| Message ID | 20230517061050.3778864-1-guojiufu@linux.ibm.com |
|---|---|
| State | New |
| Headers | show |
| Series | Optimized "(X - N * M) / N + M" to "X / N" if valid | expand |
On Wed, 17 May 2023, Jiufu Guo wrote: > Hi, > > This patch tries to optimize "(X - N * M) / N + M" to "X / N". But if that's valid why not make the transform simpler and transform (X - N * M) / N to X / N - M instead? You use the same optimize_x_minus_NM_div_N_plus_M validator for the division and shift variants but the overflow rules are different, so I'm not sure that's warranted. I'd also prefer to not split out the validator to a different file - iff then the appropriate file is fold-const.cc, not gimple-match-head.cc (I see we're a bit inconsistent here, for pure gimple matches gimple-fold.cc would be another place). Since you use range information why is the transform restricted to constant M? Richard. > As per the discussions in PR108757, we know this transformation is valid > only under some conditions. > For C code, "/" towards zero (trunc_div), and "X - N * M" > maybe wrap/overflow/underflow. So, it is valid that "X - N * M" does > not cross zero and does not wrap/overflow/underflow. > > This patch also handles the case when "N" is the power of 2, where > "(X - N * M) / N" is "(X - N * M) >> log2(N)". > > Bootstrap & regtest pass on ppc64{,le} and x86_64. > Is this ok for trunk? > > BR, > Jeff (Jiufu) > > PR tree-optimization/108757 > > gcc/ChangeLog: > > * gimple-match-head.cc (optimize_x_minus_NM_div_N_plus_M): New function. > * match.pd ((X - N * M) / N + M): New pattern. > > gcc/testsuite/ChangeLog: > > * gcc.dg/pr108757-1.c: New test. > * gcc.dg/pr108757-2.c: New test. > * gcc.dg/pr108757.h: New test. > > --- > gcc/gimple-match-head.cc | 54 ++++++++++ > gcc/match.pd | 22 ++++ > gcc/testsuite/gcc.dg/pr108757-1.c | 17 ++++ > gcc/testsuite/gcc.dg/pr108757-2.c | 18 ++++ > gcc/testsuite/gcc.dg/pr108757.h | 160 ++++++++++++++++++++++++++++++ > 5 files changed, 271 insertions(+) > create mode 100644 gcc/testsuite/gcc.dg/pr108757-1.c > create mode 100644 gcc/testsuite/gcc.dg/pr108757-2.c > create mode 100644 gcc/testsuite/gcc.dg/pr108757.h > > diff --git a/gcc/gimple-match-head.cc b/gcc/gimple-match-head.cc > index b08cd891a13..680a4cb2fc6 100644 > --- a/gcc/gimple-match-head.cc > +++ b/gcc/gimple-match-head.cc > @@ -224,3 +224,57 @@ optimize_successive_divisions_p (tree divisor, tree inner_div) > } > return true; > } > + > +/* Return true if "(X - N * M) / N + M" can be optimized into "X / N". > + Otherwise return false. > + > + For unsigned, > + If sign bit of M is 0 (clz is 0), valid range is [N*M, MAX]. > + If sign bit of M is 1, valid range is [0, MAX - N*(-M)]. > + > + For signed, > + If N*M > 0, valid range: [MIN+N*M, 0] + [N*M, MAX] > + If N*M < 0, valid range: [MIN, -(-N*M)] + [0, MAX - (-N*M)]. */ > + > +static bool > +optimize_x_minus_NM_div_N_plus_M (tree x, wide_int n, wide_int m, tree type) > +{ > + wide_int max = wi::max_value (type); > + signop sgn = TYPE_SIGN (type); > + wide_int nm; > + wi::overflow_type ovf; > + if (TYPE_UNSIGNED (type) && wi::clz (m) == 0) > + nm = wi::mul (n, -m, sgn, &ovf); > + else > + nm = wi::mul (n, m, sgn, &ovf); > + > + if (ovf != wi::OVF_NONE) > + return false; > + > + value_range vr0; > + if (!get_range_query (cfun)->range_of_expr (vr0, x) || vr0.varying_p () > + || vr0.undefined_p ()) > + return false; > + > + wide_int wmin0 = vr0.lower_bound (); > + wide_int wmax0 = vr0.upper_bound (); > + wide_int min = wi::min_value (type); > + > + /* unsigned */ > + if ((TYPE_UNSIGNED (type))) > + /* M > 0 (clz != 0): [N*M, MAX], M < 0 : [0, MAX-N*(-M)] */ > + return wi::clz (m) != 0 ? wi::ge_p (wmin0, nm, sgn) > + : wi::le_p (wmax0, max - nm, sgn); > + > + /* signed, N*M > 0 */ > + else if (wi::gt_p (nm, 0, sgn)) > + /* [N*M, MAX] or [MIN+N*M, 0] */ > + return wi::ge_p (wmin0, nm, sgn) > + || (wi::ge_p (wmin0, min + nm, sgn) && wi::le_p (wmax0, 0, sgn)); > + > + /* signed, N*M < 0 */ > + /* [MIN, N*M] or [0, MAX + N*M]*/ > + else > + return wi::le_p (wmax0, nm, sgn) > + || (wi::ge_p (wmin0, 0, sgn) && wi::le_p (wmax0, max - (-nm), sgn)); > +} > diff --git a/gcc/match.pd b/gcc/match.pd > index ceae1c34abc..1aaa5530577 100644 > --- a/gcc/match.pd > +++ b/gcc/match.pd > @@ -881,6 +881,28 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) > #endif > )))) > > +#if GIMPLE > +/* Simplify ((t + -N*M) / N + M) -> t / N. */ > +(for div (trunc_div exact_div) > + (simplify > + (plus (div (plus @0 INTEGER_CST@1) INTEGER_CST@2) INTEGER_CST@3) > + (with {wide_int n = wi::to_wide (@2); wide_int m = wi::to_wide (@3);} > + (if (INTEGRAL_TYPE_P (type) > + && n * m == -wi::to_wide (@1) > + && optimize_x_minus_NM_div_N_plus_M (@0, n, m, type)) > + (div @0 @2))))) > + > +/* Simplify ((t + -(M<<N)) >> N + M) -> t >> N. */ > +(simplify > + (plus (rshift (plus @0 INTEGER_CST@1) INTEGER_CST@2) INTEGER_CST@3) > + (with {wide_int n = wi::to_wide (@2); wide_int m = wi::to_wide (@3);} > + (if (INTEGRAL_TYPE_P (type) > + && (m << n) == -wi::to_wide (@1) > + && optimize_x_minus_NM_div_N_plus_M (@0, > + wi::one (TYPE_PRECISION (type)) << n, m, type)) > + (rshift @0 @2)))) > +#endif > + > (for op (negate abs) > /* Simplify cos(-x) and cos(|x|) -> cos(x). Similarly for cosh. */ > (for coss (COS COSH) > diff --git a/gcc/testsuite/gcc.dg/pr108757-1.c b/gcc/testsuite/gcc.dg/pr108757-1.c > new file mode 100644 > index 00000000000..349318a7c82 > --- /dev/null > +++ b/gcc/testsuite/gcc.dg/pr108757-1.c > @@ -0,0 +1,17 @@ > +/* PR tree-optimization/108757 */ > +/* { dg-do compile } */ > +/* { dg-options "-O2 -fdump-tree-optimized" } */ > + > +#include <limits.h> > +#define N 4 > +#define M 3 > +#define GAP 0 > +typedef unsigned int UINT; > +typedef int INT; > +#define UMAX UINT_MAX > +#define IMAX INT_MAX > +#define IMIN INT_MIN > +#include "pr108757.h" > + > +/* { dg-final { scan-tree-dump-not " = x_\[0-9\]\\(D\\) \\+ " "optimized" } } */ > +/* { dg-final { scan-tree-dump-not " = b_\[0-9\] \\+ " "optimized" } } */ > diff --git a/gcc/testsuite/gcc.dg/pr108757-2.c b/gcc/testsuite/gcc.dg/pr108757-2.c > new file mode 100644 > index 00000000000..7302e9c606c > --- /dev/null > +++ b/gcc/testsuite/gcc.dg/pr108757-2.c > @@ -0,0 +1,18 @@ > +/* PR tree-optimization/108757 */ > +/* { dg-do compile } */ > +/* { dg-options "-O2 -fdump-tree-optimized" } */ > + > +#include <limits.h> > +#define N 4 > +#define M 3 > +#define GAP 2 > +typedef unsigned int UINT; > +typedef int INT; > +#define UMAX UINT_MAX > +#define IMAX INT_MAX > +#define IMIN INT_MIN > +#include "pr108757.h" > + > +/* { dg-final { scan-tree-dump-times " = x_\[0-9\]\\(D\\) \\+ " 16 "optimized" } } */ > +/* { dg-final { scan-tree-dump-times " = b_\[0-9\] \\+ " 16 "optimized" } } */ > + > diff --git a/gcc/testsuite/gcc.dg/pr108757.h b/gcc/testsuite/gcc.dg/pr108757.h > new file mode 100644 > index 00000000000..9e12d106aad > --- /dev/null > +++ b/gcc/testsuite/gcc.dg/pr108757.h > @@ -0,0 +1,160 @@ > +#define NOINLINE __attribute__ ((noinline)) > +UINT NOINLINE > +opt_u1 (UINT x) > +{ > + if (x < (M * N) - GAP) > + return 0; > + UINT a = x - (M * N); > + UINT b = a / N; > + return b + M; > +} > + > +UINT NOINLINE > +opt_u2 (UINT x) > +{ > + if (x > (UMAX - (M * N) + GAP)) > + return 0; > + UINT a = x + (M * N); > + UINT b = a / N; > + return b - M; > +} > + > +INT NOINLINE > +opt_s1 (INT x) > +{ > + if (x < (M * N) - GAP) > + return 0; > + INT a = x - (M * N); > + INT b = a / N; > + return b + M; > +} > + > +INT NOINLINE > +opt_s2 (INT x) > +{ > + if (x < IMIN + (M * N) - GAP || x > 0) > + return 0; > + INT a = x - (M * N); > + INT b = a / N; > + return b + M; > +} > + > +INT NOINLINE > +opt_s3 (INT x) > +{ > + if (x < (M * N) - GAP) > + return 0; > + INT a = x - (M * N); > + INT b = a / -N; > + return b + -M; > +} > + > +INT NOINLINE > +opt_s4 (INT x) > +{ > + if (x < IMIN + (M * N) - GAP || x > 0) > + return 0; > + INT a = x - (M * N); > + INT b = a / -N; > + return b + -M; > +} > + > +INT NOINLINE > +opt_s5 (INT x) > +{ > + if (x > (-M * N) + GAP) > + return 0; > + INT a = x - (-M * N); > + INT b = a / N; > + return b + -M; > +} > + > +INT NOINLINE > +opt_s6 (INT x) > +{ > + if (x > IMAX - (M * N) + GAP || x < 0) > + return 0; > + INT a = x - (-M * N); > + INT b = a / N; > + return b + -M; > +} > + > +INT NOINLINE > +opt_s7 (INT x) > +{ > + if (x > (M * -N) + GAP) > + return 0; > + INT a = x - (M * -N); > + INT b = a / -N; > + return b + M; > +} > + > +INT NOINLINE > +opt_s8 (INT x) > +{ > + if (x > IMAX - (M * N) + GAP || x < 0) > + return 0; > + INT a = x - (M * -N); > + INT b = a / -N; > + return b + M; > +} > + > +UINT NOINLINE > +opt_u3 (UINT x) > +{ > + if (x < (M << N) - GAP) > + return 0; > + UINT a = x - (M << N); > + UINT b = a >> N; > + return b + M; > +} > + > +UINT NOINLINE > +opt_u4 (UINT x) > +{ > + if (x > (UMAX - (M << N)) + GAP) > + return 0; > + UINT a = x + (M << N); > + UINT b = a >> N; > + return b - M; > +} > + > +INT NOINLINE > +opt_s9 (INT x) > +{ > + if (x < (M << N) - GAP) > + return 0; > + INT a = x - (M << N); > + INT b = a >> N; > + return b + M; > +} > + > +INT NOINLINE > +opt_s10 (INT x) > +{ > + if (x < IMIN + (M << N) - GAP || x > 0) > + return 0; > + INT a = x - (M << N); > + INT b = a >> N; > + return b + M; > +} > + > +INT NOINLINE > +opt_s11 (INT x) > +{ > + if (x > (-M << N) + GAP) > + return 0; > + INT a = x - (-M << N); > + INT b = a >> N; > + return b + -M; > +} > + > +INT NOINLINE > +opt_s12 (INT x) > +{ > + if (x > IMAX - (M << N) + GAP || x < 0) > + return 0; > + INT a = x - (-M << N); > + INT b = a >> N; > + return b + -M; > +} >
