Hi Carl,
on 2023/8/25 03:53, Carl Love wrote:
> GCC maintainers:
>
> Version 3, fixed the built-in instance names. Missed removing the "n"
> the name. Added the tighter constraints on the predicates for the
> define_insn. Updated the wording for the built-ins in the
> documentation file. Changed the test file name again. Updated the
> ChangeLog file, added the PR target line. Retested the patch on Power
> 10LE and Power 8 and Power 9.
>
> Version 2, renamed the built-in instances. Changed the name of the
> overloaded built-in. Added the missing documentation for the new
> built-ins. Fixed typos. Changed name of the test. Updated the
> effective target for the test. Retested the patch on Power 10LE and
> Power 8 and Power 9.
>
> The following patch adds four built-ins for the decimal floating point
> (DFP) quantize instructions on rs6000. The built-ins are for 64-bit
> and 128-bit DFP operands.
>
> The patch also adds a test case for the new builtins.
>
> The Patch has been tested on Power 10LE and Power 9 LE/BE.
>
> Please let me know if the patch is acceptable for mainline. Thanks.
>
> Carl Love
>
>
> -------------------------------------------
> rs6000, add overloaded DFP quantize support
>
> Add decimal floating point (DFP) quantize built-ins for both 64-bit DFP
> and 128-DFP operands. In each case, there is an immediate version and a
> variable version of the built-in. The RM value is a 2-bit constant int
> which specifies the rounding mode to use. For the immediate versions of
> the built-in, the TE field is a 5-bit constant that specifies the value of
> the ideal exponent for the result. The built-in specifications are:
>
> __Decimal64 builtin_dfp_quantize (_Decimal64, _Decimal64,
> const int RM)
> __Decimal64 builtin_dfp_quantize (const int TE, _Decimal64,
> const int RM)
> __Decimal128 builtin_dfp_quantize (_Decimal128, _Decimal128,
> const int RM)
> __Decimal128 builtin_dfp_quantize (const int TE, _Decimal128,
> const int RM)
>
> A testcase is added for the new built-in definitions.
>
> gcc/ChangeLog:
> * config/rs6000/dfp.md: New UNSPEC_DQUAN.
Nit: (UNSPEC_DQUAN): New unspec.
> (dfp_dqua_<mode>, dfp_dqua_i<mode>): New define_insn.
> * config/rs6000/rs6000-builtins.def (__builtin_dfp_dqua,
> __builtin_dfp_dquai, __builtin_dfp_dquaq, __builtin_dfp_dquaqi):
> New buit-in definitions.
> * config/rs6000/rs6000-overload.def (__builtin_dfp_quantize): New
> overloaded definition.
> * doc/extend.texi: Add documentation for __builtin_dfp_quantize.
>
> gcc/testsuite/
> * gcc.target/powerpc/pr93448.c: New test case.
>
> PR target/93448
> ---
> gcc/config/rs6000/dfp.md | 25 ++-
> gcc/config/rs6000/rs6000-builtins.def | 15 ++
> gcc/config/rs6000/rs6000-overload.def | 10 ++
> gcc/doc/extend.texi | 17 ++
> gcc/testsuite/gcc.target/powerpc/pr93448.c | 200 +++++++++++++++++++++
> 5 files changed, 266 insertions(+), 1 deletion(-)
> create mode 100644 gcc/testsuite/gcc.target/powerpc/pr93448.c
>
> diff --git a/gcc/config/rs6000/dfp.md b/gcc/config/rs6000/dfp.md
> index 5ed8a73ac51..052dc0946d3 100644
> --- a/gcc/config/rs6000/dfp.md
> +++ b/gcc/config/rs6000/dfp.md
> @@ -271,7 +271,8 @@ (define_c_enum "unspec"
> UNSPEC_DIEX
> UNSPEC_DSCLI
> UNSPEC_DTSTSFI
> - UNSPEC_DSCRI])
> + UNSPEC_DSCRI
> + UNSPEC_DQUAN])
>
> (define_code_iterator DFP_TEST [eq lt gt unordered])
>
> @@ -395,3 +396,25 @@ (define_insn "dfp_dscri_<mode>"
> "dscri<q> %0,%1,%2"
> [(set_attr "type" "dfp")
> (set_attr "size" "<bits>")])
> +
> +(define_insn "dfp_dqua_<mode>"
> + [(set (match_operand:DDTD 0 "gpc_reg_operand" "=d")
> + (unspec:DDTD [(match_operand:DDTD 1 "gpc_reg_operand" "d")
> + (match_operand:DDTD 2 "gpc_reg_operand" "d")
> + (match_operand:SI 3 "const_0_to_3_operand" "n")]
> + UNSPEC_DQUAN))]
> + "TARGET_DFP"
> + "dqua<q> %0,%1,%2,%3"
> + [(set_attr "type" "dfp")
> + (set_attr "size" "<bits>")])
> +
> +(define_insn "dfp_dqua_i<mode>"
Sorry for nitpicking, but what I suggested previously was "dfp_dquai_"
instead of "dfp_dqua_i", "dquai" matches the according mnemonic so it's
read better, i<mode> expands to "idd" and "itd" that look odd to me.
