Re: [PATCHv2, ARM, libgcc] New aeabi_idiv function for armv6-m
On 11/07/16 18:09, Andre Vieira (lists) wrote: > On 06/07/16 11:52, Andre Vieira (lists) wrote: >> On 01/07/16 14:40, Ramana Radhakrishnan wrote: >>> >>> >>> On 13/10/15 18:01, Andre Vieira wrote: This patch ports the aeabi_idiv routine from Linaro Cortex-Strings (https://git.linaro.org/toolchain/cortex-strings.git), which was contributed by ARM under Free BSD license. The new aeabi_idiv routine is used to replace the one in libgcc/config/arm/lib1funcs.S. This replacement happens within the Thumb1 wrapper. The new routine is under LGPLv3 license. >>> >>> This is not under LGPLv3 . It is under GPLv3 with the runtime library >>> exception license, there's a difference. Assuming your licensing >>> expectation is ok read on for more of a review. >>> The main advantage of this version is that it can improve the performance of the aeabi_idiv function for Thumb1. This solution will also increase the code size. So it will only be used if __OPTIMIZE_SIZE__ is not defined. Make check passed for armv6-m. libgcc/ChangeLog: 2015-08-10 Hale WangAndre Vieira * config/arm/lib1funcs.S: Add new wrapper. 0001-integer-division.patch From 832a3d6af6f06399f70b5a4ac3727d55960c93b7 Mon Sep 17 00:00:00 2001 From: Andre Simoes Dias Vieira Date: Fri, 21 Aug 2015 14:23:28 +0100 Subject: [PATCH] new wrapper idivmod --- libgcc/config/arm/lib1funcs.S | 250 -- 1 file changed, 217 insertions(+), 33 deletions(-) diff --git a/libgcc/config/arm/lib1funcs.S b/libgcc/config/arm/lib1funcs.S index 252efcbd5385cc58a5ce1e48c6816d36a6f4c797..c9e544114590da8cde88382bea0f67206e593816 100644 --- a/libgcc/config/arm/lib1funcs.S +++ b/libgcc/config/arm/lib1funcs.S @@ -306,34 +306,12 @@ LSYM(Lend_fde): #ifdef __ARM_EABI__ .macro THUMB_LDIV0 name signed #if defined(__ARM_ARCH_6M__) - .ifc \signed, unsigned - cmp r0, #0 - beq 1f - mov r0, #0 - mvn r0, r0 @ 0x -1: - .else - cmp r0, #0 - beq 2f - blt 3f + + push{r0, lr} mov r0, #0 - mvn r0, r0 - lsr r0, r0, #1 @ 0x7fff - b 2f -3:mov r0, #0x80 - lsl r0, r0, #24 @ 0x8000 -2: - .endif - push{r0, r1, r2} - ldr r0, 4f - adr r1, 4f - add r0, r1 - str r0, [sp, #8] - @ We know we are not on armv4t, so pop pc is safe. - pop {r0, r1, pc} - .align 2 -4: - .word __aeabi_idiv0 - 4b + bl SYM(__aeabi_idiv0) + pop {r1, pc} + >>> >>> I'd still retain the comment about pop pc here because there's often a >>> misconception of merging armv4t and armv6m code. >>> #elif defined(__thumb2__) .syntax unified .ifc \signed, unsigned @@ -945,7 +923,170 @@ LSYM(Lover7): add dividend, work .endif LSYM(Lgot_result): -.endm +.endm + +#if defined(__prefer_thumb__) && !defined(__OPTIMIZE_SIZE__) +/* If performance is preferred, the following functions are provided. */ + >>> >>> Comment above #if please and also check elsewhere in patch. >>> +/* Branch to div(n), and jump to label if curbit is lo than divisior. */ +.macro BranchToDiv n, label + lsr curbit, dividend, \n + cmp curbit, divisor + blo \label +.endm + +/* Body of div(n). Shift the divisor in n bits and compare the divisor + and dividend. Update the dividend as the substruction result. */ +.macro DoDiv n + lsr curbit, dividend, \n + cmp curbit, divisor + bcc 1f + lsl curbit, divisor, \n + sub dividend, dividend, curbit + +1:adc result, result +.endm + +/* The body of division with positive divisor. Unless the divisor is very + big, shift it up in multiples of four bits, since this is the amount of + unwinding in the main division loop. Continue shifting until the divisor + is larger than the dividend. */ +.macro THUMB1_Div_Positive + mov result, #0 + BranchToDiv #1, LSYM(Lthumb1_div1) + BranchToDiv #4, LSYM(Lthumb1_div4) + BranchToDiv #8, LSYM(Lthumb1_div8) + BranchToDiv #12, LSYM(Lthumb1_div12) + BranchToDiv #16, LSYM(Lthumb1_div16) +LSYM(Lthumb1_div_large_positive): + mov result, #0xff + lsl divisor, divisor, #8 + rev result, result + lsr curbit, dividend, #16 + cmp curbit, divisor + blo 1f + asr result, #8