Hi, Richard Biener <rguenther@suse.de> writes: > On Wed, 17 May 2023, Jiufu Guo wrote: > >> Hi, >> >> This patch tries to optimize "(X - N * M) / N + M" to "X / N". > > But if that's valid why not make the transform simpler and transform > (X - N * M) / N to X / N - M instead? Great catch! If "N * M" is not constant, "X / N - M" would be better than "(X - N * M) / N". If "N, M" are constants, "(X - N * M) / N" and "X / N - M" may be similar; while for this case, "X / N - M" should also be fine! I would try to update accordingly. > > You use the same optimize_x_minus_NM_div_N_plus_M validator for > the division and shift variants but the overflow rules are different, > so I'm not sure that's warranted. I'd also prefer to not split out > the validator to a different file - iff then the appropriate file > is fold-const.cc, not gimple-match-head.cc (I see we're a bit > inconsistent here, for pure gimple matches gimple-fold.cc would > be another place). Thanks for pointing out this! For shift, I guess you may concern that: 1. if the right operand is negative or is greater than or equal to the type width. 2. if it is a signed negative value. They may UB or 'sign bit shift'? This patch assumes it is ok to do the transform. I may have more check to see if this is really ok, and hope some one can point out if this is invalid. "(X - N * M) >> log2(N)" ==> " X >> log2(N) - M". I split out the validator just because: it is shared for division and shift :). And it seems gimple-match-head.cc and generic-match-head.cc, may be introduced for match.pd. So, I put it into gimple-match-head.cc. > > Since you use range information why is the transform restricted > to constant M? If M is a variable, the range for "X" is varying_p. I did not find the method to get the bounds for "X" (or for "X - N * M") to check no wraps. Any suggestions? Again, thanks for your great help! BR, Jeff (Jiufu Guo) > > Richard. > >> As per the discussions in PR108757, we know this transformation is valid >> only under some conditions. >> For C code, "/" towards zero (trunc_div), and "X - N * M" >> maybe wrap/overflow/underflow. So, it is valid that "X - N * M" does >> not cross zero and does not wrap/overflow/underflow. >> >> This patch also handles the case when "N" is the power of 2, where >> "(X - N * M) / N" is "(X - N * M) >> log2(N)". >> >> Bootstrap & regtest pass on ppc64{,le} and x86_64. >> Is this ok for trunk? >> >> BR, >> Jeff (Jiufu) >> >> PR tree-optimization/108757 >> >> gcc/ChangeLog: >> >> * gimple-match-head.cc (optimize_x_minus_NM_div_N_plus_M): New function. >> * match.pd ((X - N * M) / N + M): New pattern. >> >> gcc/testsuite/ChangeLog: >> >> * gcc.dg/pr108757-1.c: New test. >> * gcc.dg/pr108757-2.c: New test. >> * gcc.dg/pr108757.h: New test. >> >> --- >> gcc/gimple-match-head.cc | 54 ++++++++++ >> gcc/match.pd | 22 ++++ >> gcc/testsuite/gcc.dg/pr108757-1.c | 17 ++++ >> gcc/testsuite/gcc.dg/pr108757-2.c | 18 ++++ >> gcc/testsuite/gcc.dg/pr108757.h | 160 ++++++++++++++++++++++++++++++ >> 5 files changed, 271 insertions(+) >> create mode 100644 gcc/testsuite/gcc.dg/pr108757-1.c >> create mode 100644 gcc/testsuite/gcc.dg/pr108757-2.c >> create mode 100644 gcc/testsuite/gcc.dg/pr108757.h >> >> diff --git a/gcc/gimple-match-head.cc b/gcc/gimple-match-head.cc >> index b08cd891a13..680a4cb2fc6 100644 >> --- a/gcc/gimple-match-head.cc >> +++ b/gcc/gimple-match-head.cc >> @@ -224,3 +224,57 @@ optimize_successive_divisions_p (tree divisor, tree inner_div) >> } >> return true; >> } >> + >> +/* Return true if "(X - N * M) / N + M" can be optimized into "X / N". >> + Otherwise return false. >> + >> + For unsigned, >> + If sign bit of M is 0 (clz is 0), valid range is [N*M, MAX]. >> + If sign bit of M is 1, valid range is [0, MAX - N*(-M)]. >> + >> + For signed, >> + If N*M > 0, valid range: [MIN+N*M, 0] + [N*M, MAX] >> + If