Do you agree "dquai" is better? If yes, the changelog and the related
expanders need to be updated as well.
The others look good to me, thanks!
BR,
Kewen
> + [(set (match_operand:DDTD 0 "gpc_reg_operand" "=d")
> + (unspec:DDTD [(match_operand:SI 1 "s5bit_cint_operand" "n")
> + (match_operand:DDTD 2 "gpc_reg_operand" "d")
> + (match_operand:SI 3 "const_0_to_3_operand" "n")]
> + UNSPEC_DQUAN))]
> + "TARGET_DFP"
> + "dquai<q> %1,%0,%2,%3"
> + [(set_attr "type" "dfp")
> + (set_attr "size" "<bits>")])
> diff --git a/gcc/config/rs6000/rs6000-builtins.def
> b/gcc/config/rs6000/rs6000-builtins.def
> index 8a294d6c934..81a0de88b9c 100644
> --- a/gcc/config/rs6000/rs6000-builtins.def
> +++ b/gcc/config/rs6000/rs6000-builtins.def
> @@ -2983,6 +2983,21 @@
> const unsigned long long __builtin_unpack_dec128 (_Decimal128, const
> int<1>);
> UNPACK_TD unpacktd {}
>
> + const _Decimal64 __builtin_dfp_dqua (_Decimal64, _Decimal64, \
> + const int<2>);
> + DFPQUAN_64 dfp_dqua_dd {}
> +
> + const _Decimal64 __builtin_dfp_dquai (const int<5>, _Decimal64, \
> + const int<2>);
> + DFPQUAN_64i dfp_dqua_idd {}
> +
> + const _Decimal128 __builtin_dfp_dquaq (_Decimal128, _Decimal128, \
> + const int<2>);
> + DFPQUAN_128 dfp_dqua_td {}
> +
> + const _Decimal128 __builtin_dfp_dquaqi (const int<5>, _Decimal128, \
> + const int<2>);
> + DFPQUAN_128i dfp_dqua_itd {}
>
> [crypto]
> const vull __builtin_crypto_vcipher (vull, vull);
> diff --git a/gcc/config/rs6000/rs6000-overload.def
> b/gcc/config/rs6000/rs6000-overload.def
> index b83946f5ad8..38d92fcf1f0 100644
> --- a/gcc/config/rs6000/rs6000-overload.def
> +++ b/gcc/config/rs6000/rs6000-overload.def
> @@ -195,6 +195,16 @@
> unsigned long long __builtin_cmpb (unsigned long long, unsigned long long);
> CMPB
>
> +[DFPQUAN, dfp_quantize, __builtin_dfp_quantize]
> + _Decimal64 __builtin_dfp_quantize (_Decimal64, _Decimal64, const int);
> + DFPQUAN_64
> + _Decimal64 __builtin_dfp_quantize (const int, _Decimal64, const int);
> + DFPQUAN_64i
> + _Decimal128 __builtin_dfp_quantize (_Decimal128, _Decimal128, const int);
> + DFPQUAN_128
> + _Decimal128 __builtin_dfp_quantize (const int, _Decimal128, const int);
> + DFPQUAN_128i
> +
> [VEC_ABS, vec_abs, __builtin_vec_abs]
> vsc __builtin_vec_abs (vsc);
> ABS_V16QI
> diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
> index 73a997276cb..8d7a1116cd9 100644
> --- a/gcc/doc/extend.texi
> +++ b/gcc/doc/extend.texi
> @@ -18566,6 +18566,23 @@ The builtin uses the ISA 3.0 instruction
> @code{mffscdrn} if available.
> Otherwise the builtin reads the FPSCR, masks the current decimal rounding
> mode bits out and OR's in the new value.