Re: [PATCHv2, ARM, libgcc] New aeabi_idiv function for armv6-m
On 06/07/16 11:52, Andre Vieira (lists) wrote: > On 01/07/16 14:40, Ramana Radhakrishnan wrote: >> >> >> On 13/10/15 18:01, Andre Vieira wrote: >>> This patch ports the aeabi_idiv routine from Linaro Cortex-Strings >>> (https://git.linaro.org/toolchain/cortex-strings.git), which was >>> contributed by ARM under Free BSD license. >>> >>> The new aeabi_idiv routine is used to replace the one in >>> libgcc/config/arm/lib1funcs.S. This replacement happens within the Thumb1 >>> wrapper. The new routine is under LGPLv3 license. >> >> This is not under LGPLv3 . It is under GPLv3 with the runtime library >> exception license, there's a difference. Assuming your licensing expectation >> is ok read on for more of a review. >> >>> >>> The main advantage of this version is that it can improve the performance >>> of the aeabi_idiv function for Thumb1. This solution will also increase the >>> code size. So it will only be used if __OPTIMIZE_SIZE__ is not defined. >>> >>> Make check passed for armv6-m. >>> >>> libgcc/ChangeLog: >>> 2015-08-10 Hale Wang>>> Andre Vieira >>> >>> * config/arm/lib1funcs.S: Add new wrapper. >>> >>> 0001-integer-division.patch >>> >>> >>> From 832a3d6af6f06399f70b5a4ac3727d55960c93b7 Mon Sep 17 00:00:00 2001 >>> From: Andre Simoes Dias Vieira >>> Date: Fri, 21 Aug 2015 14:23:28 +0100 >>> Subject: [PATCH] new wrapper idivmod >>> >>> --- >>> libgcc/config/arm/lib1funcs.S | 250 >>> -- >>> 1 file changed, 217 insertions(+), 33 deletions(-) >>> >>> diff --git a/libgcc/config/arm/lib1funcs.S b/libgcc/config/arm/lib1funcs.S >>> index >>> 252efcbd5385cc58a5ce1e48c6816d36a6f4c797..c9e544114590da8cde88382bea0f67206e593816 >>> 100644 >>> --- a/libgcc/config/arm/lib1funcs.S >>> +++ b/libgcc/config/arm/lib1funcs.S >>> @@ -306,34 +306,12 @@ LSYM(Lend_fde): >>> #ifdef __ARM_EABI__ >>> .macro THUMB_LDIV0 name signed >>> #if defined(__ARM_ARCH_6M__) >>> - .ifc \signed, unsigned >>> - cmp r0, #0 >>> - beq 1f >>> - mov r0, #0 >>> - mvn r0, r0 @ 0x >>> -1: >>> - .else >>> - cmp r0, #0 >>> - beq 2f >>> - blt 3f >>> + >>> + push{r0, lr} >>> mov r0, #0 >>> - mvn r0, r0 >>> - lsr r0, r0, #1 @ 0x7fff >>> - b 2f >>> -3: mov r0, #0x80 >>> - lsl r0, r0, #24 @ 0x8000 >>> -2: >>> - .endif >>> - push{r0, r1, r2} >>> - ldr r0, 4f >>> - adr r1, 4f >>> - add r0, r1 >>> - str r0, [sp, #8] >>> - @ We know we are not on armv4t, so pop pc is safe. >>> - pop {r0, r1, pc} >>> - .align 2 >>> -4: >>> - .word __aeabi_idiv0 - 4b >>> + bl SYM(__aeabi_idiv0) >>> + pop {r1, pc} >>> + >> >> I'd still retain the comment about pop pc here because there's often a >> misconception of merging armv4t and armv6m code. >> >>> #elif defined(__thumb2__) >>> .syntax unified >>> .ifc \signed, unsigned >>> @@ -945,7 +923,170 @@ LSYM(Lover7): >>> add dividend, work >>>.endif >>> LSYM(Lgot_result): >>> -.endm >>> +.endm >>> + >>> +#if defined(__prefer_thumb__) && !defined(__OPTIMIZE_SIZE__) >>> +/* If performance is preferred, the following functions are provided. */ >>> + >> >> Comment above #if please and also check elsewhere in patch. >> >>> +/* Branch to div(n), and jump to label if curbit is lo than divisior. */ >>> +.macro BranchToDiv n, label >>> + lsr curbit, dividend, \n >>> + cmp curbit, divisor >>> + blo \label >>> +.endm >>> + >>> +/* Body of div(n). Shift the divisor in n bits and compare the divisor >>> + and