Message ID | 00b501d88fd9$e89e6700$b9db3500$@nextmovesoftware.com |
---|---|
State | New |
Headers | show |
Series | [x86,take,#2] Doubleword version of and; cmp to not; test optimization. | expand |
On Mon, Jul 4, 2022 at 9:11 PM Roger Sayle <roger@nextmovesoftware.com> wrote: > > > This patch is the latest revision of the patch originally posted at: > https://gcc.gnu.org/pipermail/gcc-patches/2022-June/596201.html > > This patch extends the earlier and;cmp to not;test optimization to also > perform this transformation for TImode on TARGET_64BIT and DImode on -m32, > One motivation for this is that it's a step to fixing the current failure > of gcc.target/i386/pr65105-5.c on -m32. > > A more direct benefit for x86_64 is that the following code: > > int foo(__int128 x, __int128 y) > { > return (x & y) == y; > } > > improves with -O2 from 15 instructions: > > movq %rdi, %r8 > movq %rsi, %rax > movq %rax, %rdi > movq %r8, %rsi > movq %rdx, %r8 > andq %rdx, %rsi > andq %rcx, %rdi > movq %rsi, %rax > movq %rdi, %rdx > xorq %r8, %rax > xorq %rcx, %rdx > orq %rdx, %rax > sete %al > movzbl %al, %eax > ret > > to the slightly better 13 instructions: > > movq %rdi, %r8 > movq %rsi, %rax > movq %r8, %rsi > movq %rax, %rdi > notq %rsi > notq %rdi > andq %rdx, %rsi > andq %rcx, %rdi > movq %rsi, %rax > orq %rdi, %rax > sete %al > movzbl %al, %eax > ret > > Now that all of the doubleword pieces are already in the tree, this > patch is now much shorter (an rtx_costs improvement and a single new > define_insn_and_split), however I couldn't resist including two very > minor pattern naming tweaks/clean-ups to fix nits. > > This revised patch has been tested on x86_64-pc-linux-gnu with > make bootstrap and make -k check, where on TARGET_64BIT there are > no new failures, and on --target_board=unix{-m32} with a single new > failure; the other dg-final in gcc.target/i386/pr65105-5.c now also > fails (as that code diverges further from the expected vectorized > output). This is progress as both FAILs in pr65105-5.c may now be > fixed by changes localized to the STV pass. OK for mainline? > > > 2022-07-04 Roger Sayle <roger@nextmovesoftware.com> > > gcc/ChangeLog > * config/i386/i386.cc (ix86_rtx_costs) <COMPARE>: Provide costs > for double word comparisons and tests (comparisons against zero). > * config/i386/i386.md (*test<mode>_not_doubleword): Split DWI > and;cmp into andn;cmp $0 as a pre-reload splitter. > (*andn<dwi>3_doubleword_bmi): Use <dwi> instead of <mode> in name. > (*<any_or><dwi>3_doubleword): Likewise. > > gcc/testsuite/ChangeLog > * gcc.target/i386/testnot-3.c: New test case. > +;; Split and;cmp (as optimized by combine) into andn;cmp $0 +(define_insn_and_split "*test<mode>_not_doubleword" + [(set (reg:CCZ FLAGS_REG) + (compare:CCZ + (and:DWI + (not:DWI (match_operand:DWI 0 "nonimmediate_operand")) + (match_operand:DWI 1 "nonimmediate_operand")) + (const_int 0)))] + "ix86_pre_reload_split ()" + "#" + "&& 1" + [(parallel + [(set (match_dup 2) (and:DWI (not:DWI (match_dup 0)) (match_dup 1))) + (clobber (reg:CC FLAGS_REG))]) + (set (reg:CCZ FLAGS_REG) (compare:CCZ (match_dup 2) (const_int 0)))] { + operands[0] = force_reg (<MODE>mode, operands[0]); operands[2] = gen_reg_rtx (<MODE>mode); }) I don't think we can count on a follow-up split to lower ANDN for !TARGET_BMI case, it is also a pre-reload splitter. Please emit ANDN only for TARGET_BMI and NOT/AND for !TARGET_BMI instead. Uros. > Thanks in advance, > Roger > -- >