N*M < 0, valid range: [MIN, -(-N*M)] + [0, MAX - (-N*M)]. */ >> + >> +static bool >> +optimize_x_minus_NM_div_N_plus_M (tree x, wide_int n, wide_int m, tree type) >> +{ >> + wide_int max = wi::max_value (type); >> + signop sgn = TYPE_SIGN (type); >> + wide_int nm; >> + wi::overflow_type ovf; >> + if (TYPE_UNSIGNED (type) && wi::clz (m) == 0) >> + nm = wi::mul (n, -m, sgn, &ovf); >> + else >> + nm = wi::mul (n, m, sgn, &ovf); >> + >> + if (ovf != wi::OVF_NONE) >> + return false; >> + >> + value_range vr0; >> + if (!get_range_query (cfun)->range_of_expr (vr0, x) || vr0.varying_p () >> + || vr0.undefined_p ()) >> + return false; >> + >> + wide_int wmin0 = vr0.lower_bound (); >> + wide_int wmax0 = vr0.upper_bound (); >> + wide_int min = wi::min_value (type); >> + >> + /* unsigned */ >> + if ((TYPE_UNSIGNED (type))) >> + /* M > 0 (clz != 0): [N*M, MAX], M < 0 : [0, MAX-N*(-M)] */ >> + return wi::clz (m) != 0 ? wi::ge_p (wmin0, nm, sgn) >> + : wi::le_p (wmax0, max - nm, sgn); >> + >> + /* signed, N*M > 0 */ >> + else if (wi::gt_p (nm, 0, sgn)) >> + /* [N*M, MAX] or [MIN+N*M, 0] */ >> + return wi::ge_p (wmin0, nm, sgn) >> + || (wi::ge_p (wmin0, min + nm, sgn) && wi::le_p (wmax0, 0, sgn)); >> + >> + /* signed, N*M < 0 */ >> + /* [MIN, N*M] or [0, MAX + N*M]*/ >> + else >> + return wi::le_p (wmax0, nm, sgn) >> + || (wi::ge_p (wmin0, 0, sgn) && wi::le_p (wmax0, max - (-nm), sgn)); >> +} >> diff --git a/gcc/match.pd b/gcc/match.pd >> index ceae1c34abc..1aaa5530577 100644 >> --- a/gcc/match.pd >> +++ b/gcc/match.pd >> @@ -881,6 +881,28 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) >> #endif >> )))) >> >> +#if GIMPLE >> +/* Simplify ((t + -N*M) / N + M) -> t / N. */ >> +(for div (trunc_div exact_div) >> + (simplify >> + (plus (div (plus @0 INTEGER_CST@1) INTEGER_CST@2) INTEGER_CST@3) >> + (with {wide_int n = wi::to_wide (@2); wide_int m = wi::to_wide (@3);} >> + (if (INTEGRAL_TYPE_P (type) >> + && n * m == -wi::to_wide (@1) >> + && optimize_x_minus_NM_div_N_plus_M (@0, n, m, type)) >> + (div @0 @2))))) >> + >> +/* Simplify ((t + -(M<<N)) >> N + M) -> t >> N. */ >> +(simplify >> + (plus (rshift (plus @0 INTEGER_CST@1) INTEGER_CST@2) INTEGER_CST@3) >> + (with {wide_int n = wi::to_wide (@2); wide_int m = wi::to_wide (@3);} >> + (if (INTEGRAL_TYPE_P (type) >> + && (m << n) == -wi::to_wide (@1) >> + && optimize_x_minus_NM_div_N_plus_M (@0, >> + wi::one (TYPE_PRECISION (type)) << n, m, type)) >> + (rshift @0 @2)))) >> +#endif >> + >> (for op (negate abs) >> /* Simplify cos(-x) and cos(|x|) -> cos(x). Similarly for cosh. */ >> (for coss (COS COSH) >> diff --git a/gcc/testsuite/gcc.dg/pr108757-1.c b/gcc/testsuite/gcc.dg/pr108757-1.c >> new file mode 100644 >> index 00000000000..349318a7c82 >> --- /dev/null >> +++ b/gcc/testsuite/gcc.dg/pr108757-1.c >> @@ -0,0 +1,17 @@ >> +/* PR tree-optimization/108757 */ >> +/* { dg-do compile } */ >> +/* { dg-options "-O2 -fdump-tree-optimized" } */ >> + >> +#include <limits.h> >> +#define N 4 >> +#define M 3 >> +#define GAP 0 >> +typedef unsigned int UINT; >> +typedef int INT; >> +#define UMAX UINT_MAX >> +#define IMAX INT_MAX >> +#define IMIN INT_MIN >> +#include "pr108757.h" >> + >> +/* { dg-final { scan-tree-dump-not " = x_\[0-9\]\\(D\\) \\+ " "optimized" } } */ >> +/* { dg-final { scan-tree-dump-not " = b_\[0-9\] \\+ " "optimized" } } */ >> diff --git a/gcc/testsuite/gcc.dg/pr108757-2.c b/gcc/testsuite/gcc.dg/pr108757-2.c >> new file mode 100644 >> index 00000000000..7302e9c606c >> --- /dev/null >> +++ b/gcc/testsuite/gcc.dg/pr108757-2.c >> @@ -0,0 +1,18 @@ >> +/* PR tree-optimization/108757 */ >> +/* { dg-do compile } */ >> +/* { dg-options "-O2 -fdump-tree-optimized" } */ >> + >> +#include <limits.h> >> +#define N 4 >> +#define M 3 >> +#define GAP 2 >> +typedef unsigned int UINT; >> +typedef int INT; >> +#define UMAX UINT_MAX >> +#define IMAX INT_MAX >> +#define IMIN INT_MIN >> +#include "pr108757.h" >> + >> +/* { dg-final { scan-tree-dump-times " = x_\[0-9\]\\(D\\) \\+ " 16 "optimized" } } */ >> +/* { dg-final { scan-tree-dump-times " = b_\[0-9\] \\+ " 16 "optimized" } } */ >> + >> diff --git a/gcc/testsuite/gcc.dg/pr108757.h b/gcc/testsuite/gcc.dg/pr108757.h >> new file mode 100644 >> index 00000000000..9e12d106aad >> --- /dev/null >> +++ b/gcc/testsuite/gcc.dg/pr108757.h >> @@ -0,0 +1,160 @@ >> +#define NOINLINE __attribute__ ((noinline)) >> +UINT NOINLINE >> +opt_u1 (UINT x) >> +{ >> + if (x < (M * N) - GAP) >> + return 0; >> + UINT a = x - (M * N); >> + UINT