dividend. Update the dividend as the substruction result. */ >>> +.macro DoDiv n >>> + lsr curbit, dividend, \n >>> + cmp curbit, divisor >>> + bcc 1f >>> + lsl curbit, divisor, \n >>> + sub dividend, dividend, curbit >>> + >>> +1: adc result, result >>> +.endm >>> + >>> +/* The body of division with positive divisor. Unless the divisor is very >>> + big, shift it up in multiples of four bits, since this is the amount of >>> + unwinding in the main division loop. Continue shifting until the >>> divisor >>> + is larger than the dividend. */ >>> +.macro THUMB1_Div_Positive >>> + mov result, #0 >>> + BranchToDiv #1, LSYM(Lthumb1_div1) >>> + BranchToDiv #4, LSYM(Lthumb1_div4) >>> + BranchToDiv #8, LSYM(Lthumb1_div8) >>> + BranchToDiv #12, LSYM(Lthumb1_div12) >>> + BranchToDiv #16, LSYM(Lthumb1_div16) >>> +LSYM(Lthumb1_div_large_positive): >>> + mov result, #0xff >>> + lsl divisor, divisor, #8 >>> + rev result, result >>> + lsr curbit, dividend, #16 >>> + cmp curbit, divisor >>> + blo 1f >>> + asr result, #8 >>> + lsl divisor, divisor, #8 >>> + beq LSYM(Ldivbyzero_waypoint) >>> + >>> +1: lsr curbit, dividend, #12 >>> + cmp curbit, divisor
Re: [PATCHv2, ARM, libgcc] New aeabi_idiv function for armv6-m
On 01/07/16 14:40, Ramana Radhakrishnan wrote: > > > On 13/10/15 18:01, Andre Vieira wrote: >> This patch ports the aeabi_idiv routine from Linaro Cortex-Strings >> (https://git.linaro.org/toolchain/cortex-strings.git), which was contributed >> by ARM under Free BSD license. >> >> The new aeabi_idiv routine is used to replace the one in >> libgcc/config/arm/lib1funcs.S. This replacement happens within the Thumb1 >> wrapper. The new routine is under LGPLv3 license. > > This is not under LGPLv3 . It is under GPLv3 with the runtime library > exception license, there's a difference. Assuming your licensing expectation > is ok read on for more of a review. > >> >> The main advantage of this version is that it can improve the performance of >> the aeabi_idiv function for Thumb1. This solution will also increase the >> code size. So it will only be used if __OPTIMIZE_SIZE__ is not defined. >> >> Make check passed for armv6-m. >> >> libgcc/ChangeLog: >> 2015-08-10 Hale Wang>> Andre Vieira >> >> * config/arm/lib1funcs.S: Add new wrapper. >> >> 0001-integer-division.patch >> >> >> From 832a3d6af6f06399f70b5a4ac3727d55960c93b7 Mon Sep 17 00:00:00 2001 >> From: Andre Simoes Dias Vieira >> Date: Fri, 21 Aug 2015 14:23:28 +0100 >> Subject: [PATCH] new wrapper idivmod >> >> --- >> libgcc/config/arm/lib1funcs.S | 250 >> -- >> 1 file changed, 217 insertions(+), 33 deletions(-) >> >> diff --git a/libgcc/config/arm/lib1funcs.S b/libgcc/config/arm/lib1funcs.S >> index >> 252efcbd5385cc58a5ce1e48c6816d36a6f4c797..c9e544114590da8cde88382bea0f67206e593816 >> 100644 >> --- a/libgcc/config/arm/lib1funcs.S >> +++ b/libgcc/config/arm/lib1funcs.S >> @@ -306,34 +306,12 @@ LSYM(Lend_fde): >> #ifdef __ARM_EABI__ >> .macro THUMB_LDIV0 name signed >> #if defined(__ARM_ARCH_6M__) >> -.ifc \signed, unsigned >> -cmp r0, #0 >> -beq 1f >> -mov r0, #0 >> -mvn r0, r0 @ 0x >> -1: >> -.else >> -cmp r0, #0 >> -beq 2f >> -blt 3f >> + >> +push{r0, lr} >> mov r0, #0 >> -mvn r0, r0 >> -lsr r0, r0, #1 @ 0x7fff >> -b 2f >> -3: mov r0, #0x80 >> -lsl r0, r0, #24 @ 0x8000 >> -2: >> -.endif >> -push{r0, r1, r2} >> -ldr r0, 4f >> -adr r1, 4f >> -add r0, r1 >> -str r0, [sp, #8] >> -@ We know we are not on armv4t, so pop pc is safe. >> -pop {r0, r1, pc} >> -.align 2 >> -4: >> -.word __aeabi_idiv0 - 4b >> +bl SYM(__aeabi_idiv0) >> +pop {r1, pc} >> + > > I'd still retain the comment about pop pc here because there's often a > misconception of merging armv4t and armv6m