>
> +_Decimal64 __builtin_dfp_quantize (_Decimal64, _Decimal64, const int);
> +_Decimal64 __builtin_dfp_quantize (const int, _Decimal64, const int);
> +_Decimal128 __builtin_dfp_quantize (_Decimal128, _Decimal128, const int);
> +_Decimal128 __builtin_dfp_quantize (const int, _Decimal128, const int);
> +
> +The @code{__builtin_dfp_quantize} built-in, converts and rounds the second
> +argument to the form with the exponent as specified by the first
> +argument based on the rounding mode specified by the third argument.
> +If the first argument is a decimal floating point value, its exponent is used
> +for converting and rounding of the second argument. If the first argument
> is a
> +5-bit constant integer value, then the value specifies the exponent to be
> used
> +when rounding and converting the second argument. The third argument is a
> +two bit constant integer that specifies the rounding mode. The possible
> modes
> +are: 00 Round to nearest, ties to even; 01 Round toward 0; 10 Round to
> nearest,
> +ties away from 0; 11 Round according to DRN where DRN is the Decimal Floating
> +point field of the FPSCR.
> +
> @end smallexample
>
> The following functions require @option{-mhard-float},
> diff --git a/gcc/testsuite/gcc.target/powerpc/pr93448.c
> b/gcc/testsuite/gcc.target/powerpc/pr93448.c
> new file mode 100644
> index 00000000000..f9c388585d7
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/powerpc/pr93448.c
> @@ -0,0 +1,200 @@
> +/* { dg-do run } */
> +/* { dg-require-effective-target dfp_hw} */
> +/* { dg-require-effective-target has_arch_pwr6} */
> +/* { dg-options "-mhard-float -O2 -save-temps" } */
> +
> +/* Test the decimal floating point quantize built-ins. */
> +
> +#define DEBUG 0
> +
> +#ifdef DEBUG
> +#include <stdio.h>
> +#endif
> +#include <float.h>
> +
> +void abort (void);
> +
> +int main()
> +{
> +#define IMM2 2
> +#define IMM3 3
> +#define IMM4 4
> +
> + _Decimal64 srcA_dfp64, srcB_dfp64;
> + _Decimal64 result_dfp64;
> + _Decimal64 expected_result_dfp64;
> + _Decimal128 srcA_dfp128, srcB_dfp128;
> + _Decimal128 result_dfp128;
> + _Decimal128 expected_result_dfp128;
> +
> + /* Third argument of quantize built-ins is the rounding mode value (RMC).
> +
> + RMC Rounding Mode
> + 00 Round to nearest, ties to even
> + 01 Round toward 0
> + 10 Round to nearest, ties toward 0
> + 11 Round according to DRN */
> +
> +
> + /* Tests for quantize with 64-bit DFP variable. */
> + srcA_dfp64 = 100.0df;
> + srcB_dfp64 = 300.456789df;
> + expected_result_dfp64 = 300.5df;
> +
> + result_dfp64 = __builtin_dfp_quantize (srcA_dfp64, srcB_dfp64, 0x0);
> +
> + if (result_dfp64 != expected_result_dfp64)
> +#if DEBUG
> + printf("DFP 64-bit quantize of variable, RMC = 0 result does not match
> expected result\n");
> +#else
> + abort();
> +#endif
> +
> + srcA_dfp64 = 100.00df;
> + srcB_dfp64 = 300.456789df;
> + expected_result_dfp64 = 300.45df;
> +
> + result_dfp64 = __builtin_dfp_quantize (srcA_dfp64, srcB_dfp64, 0x1);
> +
> + if (result_dfp64 != expected_result_dfp64)
> +#if DEBUG
> + printf("DFP 64-bit quantize of variable, RMC = 1 result does not match
> expected result\n");
> +#else
> + abort();
> +#endif
> +
> + srcA_dfp64 = 100.001df;
> + srcB_dfp64 = 3001.456789df;
> + expected_result_dfp64 = 3001.457df;
> +
> + result_dfp64 = __builtin_dfp_quantize (srcA_dfp64, srcB_dfp64, 0x2);
> +
> + if (result_dfp64 != expected_result_dfp64)
> +#if DEBUG
> + printf("DFP 64-bit quantize of variable, RMC = 2 result does not match
> expected result\n");
> +#else
> + abort();
> +#endif
> +
> + /* Tests for 64-bit quantize with immediate value. */