b = a / N; >> + return b + M; >> +} >> + >> +UINT NOINLINE >> +opt_u2 (UINT x) >> +{ >> + if (x > (UMAX - (M * N) + GAP)) >> + return 0; >> + UINT a = x + (M * N); >> + UINT b = a / N; >> + return b - M; >> +} >> + >> +INT NOINLINE >> +opt_s1 (INT x) >> +{ >> + if (x < (M * N) - GAP) >> + return 0; >> + INT a = x - (M * N); >> + INT b = a / N; >> + return b + M; >> +} >> + >> +INT NOINLINE >> +opt_s2 (INT x) >> +{ >> + if (x < IMIN + (M * N) - GAP || x > 0) >> + return 0; >> + INT a = x - (M * N); >> + INT b = a / N; >> + return b + M; >> +} >> + >> +INT NOINLINE >> +opt_s3 (INT x) >> +{ >> + if (x < (M * N) - GAP) >> + return 0; >> + INT a = x - (M * N); >> + INT b = a / -N; >> + return b + -M; >> +} >> + >> +INT NOINLINE >> +opt_s4 (INT x) >> +{ >> + if (x < IMIN + (M * N) - GAP || x > 0) >> + return 0; >> + INT a = x - (M * N); >> + INT b = a / -N; >> + return b + -M; >> +} >> + >> +INT NOINLINE >> +opt_s5 (INT x) >> +{ >> + if (x > (-M * N) + GAP) >> + return 0; >> + INT a = x - (-M * N); >> + INT b = a / N; >> + return b + -M; >> +} >> + >> +INT NOINLINE >> +opt_s6 (INT x) >> +{ >> + if (x > IMAX - (M * N) + GAP || x < 0) >> + return 0; >> + INT a = x - (-M * N); >> + INT b = a / N; >> + return b + -M; >> +} >> + >> +INT NOINLINE >> +opt_s7 (INT x) >> +{ >> + if (x > (M * -N) + GAP) >> + return 0; >> + INT a = x - (M * -N); >> + INT b = a / -N; >> + return b + M; >> +} >> + >> +INT NOINLINE >> +opt_s8 (INT x) >> +{ >> + if (x > IMAX - (M * N) + GAP || x < 0) >> + return 0; >> + INT a = x - (M * -N); >> + INT b = a / -N; >> + return b + M; >> +} >> + >> +UINT NOINLINE >> +opt_u3 (UINT x) >> +{ >> + if (x < (M << N) - GAP) >> + return 0; >> + UINT a = x - (M << N); >> + UINT b = a >> N; >> + return b + M; >> +} >> + >> +UINT NOINLINE >> +opt_u4 (UINT x) >> +{ >> + if (x > (UMAX - (M << N)) + GAP) >> + return 0; >> + UINT a = x + (M << N); >> + UINT b = a >> N; >> + return b - M; >> +} >> + >> +INT NOINLINE >> +opt_s9 (INT x) >> +{ >> + if (x < (M << N) - GAP) >> + return 0; >> + INT a = x - (M << N); >> + INT b = a >> N; >> + return b + M; >> +} >> + >> +INT NOINLINE >> +opt_s10 (INT x) >> +{ >> + if (x < IMIN + (M << N) - GAP || x > 0) >> + return 0; >> + INT a = x - (M << N); >> + INT b = a >> N; >> + return b + M; >> +} >> + >> +INT NOINLINE >> +opt_s11 (INT x) >> +{ >> + if (x > (-M << N) + GAP) >> + return 0; >> + INT a = x - (-M << N); >> + INT b = a >> N; >> + return b + -M; >> +} >> + >> +INT NOINLINE >> +opt_s12 (INT x) >> +{ >> + if (x > IMAX - (M << N) + GAP || x < 0) >> + return 0; >> + INT a = x - (-M << N); >> + INT b = a >> N; >> + return b + -M; >> +} >>
Hi, Jiufu Guo via Gcc-patches <gcc-patches@gcc.gnu.org> writes: > Hi, > > Richard Biener <rguenther@suse.de> writes: > >> On Wed, 17 May 2023, Jiufu Guo wrote: >> >>> Hi, >>> >>> This patch tries to optimize "(X - N * M) / N + M" to "X / N". >> >> But if that's valid why not make the transform simpler and transform >> (X - N * M) / N to X / N - M instead? > > Great catch! > If "N * M" is not constant, "X / N - M" would be better than > "(X - N * M) / N". If "N, M" are constants, "(X - N * M) / N" and > "X / N - M" may be similar; while for this case, "X / N - M" should > also be fine! I would try to update accordingly. > >> >> You use the same optimize_x_minus_NM_div_N_plus_M validator for >> the division and shift variants but the overflow rules are different, >> so I'm not sure that's warranted. I'd also prefer to not split out >> the validator to a different file - iff then the appropriate file >> is fold-const.cc, not gimple-match-head.cc (I see we're a bit >> inconsistent here, for pure gimple matches gimple-fold.cc would >> be another place). > > Thanks for pointing out this! > For shift, I guess you may concern that: 1. if the right operand is > negative or is greater than or equal to the type width. 