code. > >> #elif defined(__thumb2__) >> .syntax unified >> .ifc \signed, unsigned >> @@ -945,7 +923,170 @@ LSYM(Lover7): >> add dividend, work >>.endif >> LSYM(Lgot_result): >> -.endm >> +.endm >> + >> +#if defined(__prefer_thumb__) && !defined(__OPTIMIZE_SIZE__) >> +/* If performance is preferred, the following functions are provided. */ >> + > > Comment above #if please and also check elsewhere in patch. > >> +/* Branch to div(n), and jump to label if curbit is lo than divisior. */ >> +.macro BranchToDiv n, label >> +lsr curbit, dividend, \n >> +cmp curbit, divisor >> +blo \label >> +.endm >> + >> +/* Body of div(n). Shift the divisor in n bits and compare the divisor >> + and dividend. Update the dividend as the substruction result. */ >> +.macro DoDiv n >> +lsr curbit, dividend, \n >> +cmp curbit, divisor >> +bcc 1f >> +lsl curbit, divisor, \n >> +sub dividend, dividend, curbit >> + >> +1: adc result, result >> +.endm >> + >> +/* The body of division with positive divisor. Unless the divisor is very >> + big, shift it up in multiples of four bits, since this is the amount of >> + unwinding in the main division loop. Continue shifting until the divisor >> + is larger than the dividend. */ >> +.macro THUMB1_Div_Positive >> +mov result, #0 >> +BranchToDiv #1, LSYM(Lthumb1_div1) >> +BranchToDiv #4, LSYM(Lthumb1_div4) >> +BranchToDiv #8, LSYM(Lthumb1_div8) >> +BranchToDiv #12, LSYM(Lthumb1_div12) >> +BranchToDiv #16, LSYM(Lthumb1_div16) >> +LSYM(Lthumb1_div_large_positive): >> +mov result, #0xff >> +lsl divisor, divisor, #8 >> +rev result, result >> +lsr curbit, dividend, #16 >> +cmp curbit, divisor >> +blo 1f >> +asr result, #8 >> +lsl divisor, divisor, #8 >> +beq LSYM(Ldivbyzero_waypoint) >> + >> +1: lsr curbit, dividend, #12 >> +cmp curbit, divisor >> +blo LSYM(Lthumb1_div12) >> +b LSYM(Lthumb1_div16) >> +LSYM(Lthumb1_div_loop): >> +lsr divisor, divisor,
Re: [PATCHv2, ARM, libgcc] New aeabi_idiv function for armv6-m
On 13/10/15 18:01, Andre Vieira wrote: > This patch ports the aeabi_idiv routine from Linaro Cortex-Strings > (https://git.linaro.org/toolchain/cortex-strings.git), which was contributed > by ARM under Free BSD license. > > The new aeabi_idiv routine is used to replace the one in > libgcc/config/arm/lib1funcs.S. This replacement happens within the Thumb1 > wrapper. The new routine is under LGPLv3 license. This is not under LGPLv3 . It is under GPLv3 with the runtime library exception license, there's a difference. Assuming your licensing expectation is ok read on for more of a review. > > The main advantage of this version is that it can improve the performance of > the aeabi_idiv function for Thumb1. This solution will also increase the code > size. So it will only be used if __OPTIMIZE_SIZE__ is not defined. > > Make check passed for armv6-m. > > libgcc/ChangeLog: > 2015-08-10 Hale Wang> Andre Vieira > > * config/arm/lib1funcs.S: Add new wrapper. > > 0001-integer-division.patch > > > From 832a3d6af6f06399f70b5a4ac3727d55960c93b7 Mon Sep 17 00:00:00 2001 > From: Andre Simoes Dias Vieira > Date: Fri, 21 Aug 2015 14:23:28 +0100 > Subject: [PATCH] new wrapper idivmod > > --- > libgcc/config/arm/lib1funcs.S | 250 > -- > 1 file changed, 217 insertions(+), 33 deletions(-) > > diff --git a/libgcc/config/arm/lib1funcs.S b/libgcc/config/arm/lib1funcs.S > index > 252efcbd5385cc58a5ce1e48c6816d36a6f4c797..c9e544114590da8cde88382bea0f67206e593816 > 100644 > --- a/libgcc/config/arm/lib1funcs.S > +++ b/libgcc/config/arm/lib1funcs.S > @@ -306,34 +306,12 @@ LSYM(Lend_fde): > #ifdef __ARM_EABI__ > .macro THUMB_LDIV0 name signed > #if defined(__ARM_ARCH_6M__) > - .ifc \signed, unsigned > - cmp r0, #0 > - beq 1f > - mov