On Tue, Jul 5, 2022 at 9:56 AM Uros Bizjak <ubizjak@gmail.com> wrote: > > On Mon, Jul 4, 2022 at 9:11 PM Roger Sayle <roger@nextmovesoftware.com> wrote: > > > > > > This patch is the latest revision of the patch originally posted at: > > https://gcc.gnu.org/pipermail/gcc-patches/2022-June/596201.html > > > > This patch extends the earlier and;cmp to not;test optimization to also > > perform this transformation for TImode on TARGET_64BIT and DImode on -m32, > > One motivation for this is that it's a step to fixing the current failure > > of gcc.target/i386/pr65105-5.c on -m32. > > > > A more direct benefit for x86_64 is that the following code: > > > > int foo(__int128 x, __int128 y) > > { > > return (x & y) == y; > > } > > > > improves with -O2 from 15 instructions: > > > > movq %rdi, %r8 > > movq %rsi, %rax > > movq %rax, %rdi > > movq %r8, %rsi > > movq %rdx, %r8 > > andq %rdx, %rsi > > andq %rcx, %rdi > > movq %rsi, %rax > > movq %rdi, %rdx > > xorq %r8, %rax > > xorq %rcx, %rdx > > orq %rdx, %rax > > sete %al > > movzbl %al, %eax > > ret > > > > to the slightly better 13 instructions: > > > > movq %rdi, %r8 > > movq %rsi, %rax > > movq %r8, %rsi > > movq %rax, %rdi > > notq %rsi > > notq %rdi > > andq %rdx, %rsi > > andq %rcx, %rdi > > movq %rsi, %rax > > orq %rdi, %rax > > sete %al > > movzbl %al, %eax > > ret > > > > Now that all of the doubleword pieces are already in the tree, this > > patch is now much shorter (an rtx_costs improvement and a single new > > define_insn_and_split), however I couldn't resist including two very > > minor pattern naming tweaks/clean-ups to fix nits. > > > > This revised patch has been tested on x86_64-pc-linux-gnu with > > make bootstrap and make -k check, where on TARGET_64BIT there are > > no new failures, and on --target_board=unix{-m32} with a single new > > failure; the other dg-final in gcc.target/i386/pr65105-5.c now also > > fails (as that code diverges further from the expected vectorized > > output). This is progress as both FAILs in pr65105-5.c may now be > > fixed by changes localized to the STV pass. OK for mainline? > > > > > > 2022-07-04 Roger Sayle <roger@nextmovesoftware.com> > > > > gcc/ChangeLog > > * config/i386/i386.cc (ix86_rtx_costs) <COMPARE>: Provide costs > > for double word comparisons and tests (comparisons against zero). > > * config/i386/i386.md (*test<mode>_not_doubleword): Split DWI > > and;cmp into andn;cmp $0 as a pre-reload splitter. > > (*andn<dwi>3_doubleword_bmi): Use <dwi> instead of <mode> in name. > > (*<any_or><dwi>3_doubleword): Likewise. > > > > gcc/testsuite/ChangeLog > > * gcc.target/i386/testnot-3.c: New test case. > > > > > +;; Split and;cmp (as optimized by combine) into andn;cmp $0 > +(define_insn_and_split "*test<mode>_not_doubleword" > + [(set (reg:CCZ FLAGS_REG) > + (compare:CCZ > + (and:DWI > + (not:DWI (match_operand:DWI 0 "nonimmediate_operand")) > + (match_operand:DWI 1 "nonimmediate_operand")) > + (const_int 0)))] > + "ix86_pre_reload_split ()" > + "#" > + "&& 1" > + [(parallel > + [(set (match_dup 2) (and:DWI (not:DWI (match_dup 0)) (match_dup 1))) > + (clobber (reg:CC FLAGS_REG))]) > + (set (reg:CCZ FLAGS_REG) (compare:CCZ (match_dup 2) (const_int 0)))] > { > + operands[0] = force_reg (<MODE>mode, operands[0]); > operands[2] = gen_reg_rtx (<MODE>mode); > }) > > I don't think we can count on a follow-up split to lower ANDN for > !TARGET_BMI case, it is also a pre-reload splitter. Actually, splitters *CAN* be chained: Splitting with gen_split_231 (i386.md:10408) scanning new insn with uid = 30. scanning new insn with uid = 31. deleting insn with uid = 12. Splitting with gen_split_235 (i386.md:10444) scanning new insn with uid = 32. scanning new insn with uid = 33. deleting insn with uid = 30. Splitting with gen_split_2 (i386.md:1510) scanning new insn with uid = 34. scanning new insn with uid = 35. scanning new insn with uid = 36. scanning new insn with uid = 37. deleting insn with uid = 31. deleting insn with uid = 12. INSNs are recognized after they are split. The patch is OK as is. Thanks, Uros.
diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc index b15b489..70c9a27 100644 --- a/gcc/config/i386/i386.cc +++ b/gcc/config/i386/i386.cc @@ -20935,6 +20935,19 @@ ix86_rtx_costs (rtx x, machine_mode mode, int outer_code_i, int opno, return true; } + if (SCALAR_INT_MODE_P (GET_MODE (op0)) + && GET_MODE_SIZE (GET_MODE (op0)) > UNITS_PER_WORD) + { + if (op1 == const0_rtx) + *total = cost->add + + rtx_cost (op0, GET_MODE (op0), outer_code, opno, speed); + else + *total = 3*cost->add + + rtx_cost (op0, GET_MODE (op0), outer_code, opno, speed) + + rtx_cost (op1, GET_MODE (op0), outer_code, opno, speed); + return true; + } + /* The embedded comparison operand is completely free. */ if (!general_operand (op0, GET_MODE (op0)) && op1 == const0_rtx) *total = 0; diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md index 20c3b9a..2492ad4 100644 --- a/gcc/config/i386/i386.md +++ b/gcc/config/i386/i386.md @@ -9792,7 +9792,25 @@ (set (reg:CCZ FLAGS_REG) (compare:CCZ (and:SWI (match_dup 2) (match_dup 1)) (const_int 0)))] + "operands[2] = gen_reg_rtx (<MODE>mode);") + +;; Split and;cmp (as optimized by combine) into andn;cmp $0 +(define_insn_and_split "*test<mode>_not_doubleword" + [(set (reg:CCZ FLAGS_REG) + (compare:CCZ + (and:DWI + (not:DWI (match_operand:DWI 0 "nonimmediate_operand")) + (match_operand:DWI 1 "nonimmediate_operand")) + (const_int 0)))] + "ix86_pre_reload_split ()" + "#" + "&& 1" + [(parallel + [(set (match_dup 2) (and:DWI (not:DWI (match_dup 0)) (match_dup 1))) + (clobber (reg:CC FLAGS_REG))]) + (set (reg:CCZ FLAGS_REG) (compare:CCZ (match_dup 2) (const_int 0)))] { + operands[0] = force_reg (<MODE>mode, operands[0]); operands[2] = gen_reg_rtx (<MODE>mode); }) @@ -10404,7 +10422,7 @@ operands[2] = gen_int_mode (INTVAL (operands[2]), QImode); }) -(define_insn_and_split "*andn<mode>3_doubleword_bmi" +(define_insn_and_split "*andn<dwi>3_doubleword_bmi" [(set (match_operand:<DWI> 0 "register_operand" "=r") (and:<DWI> (not:<DWI> (match_operand:<DWI> 1 "register_operand" "r")) @@ -10542,7 +10560,7 @@ DONE; }) -(define_insn_and_split "*<code><mode>3_doubleword" +(define_insn_and_split "*<code><dwi>3_doubleword" [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r") (any_or:<DWI> (match_operand:<DWI> 1 "nonimmediate_operand" "%0,0") diff --git a/gcc/testsuite/gcc.target/i386/testnot-3.c b/gcc/testsuite/gcc.target/i386/testnot-3.c new file mode 100644 index 0000000..7c54dbc --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/testnot-3.c @@ -0,0 +1,9 @@ +/* { dg-do compile { target int128 } } */ +/* { dg-options "-O2" } */ + +int foo(__int128 x, __int128 y) +{ + return (x & y) == y; +} + +/* { dg-final { scan-assembler-not "xorq" } } */