From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 1005) id 97AF13858D1E; Fri, 4 Mar 2022 23:59:39 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 97AF13858D1E Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: Michael Meissner To: gcc-cvs@gcc.gnu.org Subject: [gcc(refs/users/meissner/heads/work080)] Optimize signed DImode -> TImode on power10. X-Act-Checkin: gcc X-Git-Author: Michael Meissner X-Git-Refname: refs/users/meissner/heads/work080 X-Git-Oldrev: 3e4703bc7e511969902e3354e152bf20a8de72f2 X-Git-Newrev: 980fc679ad3e93c9dcc02f87911763936c04bb2f Message-Id: <20220304235939.97AF13858D1E@sourceware.org> Date: Fri, 4 Mar 2022 23:59:39 +0000 (GMT) X-BeenThere: gcc-cvs@gcc.gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Gcc-cvs mailing list List-Unsubscribe: , List-Archive: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 04 Mar 2022 23:59:39 -0000 https://gcc.gnu.org/g:980fc679ad3e93c9dcc02f87911763936c04bb2f commit 980fc679ad3e93c9dcc02f87911763936c04bb2f Author: Michael Meissner Date: Fri Mar 4 18:59:22 2022 -0500 Optimize signed DImode -> TImode on power10. On power10, GCC tries to optimize the signed conversion from DImode to TImode by using the vextsd2q instruction. However to generate this instruction, it would have to generate 3 direct moves (1 from the GPR registers to the altivec registers, and 2 from the altivec registers to the GPR register). This patch generates the shift right immediate instruction to do the conversion if the target/source registers ares GPR registers like it does on earlier systems. If the target/source registers are Altivec registers, it will generate the vextsd2q instruction. 2022-03-04 Michael Meissner gcc/ PR target/104698 * config/rs6000/vsx.md (UNSPEC_MTVSRD_DITI_W1): Delete. (mtvsrdd_diti_w1): Delete. (extendditi2): Convert from define_expand to define_insn_and_split. Replace with code to deal with both GPR registers and with altivec registers. gcc/testsuite/ PR target/104698 * gcc.target/powerpc/pr104698-1.c: New test. * gcc.target/powerpc/pr104698-2.c: New test. Diff: --- gcc/config/rs6000/vsx.md | 83 ++++++++++++++++++++------- gcc/testsuite/gcc.target/powerpc/pr104698-1.c | 30 ++++++++++ gcc/testsuite/gcc.target/powerpc/pr104698-2.c | 33 +++++++++++ 3 files changed, 124 insertions(+), 22 deletions(-) diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md index b53de103872..d0fb92f5985 100644 --- a/gcc/config/rs6000/vsx.md +++ b/gcc/config/rs6000/vsx.md @@ -360,7 +360,6 @@ UNSPEC_XXGENPCV UNSPEC_MTVSBM UNSPEC_EXTENDDITI2 - UNSPEC_MTVSRD_DITI_W1 UNSPEC_VCNTMB UNSPEC_VEXPAND UNSPEC_VEXTRACT @@ -5023,15 +5022,67 @@ DONE; }) -;; ISA 3.1 vector sign extend -;; Move DI value from GPR to TI mode in VSX register, word 1. -(define_insn "mtvsrdd_diti_w1" - [(set (match_operand:TI 0 "register_operand" "=wa") - (unspec:TI [(match_operand:DI 1 "register_operand" "r")] - UNSPEC_MTVSRD_DITI_W1))] - "TARGET_POWERPC64 && TARGET_DIRECT_MOVE" - "mtvsrdd %x0,0,%1" - [(set_attr "type" "vecmove")]) +;; Sign extend DI to TI. We provide both GPR targets and Altivec targets on +;; power10. On earlier systems, the machine independent code will generate a +;; shift left to sign extend the 64-bit value to 128-bit. +;; +;; If the register allocator prefers to use GPR registers, we will use a shift +;; left instruction to sign extend the 64-bit value to 128-bit. +;; +;; If the register allocator prefers to use Altivec registers on power10, +;; generate the vextsd2q instruction. +(define_insn_and_split "extendditi2" + [(set (match_operand:TI 0 "register_operand" "=r,r,v,v,v") + (sign_extend:TI (match_operand:DI 1 "input_operand" "r,m,r,wa,Z"))) + (clobber (reg:DI CA_REGNO))] + "TARGET_POWERPC64 && TARGET_POWER10" + "#" + "&& reload_completed" + [(pc)] +{ + rtx dest = operands[0]; + rtx src = operands[1]; + int dest_regno = reg_or_subregno (dest); + + /* Handle conversion to GPR registers. Load up the low part and then do + a sign extension to the upper part. */ + if (INT_REGNO_P (dest_regno)) + { + rtx dest_hi = gen_highpart (DImode, dest); + rtx dest_lo = gen_lowpart (DImode, dest); + + emit_move_insn (dest_lo, src); + /* In case src is a MEM, we have to use the destination, which is a + register, instead of re-using the source. */ + rtx src2 = (REG_P (src) || SUBREG_P (src)) ? src : dest_lo; + emit_insn (gen_ashrdi3 (dest_hi, src2, GEN_INT (63))); + DONE; + } + + /* For conversion to an Altivec register, generate either a splat operation + or a load rightmost double word instruction. Both instructions gets the + DImode value into the lower 64 bits, and then do the vextsd2q + instruction. */ + + else if (ALTIVEC_REGNO_P (dest_regno)) + { + if (MEM_P (src)) + emit_insn (gen_vsx_lxvrdx (dest, src)); + else + { + rtx dest_v2di = gen_rtx_REG (V2DImode, dest_regno); + emit_insn (gen_vsx_splat_v2di (dest_v2di, src)); + } + + emit_insn (gen_extendditi2_vector (dest, dest)); + DONE; + } + + else + gcc_unreachable (); +} + [(set_attr "length" "8") + (set_attr "type" "shift,load,vecmove,vecperm,load")]) ;; Sign extend 64-bit value in TI reg, word 1, to 128-bit value in TI reg (define_insn "extendditi2_vector" @@ -5042,18 +5093,6 @@ "vextsd2q %0,%1" [(set_attr "type" "vecexts")]) -(define_expand "extendditi2" - [(set (match_operand:TI 0 "gpc_reg_operand") - (sign_extend:DI (match_operand:DI 1 "gpc_reg_operand")))] - "TARGET_POWER10" - { - /* Move 64-bit src from GPR to vector reg and sign extend to 128-bits. */ - rtx temp = gen_reg_rtx (TImode); - emit_insn (gen_mtvsrdd_diti_w1 (temp, operands[1])); - emit_insn (gen_extendditi2_vector (operands[0], temp)); - DONE; - }) - ;; ISA 3.0 Binary Floating-Point Support diff --git a/gcc/testsuite/gcc.target/powerpc/pr104698-1.c b/gcc/testsuite/gcc.target/powerpc/pr104698-1.c new file mode 100644 index 00000000000..cd17b6b616d --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/pr104698-1.c @@ -0,0 +1,30 @@ +/* { dg-require-effective-target int128 } */ +/* { dg-require-effective-target power10_ok } */ +/* { dg-options "-mdejagnu-cpu=power10 -O2" } */ + +/* PR target/104698 involved a regression where on power10, conversion from + long long to __int128_t generated mtvsrdd, vextsd2q, mfvsrd, and mfvsrld + instructions instead of just a GPR sign extension. This test makes sure the + result is kept in the GPR registers. */ + +__int128_t convert_1 (long long a) +{ + return a; /* sradi. */ +} + +/* Like convert_1, but make sure a normal offsettable load is done. The + pattern in vsx.md has support for generating lxvdsx if it is coming from + memory. Make sure when the gpr is used, a normal load with offset is still + done. */ + +__int128_t convert_2 (long long *p) +{ + return p[2]; /* ld and sradi. */ +} + +/* { dg-final { scan-assembler-not {\mmfvsrd\M} } } */ +/* { dg-final { scan-assembler-not {\mmfvsrld\M} } } */ +/* { dg-final { scan-assembler-not {\mmtvsrdd\M} } } */ +/* { dg-final { scan-assembler-not {\mvextsd2q\M} } } */ +/* { dg-final { scan-assembler-times {\mld\M} 1 } } */ +/* { dg-final { scan-assembler-times {\msradi\M} 2 } } */ diff --git a/gcc/testsuite/gcc.target/powerpc/pr104698-2.c b/gcc/testsuite/gcc.target/powerpc/pr104698-2.c new file mode 100644 index 00000000000..6966fce2ba9 --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/pr104698-2.c @@ -0,0 +1,33 @@ +/* { dg-require-effective-target int128 } */ +/* { dg-require-effective-target power10_ok } */ +/* { dg-options "-mdejagnu-cpu=power10 -O2" } */ + +/* PR target/104694 involved GCC generating vextsd2q to convent long long to + __int128_t when the long long value was in the GPR register. This test + verifies that if the result is in the Altivec registers, we still want to + generate vextsd2q. We use __int128_t to indicate that we want the result of + the conversion to be in an Altivec register. */ + +void do_div_1 (__int128_t *p, __int128_t *q, long long r) +{ + *p = *q / r; /* mtvsrdd, vextsd2q, vdivsq. */ +} + +/* Test the optimization in vsx.md to use lxvrdx instead of ld and mtvsrdd if + the value is coming from memory. */ + +void do_div_2 (__int128_t *p, __int128_t *q, long long *r) +{ + *p = *q / r[2]; /* lxvrdx, vextsd2q, vdivsq. */ +} + +/* { dg-final { scan-assembler-not {\mld\M} } } */ +/* { dg-final { scan-assembler-not {\mmfvsrd\M} } } */ +/* { dg-final { scan-assembler-not {\mmfvsrld\M} } } */ +/* { dg-final { scan-assembler-not {\msradi\M} } } */ +/* { dg-final { scan-assembler-times {\mlxv\M} 2 } } */ +/* { dg-final { scan-assembler-times {\mlxvrdx\M} 1 } } */ +/* { dg-final { scan-assembler-times {\mmtvsrdd\M} 1 } } */ +/* { dg-final { scan-assembler-times {\mstxv\M} 2 } } */ +/* { dg-final { scan-assembler-times {\mvdivsq\M} 2 } } */ +/* { dg-final { scan-assembler-times {\mvextsd2q\M} 2 } } */