r0, #0 > - mvn r0, r0 @ 0x > -1: > - .else > - cmp r0, #0 > - beq 2f > - blt 3f > + > + push{r0, lr} > mov r0, #0 > - mvn r0, r0 > - lsr r0, r0, #1 @ 0x7fff > - b 2f > -3: mov r0, #0x80 > - lsl r0, r0, #24 @ 0x8000 > -2: > - .endif > - push{r0, r1, r2} > - ldr r0, 4f > - adr r1, 4f > - add r0, r1 > - str r0, [sp, #8] > - @ We know we are not on armv4t, so pop pc is safe. > - pop {r0, r1, pc} > - .align 2 > -4: > - .word __aeabi_idiv0 - 4b > + bl SYM(__aeabi_idiv0) > + pop {r1, pc} > + I'd still retain the comment about pop pc here because there's often a misconception of merging armv4t and armv6m code. > #elif defined(__thumb2__) > .syntax unified > .ifc \signed, unsigned > @@ -945,7 +923,170 @@ LSYM(Lover7): > add dividend, work >.endif > LSYM(Lgot_result): > -.endm > +.endm > + > +#if defined(__prefer_thumb__) && !defined(__OPTIMIZE_SIZE__) > +/* If performance is preferred, the following functions are provided. */ > + Comment above #if please and also check elsewhere in patch. > +/* Branch to div(n), and jump to label if curbit is lo than divisior. */ > +.macro BranchToDiv n, label > + lsr curbit, dividend, \n > + cmp curbit, divisor > + blo \label > +.endm > + > +/* Body of div(n). Shift the divisor in n bits and compare the divisor > + and dividend. Update the dividend as the substruction result. */ > +.macro DoDiv n > + lsr curbit, dividend, \n > + cmp curbit, divisor > + bcc 1f > + lsl curbit, divisor, \n > + sub dividend, dividend, curbit > + > +1: adc result, result > +.endm > + > +/* The body of division with positive divisor. Unless the divisor is very > + big, shift it up in multiples of four bits, since this is the amount of > + unwinding in the main division loop. Continue shifting until the divisor > + is larger than the dividend. */ > +.macro THUMB1_Div_Positive > + mov result, #0 > + BranchToDiv #1, LSYM(Lthumb1_div1) > + BranchToDiv #4, LSYM(Lthumb1_div4) > + BranchToDiv #8, LSYM(Lthumb1_div8) > + BranchToDiv #12, LSYM(Lthumb1_div12) > + BranchToDiv #16, LSYM(Lthumb1_div16) > +LSYM(Lthumb1_div_large_positive): > + mov result, #0xff > + lsl divisor, divisor, #8 > + rev result, result > + lsr curbit, dividend, #16 > + cmp curbit, divisor > + blo 1f > + asr result, #8 > + lsl divisor, divisor, #8 > + beq LSYM(Ldivbyzero_waypoint) > + > +1: lsr curbit, dividend, #12 > + cmp curbit, divisor > + blo LSYM(Lthumb1_div12) > + b LSYM(Lthumb1_div16) > +LSYM(Lthumb1_div_loop): > + lsr divisor, divisor, #8 > +LSYM(Lthumb1_div16): > + Dodiv #15 > + Dodiv #14 > + Dodiv #13 > + Dodiv #12 > +LSYM(Lthumb1_div12): > +
Re: [PING^5][PATCHv2, ARM, libgcc] New aeabi_idiv function for armv6-m
Ping. On 08/06/16 15:35, Andre Vieira (lists) wrote: > Ping. > > On 19/05/16 11:19, Andre Vieira (lists) wrote: >> Ping for GCC-7, patch applies cleanly, passed make check for cortex-m0. >> >> Might be worth mentioning that this patch has been used in three >> releases of the GNU ARM embedded toolchain, using GCC versions 4.9 and >> 5, and no issues have been reported so far. >> >> On 25/01/16 17:15, Andre Vieira (lists) wrote: >>> Ping. >>> >>> On 27/10/15 17:03, Andre Vieira wrote: Ping. BR, Andre On 13/10/15 18:01, Andre Vieira wrote: > This patch ports the aeabi_idiv routine from Linaro Cortex-Strings > (https://git.linaro.org/toolchain/cortex-strings.git), which was > contributed by ARM under Free BSD license. > > The new aeabi_idiv routine is used to replace the one in > libgcc/config/arm/lib1funcs.S. This replacement happens within the > Thumb1 wrapper. The new routine is under LGPLv3 license. > > The main advantage of this version is that it can improve the > performance of the aeabi_idiv function for Thumb1. This solution will > also increase the code size. So it will only be used if > __OPTIMIZE_SIZE__ is not defined. > > Make check passed for armv6-m. > > libgcc/ChangeLog: > 2015-08-10 Hale Wang> Andre Vieira > > * config/arm/lib1funcs.S: Add new wrapper. > >>> >> >
