCFP 1 "fpmask_comparison_operator" + [(match_operand:IEEE128 2 "altivec_register_operand" "v") + (match_operand:IEEE128 3 "altivec_register_operand" "v")]) + (match_operand:V2DI 4 "all_ones_constant" "") + (match_operand:V2DI 5 "zero_constant" "")))] + "TARGET_POWER10 && TARGET_FLOAT128_HW && FLOAT128_IEEE_P (mode)" + "xscmp%V1qp %0,%2,%3" + [(set_attr "type" "fpcompare")]) + +(define_insn "*xxsel" + [(set (match_operand:IEEE128 0 "altivec_register_operand" "=v") + (if_then_else:IEEE128 + (ne (match_operand:V2DI 1 "altivec_register_operand" "v") + (match_operand:V2DI 2 "zero_constant" "")) + (match_operand:IEEE128 3 "altivec_register_operand" "v") + (match_operand:IEEE128 4 "altivec_register_operand" "v")))] + "TARGET_POWER10 && TARGET_FLOAT128_HW && FLOAT128_IEEE_P (mode)" + "xxsel %x0,%x4,%x3,%x1" + [(set_attr "type" "vecmove")]) + ;; Conversions to and from floating-point. diff --git a/gcc/testsuite/gcc.target/powerpc/float128-cmove.c b/gcc/testsuite/gcc.target/powerpc/float128-cmove.c new file mode 100644 index 000000000000..2fae8dc23bcf --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/float128-cmove.c @@ -0,0 +1,58 @@ +/* { dg-do compile } */ +/* { dg-require-effective-target ppc_float128_hw } */ +/* { dg-require-effective-target power10_ok } */ +/* { dg-options "-mdejagnu-cpu=power10 -O2" } */ + +#ifndef TYPE +#ifdef __LONG_DOUBLE_IEEE128__ +#define TYPE long double + +#else +#define TYPE _Float128 +#endif +#endif + +/* Verify that the ISA 3.1 (power10) IEEE 128-bit conditional move instructions + are generated. */ + +TYPE +eq (TYPE a, TYPE b, TYPE c, TYPE d) +{ + return (a == b) ? c : d; +} + +TYPE +ne (TYPE a, TYPE b, TYPE c, TYPE d) +{ + return (a != b) ? c : d; +} + +TYPE +lt (TYPE a, TYPE b, TYPE c, TYPE d) +{ + return (a < b) ? c : d; +} + +TYPE +le (TYPE a, TYPE b, TYPE c, TYPE d) +{ + return (a <= b) ? c : d; +} + +TYPE +gt (TYPE a, TYPE b, TYPE c, TYPE d) +{ + return (a > b) ? c : d; +} + +TYPE +ge (TYPE a, TYPE b, TYPE c, TYPE d) +{ + return (a >= b) ? c : d; +} + +/* { dg-final { scan-assembler-times {\mxscmpeqqp\M} 2 } } */ +/* { dg-final { scan-assembler-times {\mxscmpgeqp\M} 2 } } */ +/* { dg-final { scan-assembler-times {\mxscmpgtqp\M} 2 } } */ +/* { dg-final { scan-assembler-times {\mxxsel\M} 6 } } */ +/* { dg-final { scan-assembler-not {\mxscmpuqp\M} } } */ diff --git a/gcc/testsuite/gcc.target/powerpc/float128-minmax-3.c b/gcc/testsuite/gcc.target/powerpc/float128-minmax-3.c new file mode 100644 index 000000000000..6f7627c0f2a1 --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/float128-minmax-3.c @@ -0,0 +1,15 @@ +/* { dg-require-effective-target ppc_float128_hw } */ +/* { dg-require-effective-target power10_ok } */ +/* { dg-options "-mdejagnu-cpu=power10 -O2" } */ + +#ifndef TYPE +#define TYPE _Float128 +#endif + +/* Test that the fminf128/fmaxf128 functions generate if/then/else and not a + call. */ +TYPE f128_min (TYPE a, TYPE b) { return (a < b) ? a : b; } +TYPE f128_max (TYPE a, TYPE b) { return (b > a) ? b : a; } + +/* { dg-final { scan-assembler {\mxsmaxcqp\M} } } */ +/* { dg-final { scan-assembler {\mxsmincqp\M} } } */ diff --git a/gcc/testsuite/gcc.target/powerpc/float128-minmax.c b/gcc/testsuite/gcc.target/powerpc/float128-minmax.c index fe397518f2f5..ef8f729d9c28 100644 --- a/gcc/testsuite/gcc.target/powerpc/float128-minmax.c +++ b/gcc/testsuite/gcc.target/powerpc/float128-minmax.c @@ -1,6 +1,4 @@ -/* { dg-do compile { target lp64 } } */ -/* { dg-require-effective-target powerpc_p9vector_ok } */ -/* { dg-require-effective-target float128 } */ +/* { dg-require-effective-target ppc_float128_hw } */ /* { dg-options "-mpower9-vector -O2 -ffast-math" } */ #ifndef TYPE @@ -12,5 +10,8 @@ TYPE f128_min (TYPE a, TYPE b) { return __builtin_fminf128 (a, b); } TYPE f128_max (TYPE a, TYPE b) { return __builtin_fmaxf128 (a, b); } -/* { dg-final { scan-assembler {\mxscmpuqp\M} } } */ -/* { dg-final { scan-assembler-not {\mbl\M} } } */ +/* Adjust code power10 which has native min/max instructions. */ +/* { dg-final { scan-assembler-times {\mxscmpuqp\M} 2 { target { ! has_arch_pwr10 } } } } */ +/* { dg-final { scan-assembler-times {\mxsmincqp\M} 1 { target has_arch_pwr10 } } } */ +/* { dg-final { scan-assembler-times {\mxsmaxcqp\M} 1 { target has_arch_pwr10 } } } */ +/* { dg-final { scan-assembler-not {\mbl\M} } } */ diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp index ad323107f2ec..411e559f5088 100644 --- a/gcc/testsuite/lib/target-supports.exp +++ b/gcc/testsuite/lib/target-supports.exp @@ -6100,6 +6100,16 @@ proc check_effective_target_has_arch_pwr9 { } { }] } +proc check_effective_target_has_arch_pwr10 { } { + return [check_no_compiler_messages arch_pwr10 assembly { + #ifndef _ARCH_PWR10 + #error does not have power10 support. + #else + /* "has power10 support" */ + #endif + }] +} + # Return 1 if this is a PowerPC target supporting -mcpu=power10. # Limit this to 64-bit linux systems for now until other targets support # power10.