> +
> + srcB_dfp64 = 10.4567df;
> + expected_result_dfp64 = 000.0df;
> +
> + result_dfp64 = __builtin_dfp_quantize (IMM2, srcB_dfp64, 0x0);
> +
> + if (result_dfp64 != expected_result_dfp64)
> +#if DEBUG
> + printf("DFP 64-bit quantize immediate, RMC = 0 result does not match
> expected result\n");
> +#else
> + abort();
> +#endif
> +
> + srcB_dfp64 = 104567.891df;
> + expected_result_dfp64 = 100000.0df;
> +
> + result_dfp64 = __builtin_dfp_quantize (IMM4, srcB_dfp64, 0x1);
> +
> + if (result_dfp64 != expected_result_dfp64)
> +#if DEBUG
> + printf("DFP 64-bit quantize immediate, RMC = 1 result does not match
> expected result\n");
> +#else
> + abort();
> +#endif
> +
> + srcB_dfp64 = 109876.54321df;
> + expected_result_dfp64 = 109900.0df;
> +
> + result_dfp64 = __builtin_dfp_quantize (IMM2, srcB_dfp64, 0x2);
> +
> + if (result_dfp64 != expected_result_dfp64)
> +#if DEBUG
> + printf("DFP 64-bit quantize immediate, RMC = 2 result does not match
> expected result\n");
> +#else
> + abort();
> +#endif
> +
> + /* Tests for quantize 128-bit DFP variable. */
> + srcA_dfp128 = 0.018df;
> + srcB_dfp128 = 50000.18345df;
> + expected_result_dfp128 = 50000.180df;
> +
> + result_dfp128 = __builtin_dfp_quantize (srcA_dfp128, srcB_dfp128, 0x0);
> +
> + if (result_dfp128 != expected_result_dfp128)
> +#if DEBUG
> + printf("DFP 128-bit quantize variable, RMC = 0 result does not match
> expected result\n");
> +#else
> + abort();
> +#endif
> +
> + srcA_dfp128 = 8.01df;
> + srcB_dfp128 = 50000.18345df;
> + expected_result_dfp128 = 50000.18df;
> +
> + result_dfp128 = __builtin_dfp_quantize (srcA_dfp128, srcB_dfp128, 0x1);
> +
> + if (result_dfp128 != expected_result_dfp128)
> +#if DEBUG
> + printf("DFP 128-bit quantize variable, RMC = 1 result does not match
> expected result\n");
> +#else
> + abort();
> +#endif
> +
> + srcA_dfp128 = 0.1234df;
> + srcB_dfp128 = 50000.18346789df;
> + expected_result_dfp128 = 50000.1800df;
> +
> + result_dfp128 = __builtin_dfp_quantize (srcA_dfp128, srcB_dfp128, 0x2);
> +
> + if (result_dfp128 != expected_result_dfp128)
> +#if DEBUG
> + printf("DFP 128-bit quantize variable, RMC = 2 result does not match
> expected result\n");
> +#else
> + abort();
> +#endif
> +
> + /* Tests for 128-bit quantize with immediate value. */
> + srcB_dfp128 = 1234.18345df;
> + expected_result_dfp128 = 1200.0df;
> +
> + result_dfp128 = __builtin_dfp_quantize (IMM2, srcB_dfp128, 0x0);
> +
> + if (result_dfp128 != expected_result_dfp128)
> +#if DEBUG
> + printf("DFP 128-bit quantize immediate, RMC = 0 result does not match
> expected result\n");
> +#else
> + abort();
> +#endif
> +
> + srcB_dfp128 = 123456.18345df;
> + expected_result_dfp128 = 120000.0df;
> +
> + result_dfp128 = __builtin_dfp_quantize (IMM4, srcB_dfp128, 0x1);
> +
> + if (result_dfp128 != expected_result_dfp128)
> +#if DEBUG
> + printf("DFP 128-bit quantize immediate, RMC = 1 result does not match
> expected result\n");
> +#else
> + abort();
> +#endif
> +
> + srcB_dfp128 = 12361834.5df;
> + expected_result_dfp128 = 12362000.0df;
> +
> + result_dfp128 = __builtin_dfp_quantize (IMM3, srcB_dfp128, 0x2);
> +
> + if (result_dfp128 != expected_result_dfp128)
> +#if DEBUG
> + printf("DFP 128-bit quantize immediate, RMC = 2 result does not match
> expected result\n");
> +#else
> + abort();
> +#endif
> +
> + return 0;
> +}
> +
> +/* { dg-final { scan-assembler-times {\mdqua\M} 3 } } */
> +/* { dg-final { scan-assembler-times {\mdquai\M} 3 } } */
> +/* { dg-final { scan-assembler-times {\mdquaq\M} 3 } } */
> +/* { dg-final { scan-assembler-times {\mdquaiq\M} 3 } } */