Re: [PING^4][PATCHv2, ARM, libgcc] New aeabi_idiv function for armv6-m
Ping. On 19/05/16 11:19, Andre Vieira (lists) wrote: > Ping for GCC-7, patch applies cleanly, passed make check for cortex-m0. > > Might be worth mentioning that this patch has been used in three > releases of the GNU ARM embedded toolchain, using GCC versions 4.9 and > 5, and no issues have been reported so far. > > On 25/01/16 17:15, Andre Vieira (lists) wrote: >> Ping. >> >> On 27/10/15 17:03, Andre Vieira wrote: >>> Ping. >>> >>> BR, >>> Andre >>> >>> On 13/10/15 18:01, Andre Vieira wrote: This patch ports the aeabi_idiv routine from Linaro Cortex-Strings (https://git.linaro.org/toolchain/cortex-strings.git), which was contributed by ARM under Free BSD license. The new aeabi_idiv routine is used to replace the one in libgcc/config/arm/lib1funcs.S. This replacement happens within the Thumb1 wrapper. The new routine is under LGPLv3 license. The main advantage of this version is that it can improve the performance of the aeabi_idiv function for Thumb1. This solution will also increase the code size. So it will only be used if __OPTIMIZE_SIZE__ is not defined. Make check passed for armv6-m. libgcc/ChangeLog: 2015-08-10 Hale WangAndre Vieira * config/arm/lib1funcs.S: Add new wrapper. >> >
[PING^3][PATCHv2, ARM, libgcc] New aeabi_idiv function for armv6-m
Ping for GCC-7, patch applies cleanly, passed make check for cortex-m0. Might be worth mentioning that this patch has been used in three releases of the GNU ARM embedded toolchain, using GCC versions 4.9 and 5, and no issues have been reported so far. On 25/01/16 17:15, Andre Vieira (lists) wrote: > Ping. > > On 27/10/15 17:03, Andre Vieira wrote: >> Ping. >> >> BR, >> Andre >> >> On 13/10/15 18:01, Andre Vieira wrote: >>> This patch ports the aeabi_idiv routine from Linaro Cortex-Strings >>> (https://git.linaro.org/toolchain/cortex-strings.git), which was >>> contributed by ARM under Free BSD license. >>> >>> The new aeabi_idiv routine is used to replace the one in >>> libgcc/config/arm/lib1funcs.S. This replacement happens within the >>> Thumb1 wrapper. The new routine is under LGPLv3 license. >>> >>> The main advantage of this version is that it can improve the >>> performance of the aeabi_idiv function for Thumb1. This solution will >>> also increase the code size. So it will only be used if >>> __OPTIMIZE_SIZE__ is not defined. >>> >>> Make check passed for armv6-m. >>> >>> libgcc/ChangeLog: >>> 2015-08-10 Hale Wang>>> Andre Vieira >>> >>> * config/arm/lib1funcs.S: Add new wrapper. >>> >
Re: [PING^2][PATCHv2, ARM, libgcc] New aeabi_idiv function for armv6-m
Ping. On 27/10/15 17:03, Andre Vieira wrote: Ping. BR, Andre On 13/10/15 18:01, Andre Vieira wrote: This patch ports the aeabi_idiv routine from Linaro Cortex-Strings (https://git.linaro.org/toolchain/cortex-strings.git), which was contributed by ARM under Free BSD license. The new aeabi_idiv routine is used to replace the one in libgcc/config/arm/lib1funcs.S. This replacement happens within the Thumb1 wrapper. The new routine is under LGPLv3 license. The main advantage of this version is that it can improve the performance of the aeabi_idiv function for Thumb1. This solution will also increase the code size. So it will only be used if __OPTIMIZE_SIZE__ is not defined. Make check passed for armv6-m. libgcc/ChangeLog: 2015-08-10 Hale WangAndre Vieira * config/arm/lib1funcs.S: Add new wrapper.
[arm-embedded][PATCHv2, ARM, libgcc] New aeabi_idiv function for armv6-m
We decided to apply this to ARM/embedded-5-branch. Best regards, Thomas > -Original Message- > From: gcc-patches-ow...@gcc.gnu.org [mailto:gcc-patches- > ow...@gcc.gnu.org] On Behalf Of Andre Vieira > Sent: Wednesday, October 28, 2015 1:03 AM > To: gcc-patches@gcc.gnu.org > Subject: Re: [PING][PATCHv2, ARM, libgcc] New aeabi_idiv function for > armv6-m > > Ping. > > BR, > Andre > > On 13/10/15 18:01, Andre Vieira wrote: > > This patch ports the aeabi_idiv routine from Linaro Cortex-Strings > > (https://git.linaro.org/toolchain/cortex-strings.git), which was > > contributed by ARM under Free BSD license. > > > > The new aeabi_idiv routine is used to replace the one in > > libgcc/config/arm/lib1funcs.S. This replacement happens within the > > Thumb1 wrapper. The new routine is under LGPLv3 license. > > > > The main advantage of this version is that it can improve the > > performance of the aeabi_idiv function for Thumb1. This solution will > > also increase the code size. So it will only be used if > > __OPTIMIZE_SIZE__ is not defined. > > > > Make check passed for armv6-m. > > > > libgcc/ChangeLog: > > 2015-08-10 Hale Wang <hale.w...@arm.com> > > Andre Vieira <andre.simoesdiasvie...@arm.com> > > > > * config/arm/lib1funcs.S: Add new wrapper. > >
Re: [PING][PATCHv2, ARM, libgcc] New aeabi_idiv function for armv6-m
Ping. BR, Andre On 13/10/15 18:01, Andre Vieira wrote: This patch ports the aeabi_idiv routine from Linaro Cortex-Strings (https://git.linaro.org/toolchain/cortex-strings.git), which was contributed by ARM under Free BSD license. The new aeabi_idiv routine is used to replace the one in libgcc/config/arm/lib1funcs.S. This replacement happens within the Thumb1 wrapper. The new routine is under LGPLv3 license. The main advantage of this version is that it can improve the performance of the aeabi_idiv function for Thumb1. This solution will also increase the code size. So it will only be used if __OPTIMIZE_SIZE__ is not defined. Make check passed for armv6-m. libgcc/ChangeLog: 2015-08-10 Hale WangAndre Vieira * config/arm/lib1funcs.S: Add new wrapper.
[PATCHv2, ARM, libgcc] New aeabi_idiv function for armv6-m
This patch ports the aeabi_idiv routine from Linaro Cortex-Strings (https://git.linaro.org/toolchain/cortex-strings.git), which was contributed by ARM under Free BSD license. The new aeabi_idiv routine is used to replace the one in libgcc/config/arm/lib1funcs.S. This replacement happens within the Thumb1 wrapper. The new routine is under LGPLv3 license. The main advantage of this version is that it can improve the performance of the aeabi_idiv function for Thumb1. This solution will also increase the code size. So it will only be used if __OPTIMIZE_SIZE__ is not defined. Make check passed for armv6-m. libgcc/ChangeLog: 2015-08-10 Hale WangAndre Vieira * config/arm/lib1funcs.S: Add new wrapper. From 832a3d6af6f06399f70b5a4ac3727d55960c93b7 Mon Sep 17 00:00:00 2001 From: Andre Simoes Dias Vieira Date: Fri, 21 Aug 2015 14:23:28 +0100 Subject: [PATCH] new wrapper idivmod --- libgcc/config/arm/lib1funcs.S | 250 -- 1 file changed, 217 insertions(+), 33 deletions(-) diff --git a/libgcc/config/arm/lib1funcs.S b/libgcc/config/arm/lib1funcs.S index 252efcbd5385cc58a5ce1e48c6816d36a6f4c797..c9e544114590da8cde88382bea0f67206e593816 100644 --- a/libgcc/config/arm/lib1funcs.S +++ b/libgcc/config/arm/lib1funcs.S @@ -306,34 +306,12 @@ LSYM(Lend_fde): #ifdef __ARM_EABI__ .macro THUMB_LDIV0 name signed #if defined(__ARM_ARCH_6M__) - .ifc \signed, unsigned - cmp r0, #0 - beq 1f - mov r0, #0 - mvn r0, r0 @ 0x -1: - .else - cmp r0, #0 - beq 2f - blt 3f + + push {r0, lr} mov r0, #0 - mvn r0, r0 - lsr r0, r0, #1 @ 0x7fff - b 2f -3: mov r0, #0x80 - lsl r0, r0, #24 @ 0x8000 -2: - .endif - push {r0, r1, r2} - ldr r0, 4f - adr r1, 4f - add r0, r1 - str r0, [sp, #8] - @ We know we are not on armv4t, so pop pc is safe. - pop {r0, r1, pc} - .align 2 -4: - .word __aeabi_idiv0 - 4b + bl SYM(__aeabi_idiv0) + pop {r1, pc} + #elif defined(__thumb2__) .syntax unified .ifc \signed, unsigned @@ -945,7 +923,170 @@ LSYM(Lover7): add dividend, work .endif LSYM(Lgot_result): -.endm +.endm + +#if defined(__prefer_thumb__) && !defined(__OPTIMIZE_SIZE__) +/* If performance is preferred, the following functions are provided. */ + +/* Branch to div(n), and jump to label if curbit is lo than divisior. */ +.macro BranchToDiv n, label + lsr curbit, dividend, \n + cmp curbit, divisor + blo \label +.endm + +/* Body of div(n). Shift the divisor in n bits and compare the divisor + and dividend. Update the dividend as the substruction result. */ +.macro DoDiv n + lsr curbit, dividend, \n + cmp curbit, divisor + bcc 1f + lsl curbit, divisor, \n + sub dividend, dividend, curbit + +1: adc result, result +.endm + +/* The body of division with positive divisor. Unless the divisor is very + big, shift it up in multiples of four bits, since this is the amount of + unwinding in the main division loop. Continue shifting until the divisor + is larger than the dividend. */ +.macro THUMB1_Div_Positive + mov result, #0 + BranchToDiv #1, LSYM(Lthumb1_div1) + BranchToDiv #4, LSYM(Lthumb1_div4) + BranchToDiv #8, LSYM(Lthumb1_div8) + BranchToDiv #12, LSYM(Lthumb1_div12) + BranchToDiv #16, LSYM(Lthumb1_div16) +LSYM(Lthumb1_div_large_positive): + mov result, #0xff + lsl divisor, divisor, #8 + rev result, result + lsr curbit, dividend, #16 + cmp curbit, divisor + blo 1f + asr result, #8 + lsl divisor, divisor, #8 + beq LSYM(Ldivbyzero_waypoint) + +1: lsr curbit, dividend, #12 + cmp curbit, divisor + blo LSYM(Lthumb1_div12) + b LSYM(Lthumb1_div16) +LSYM(Lthumb1_div_loop): + lsr divisor, divisor, #8 +LSYM(Lthumb1_div16): + Dodiv #15 + Dodiv #14 + Dodiv #13 + Dodiv #12 +LSYM(Lthumb1_div12): + Dodiv #11 + Dodiv #10 + Dodiv #9 + Dodiv #8 + bcs LSYM(Lthumb1_div_loop) +LSYM(Lthumb1_div8): + Dodiv #7 + Dodiv #6 + Dodiv #5 +LSYM(Lthumb1_div5): + Dodiv #4 +LSYM(Lthumb1_div4): + Dodiv #3 +LSYM(Lthumb1_div3): + Dodiv #2 +LSYM(Lthumb1_div2): + Dodiv #1 +LSYM(Lthumb1_div1): + sub divisor, dividend, divisor + bcs 1f + cpy divisor, dividend + +1: adc result, result + cpy dividend, result + RET + +LSYM(Ldivbyzero_waypoint): + b LSYM(Ldiv0) +.endm + +/* The body of division with negative divisor. Similar with + THUMB1_Div_Positive except that the shift steps are in multiples + of six bits. */ +.macro THUMB1_Div_Negative + lsr result, divisor, #31 + beq 1f + neg divisor, divisor + +1: asr curbit, dividend, #32 + bcc 2f + neg dividend, dividend + +2: eor curbit, result + mov result, #0 + cpy ip, curbit + BranchToDiv #4, LSYM(Lthumb1_div_negative4) + BranchToDiv #8, LSYM(Lthumb1_div_negative8) +LSYM(Lthumb1_div_large): + mov result, #0xfc + lsl divisor, divisor, #6 + rev result, result + lsr curbit, dividend, #8 + cmp curbit, divisor + blo LSYM(Lthumb1_div_negative8) + + lsl divisor, divisor, #6 + asr result, result, #6 + cmp curbit, divisor + blo LSYM(Lthumb1_div_negative8) + + lsl divisor,