2. if it is > a signed negative value. They may UB or 'sign bit shift'? This patch > assumes it is ok to do the transform. I may have more check to see > if this is really ok, and hope some one can point out if this is > invalid. "(X - N * M) >> log2(N)" ==> " X >> log2(N) - M". > > I split out the validator just because: it is shared for division and > shift :). And it seems gimple-match-head.cc and generic-match-head.cc, > may be introduced for match.pd. So, I put it into gimple-match-head.cc. > >> >> Since you use range information why is the transform restricted >> to constant M? > > If M is a variable, the range for "X" is varying_p. I did not find > the method to get the bounds for "X" (or for "X - N * M") to check no > wraps. Any suggestions? Oh, I may misunderstand here. You may say: M could be with a range too, then we can check if "X - N * M" has a valid range or possible wrap/overflow. BR, Jeff (Jiufu Guo) > > > Again, thanks for your great help! > > BR, > Jeff (Jiufu Guo) > >> >> Richard. >> >>> As per the discussions in PR108757, we know this transformation is valid >>> only under some conditions. >>> For C code, "/" towards zero (trunc_div), and "X - N * M" >>> maybe wrap/overflow/underflow. So, it is valid that "X - N * M" does >>> not cross zero and does not wrap/overflow/underflow. >>> >>> This patch also handles the case when "N" is the power of 2, where >>> "(X - N * M) / N" is "(X - N * M) >> log2(N)". >>> >>> Bootstrap & regtest pass on ppc64{,le} and x86_64. >>> Is this ok for trunk? >>> >>> BR, >>> Jeff (Jiufu) >>> >>> PR tree-optimization/108757 >>> >>> gcc/ChangeLog: >>> >>> * gimple-match-head.cc (optimize_x_minus_NM_div_N_plus_M): New function. >>> * match.pd ((X - N * M) / N + M): New pattern. >>> >>> gcc/testsuite/ChangeLog: >>> >>> * gcc.dg/pr108757-1.c: New test. >>> * gcc.dg/pr108757-2.c: New test. >>> * gcc.dg/pr108757.h: New test. >>> >>> --- >>> gcc/gimple-match-head.cc | 54 ++++++++++ >>> gcc/match.pd | 22 ++++ >>> gcc/testsuite/gcc.dg/pr108757-1.c | 17 ++++ >>> gcc/testsuite/gcc.dg/pr108757-2.c | 18 ++++ >>> gcc/testsuite/gcc.dg/pr108757.h | 160 ++++++++++++++++++++++++++++++ >>> 5 files changed, 271 insertions(+) >>> create mode 100644 gcc/testsuite/gcc.dg/pr108757-1.c >>> create mode 100644 gcc/testsuite/gcc.dg/pr108757-2.c >>> create mode 100644 gcc/testsuite/gcc.dg/pr108757.h >>> >>> diff --git a/gcc/gimple-match-head.cc b/gcc/gimple-match-head.cc >>> index b08cd891a13..680a4cb2fc6 100644 >>> --- a/gcc/gimple-match-head.cc >>> +++ b/gcc/gimple-match-head.cc >>> @@ -224,3 +224,57 @@ optimize_successive_divisions_p (tree divisor, tree inner_div) >>> } >>> return true; >>> } >>> + >>> +/* Return true if "(X - N * M) / N + M" can be optimized into "X / N". >>> + Otherwise return false. >>> + >>> + For unsigned, >>> + If sign bit of M is 0 (clz is 0), valid range is [N*M, MAX]. >>> + If sign bit of M is 1, valid range is [0, MAX - N*(-M)]. >>> + >>> + For signed, >>> + If N*M > 0, valid range: [MIN+N*M, 0] + [N*M, MAX] >>> + If N*M < 0, valid range: [MIN, -(-N*M)] + [0, MAX - (-N*M)]. */ >>> + >>> +static bool >>> +optimize_x_minus_NM_div_N_plus_M (tree x, wide_int n, wide_int m, tree type) >>> +{ >>> + wide_int max = wi::max_value (type); >>> + signop sgn = TYPE_SIGN (type); >>> + wide_int nm; >>> + wi::overflow_type ovf; >>> + if (TYPE_UNSIGNED (type) && wi::clz (m) == 0) >>> + nm = wi::mul (n, -m, sgn, &ovf); >>> + else >>> + nm = wi::mul (n, m, sgn, &ovf); >>> + >>> + if (ovf != wi::OVF_NONE) >>> + return false; >>> + >>> + value_range vr0; >>> + if (!get_range_query (cfun)->range_of_expr (vr0, x) || vr0.varying_p () >>> + || vr0.undefined_p ()) >>> + return false; >>> + >>> + wide_int wmin0 = vr0.lower_bound (); >>> + wide_int wmax0 = vr0.upper_bound (); >>> + wide_int min = wi::min_value (type); >>> + >>> + /* unsigned */ >>> + if ((TYPE_UNSIGNED (type))) >>> + /* M > 0 (clz != 0): [N*M, MAX], M < 0 : [0, MAX-N*(-M)] */ >>> + return wi::clz (m) != 0 ? wi::ge_p (wmin0, nm, sgn) >>> + : wi::le_p (wmax0, max - nm, sgn); >>> + >>> + /* signed, N*M > 0 */ >>> + else if (wi::gt_p (nm, 0, sgn)) >>> + /* [N*M, MAX] or [MIN+N*M, 0] */ >>> + return wi::ge_p (wmin0, nm, sgn) >>> + || (wi::ge_p (wmin0, min + nm, sgn) && wi::le_p (wmax0, 0, sgn)); >>> + >>> + /* signed, N*M < 0 */ >>> + /* [MIN, N*M] or [0, MAX + N*M]*/ >>> + else >>> + return wi::le_p (wmax0, nm, sgn) >>> + || (wi::ge_p (wmin0, 0, sgn) && wi::le_p (wmax0, max - (-nm), sgn)); >>> +} >>> diff --git a/gcc/match.pd b/gcc/match.pd >>> index ceae1c34abc..1aaa5530577 100644 >>> --- a/gcc/match.pd >>> +++ b/gcc/match.pd >>> @@ -881,6 +881,28 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) >>> #endif >>> )))) >>> >>> +#if GIMPLE >>> +/* Simplify ((t + -N*M) / N + M) -> t / N. */ >>> +(for div (trunc_div exact_div) >>> + (simplify >>> + (plus (div (plus @0 INTEGER_CST@1) INTEGER_CST@2) INTEGER_CST@3) >>> + (with {wide_int n = wi::to_wide (@2); wide_int m = wi::to_wide (@3);} >>> + (if (INTEGRAL_TYPE_P (type) >>> + && n * m == -wi::to_wide (@1) >>> + && optimize_x_minus_NM_div_N_plus_M (@0, n, m, type)) >>> + (div @0 @2))))) >>> + >>> +/* Simplify ((t + -(M<<N)) >> N + M) -> t >> N. */ >>> +(simplify >>> + (plus (rshift (plus @0 INTEGER_CST@1) INTEGER_CST@2) INTEGER_CST@3) >>> + (with {wide_int n = wi::to_wide (@2); wide_int m = wi::to_wide (@3);} >>> + (if (INTEGRAL_TYPE_P (type) >>> + && (m << n) == -wi::to_wide (@1) >>> + && optimize_x_minus_NM_div_N_plus_M (@0, >>> + wi::one (TYPE_PRECISION (type)) << n, m, type)) >>> + (rshift @0 @2)))) >>> +#endif >>> + >>> (for op (negate abs) >>> /* Simplify cos(-x) and cos(|x|) -> cos(x). Similarly for cosh. */ >>> (for coss (COS COSH) >>> diff --git a/gcc/testsuite/gcc.dg/pr108757-1.c b/gcc/testsuite/gcc.dg/pr108757-1.c >>> new file mode 100644 >>> index 00000000000..349318a7c82 >>> --- /dev/null >>> +++ b/gcc/testsuite/gcc.dg/pr108757-1.c >>> @@ -0,0 +1,17 @@ >>> +/* PR tree-optimization/108757 */ >>> +/* { dg-do compile } */ >>> +/* { dg-options "-O2 -fdump-tree-optimized" } */ >>> + >>> +#include <limits.h> >>> +#define N 4 >>> +#define M 3 >>> +#define GAP 0 >>> +typedef unsigned int UINT; >>> +typedef int INT; >>> +#define UMAX UINT_MAX >>> +#define IMAX INT_MAX >>> +#define IMIN INT_MIN >>> +#include "pr108757.h" >>> + >>> +/* { dg-final { scan-tree-dump-not " = x_\[0-9\]\\(D\\) \\+ " "optimized" } } */ >>> +/* { dg-final { scan-tree-dump-not " = b_\[0-9\] \\+ " "optimized" } } */ >>> diff --git a/gcc/testsuite/gcc.dg/pr108757-2.c b/gcc/testsuite/gcc.dg/pr108757-2.c >>> new file mode 100644 >>> index 00000000000..7302e9c606c >>> --- /dev/null >>> +++ b/gcc/testsuite/gcc.dg/pr108757-2.c >>> @@ -0,0 +1,18 @@ >>> +/* PR tree-optimization/108757 */ >>> +/* { dg-do compile } */ >>> +/* { dg-options "-O2 -fdump-tree-optimized" } */ >>> + >>> +#include <limits.h> >>> +#define N 4 >>> +#define M 3 >>> +#define GAP 2 >>> +typedef unsigned int UINT; >>> +typedef int INT; >>> +#define UMAX UINT_MAX >>> +#define IMAX INT_MAX >>> +#define IMIN INT_MIN >>> +#include "pr108757.h" >>> + >>> +/* { dg-final { scan-tree-dump-times " = x_\[0-9\]\\(D\\) \\+ " 16 "optimized" } } */ >>> +/* { dg-final { scan-tree-dump-times " = b_\[0-9\] \\+ " 16 "optimized" } } */ >>> + >>> diff --git a/gcc/testsuite/gcc.dg/pr108757.h b/gcc/testsuite/gcc.dg/pr108757.h >>> new file mode 100644 >>> index 00000000000..9e12d106aad >>> --- /dev/null >>> +++ b/gcc/testsuite/gcc.dg/pr108757.h >>> @@ -0,0 +1,160 @@ >>> +#define NOINLINE __attribute__ ((noinline)) >>> +UINT NOINLINE >>> +opt_u1 (UINT x) >>> +{ >>> + if (x < (M * N) - GAP) >>> + return 0; >>> + UINT a = x - (M * N); >>> + UINT b = a / N; >>> + return b + M; >>> +} >>> + >>> +UINT NOINLINE >>> +opt_u2 (UINT x) >>> +{ >>> + if (x > (UMAX - (M * N) + GAP)) >>> + return 0; >>> + UINT a = x + (M * N); >>> + UINT b = a / N; >>> + return b - M; >>> +} >>> + >>> +INT NOINLINE >>> +opt_s1 (INT x) >>> +{ >>> + if (x < (M * N) - GAP) >>> + return 0; >>> + INT a = x - (M * N); >>> + INT b = a / N; >>> + return b + M; >>> +} >>> + >>> +INT NOINLINE >>> +opt_s2 (INT x) >>> +{ >>> + if (x < IMIN + (M * N) - GAP || x > 0) >>> + return 0; >>> + INT a = x - (M * N); >>> + INT b = a / N; >>> + return b + M; >>> +} >>> + >>> +INT NOINLINE >>> +opt_s3 (INT x) >>> +{ >>> + if (x < (M * N) - GAP) >>> + return 0; >>> + INT a = x - (M * N); >>> + INT b = a / -N; >>> + return b + -M; >>> +} >>> + >>> +INT NOINLINE >>> +opt_s4 (INT x) >>> +{ >>> + if (x < IMIN + (M * N) - GAP || x > 0) >>> + return 0; >>> + INT a = x - (M * N); >>> + INT b = a / -N; >>> + return b + -M; >>> +} >>> + >>> +INT NOINLINE >>> +opt_s5 (INT x) >>> +{ >>> + if (x > (-M * N) + GAP) >>> + return 0; >>> + INT a = x - (-M * N); >>> + INT b = a / N; >>> + return b + -M; >>> +} >>> + >>> +INT NOINLINE >>> +opt_s6 (INT x) >>> +{ >>> + if (x > IMAX - (M * N) + GAP || x < 0) >>> + return 0; >>> + INT a = x - (-M * N); >>> + INT b = a / N; >>> + return b + -M; >>> +} >>> + >>> +INT NOINLINE >>> +opt_s7 (INT x) >>> +{ >>> + if (x > (M * -N) + GAP) >>> + return 0; >>> + INT a = x - (M * -N); >>> + INT b = a / -N; >>> + return b + M; >>> +} >>> + >>> +INT NOINLINE >>> +opt_s8 (INT x) >>> +{ >>> + if (x > IMAX - (M * N) + GAP || x < 0) >>> + return 0; >>> + INT a = x - (M * -N); >>> + INT b = a / -N; >>> + return b + M; >>> +} >>> + >>> +UINT NOINLINE >>> +opt_u3 (UINT x) >>> +{ >>> + if (x < (M << N) - GAP) >>> + return 0; >>> + UINT a = x - (M << N); >>> + UINT b = a >> N; >>> + return b + M; >>> +} >>> + >>> +UINT NOINLINE >>> +opt_u4 (UINT x) >>> +{ >>> + if (x > (UMAX - (M << N)) + GAP) >>> + return 0; >>> + UINT a = x + (M << N); >>> + UINT b = a >> N; >>> + return b - M; >>> +} >>> + >>> +INT NOINLINE >>> +opt_s9 (INT x) >>> +{ >>> + if (x < (M << N) - GAP) >>> + return 0; >>> + INT a = x - (M << N); >>> + INT b = a >> N; >>> + return b + M; >>> +} >>> + >>> +INT NOINLINE >>> +opt_s10 (INT x) >>> +{ >>> + if (x < IMIN + (M << N) - GAP || x > 0) >>> + return 0; >>> + INT a = x - (M << N); >>> + INT b = a >> N; >>> + return b + M; >>> +} >>> + >>> +INT NOINLINE >>> +opt_s11 (INT x) >>> +{ >>> + if (x > (-M << N) + GAP) >>> + return 0; >>> + INT a = x - (-M << N); >>> + INT b = a >> N; >>> + return b + -M; >>> +} >>> + >>> +INT NOINLINE >>> +opt_s12 (INT x) >>> +{ >>> + if (x > IMAX - (M << N) + GAP || x < 0) >>> + return 0; >>> + INT a = x - (-M << N); >>> + INT b = a >> N; >>> + return b + -M; >>> +} >>>
On Thu, 1 Jun 2023, Jiufu Guo wrote: > Hi, > > Jiufu Guo via Gcc-patches <gcc-patches@gcc.gnu.org> writes: > > > Hi, > > > > Richard Biener <rguenther@suse.de> writes: > > > >> On Wed, 17 May 2023, Jiufu Guo wrote: > >> > >>> Hi, > >>> > >>> This patch tries to optimize "(X - N * M) / N + M" to "X / N". > >> > >> But if that's valid why not make the transform simpler and transform > >> (X - N * M) / N to X / N - M instead? > > > > Great catch! > > If "N * M" is not constant, "X / N - M" would be better than > > "(X - N * M) / N". If "N, M" are constants, "(X - N * M) / N" and > > "X / N - M" may be similar; while for this case, "X / N - M" should > > also be fine! I would try to update accordingly. > > > >> > >> You use the same optimize_x_minus_NM_div_N_plus_M validator for > >> the division and shift variants but the overflow rules are different, > >> so I'm not sure that's warranted. I'd also prefer to not split out > >> the validator to a different file - iff then the appropriate file > >> is fold-const.cc, not gimple-match-head.cc (I see we're a bit > >> inconsistent here, for pure gimple matches gimple-fold.cc would > >> be another place). > > > > Thanks for pointing out this! > > For shift, I guess you may concern that: 1. if the right operand is > > negative or is greater than or equal to the type width. 2. if it is > > a signed negative value. They may UB or 'sign bit shift'? This patch > > assumes it is ok to do the transform. I may have more check to see > > if this is really ok, and hope some one can point out if this is > > invalid. "(X - N * M) >> log2(N)" ==> " X >> log2(N) - M". > > > > I split out the validator just because: it is shared for division and > > shift :). And it seems gimple-match-head.cc and generic-match-head.cc, > > may be introduced for match.pd. So, I put it into gimple-match-head.cc. > > > >> > >> Since you use range information why is the transform restricted > >> to constant M? > > > > If M is a variable, the range for "X" is varying_p. I did not find > > the method to get the bounds for "X" (or for "X - N * M") to check no > > wraps. Any suggestions? > > Oh, I may misunderstand here. > You may say: M could be with a range too, then we can check if > "X - N * M" has a valid range or possible wrap/overflow. Yes. Richard. > BR, > Jeff (Jiufu Guo) > > > > > > > Again, thanks for your great help! > > > > BR, > > Jeff (Jiufu Guo) > > > >> > >> Richard. > >> > >>> As per the discussions in PR108757, we know this transformation is valid > >>> only under some conditions. > >>> For C code, "/" towards zero (trunc_div), and "X - N * M" > >>> maybe wrap/overflow/underflow. So, it is valid that "X - N * M" does > >>> not cross zero and does not wrap/overflow/underflow. > >>> > >>> This patch also handles the case when "N" is the power of 2, where > >>> "(X - N * M) / N" is "(X - N * M) >> log2(N)". > >>> > >>> Bootstrap & regtest pass on ppc64{,le} and x86_64. > >>> Is this ok for trunk? > >>> > >>> BR, > >>> Jeff (Jiufu) > >>> > >>> PR tree-optimization/108757 > >>> > >>> gcc/ChangeLog: > >>> > >>> * gimple-match-head.cc (optimize_x_minus_NM_div_N_plus_M): New function. > >>> * match.pd ((X - N * M) / N + M): New pattern. > >>> > >>> gcc/testsuite/ChangeLog: > >>> > >>> * gcc.dg/pr108757-1.c: New test. > >>> * gcc.dg/pr108757-2.c: New test. > >>> * gcc.dg/pr108757.h: New test. > >>> > >>> --- > >>> gcc/gimple-match-head.cc | 54 ++++++++++ > >>> gcc/match.pd | 22 ++++ > >>> gcc/testsuite/gcc.dg/pr108757-1.c | 17 ++++ > >>> gcc/testsuite/gcc.dg/pr108757-2.c | 18 ++++ > >>> gcc/testsuite/gcc.dg/pr108757.h | 160 ++++++++++++++++++++++++++++++ > >>> 5 files changed, 271 insertions(+) > >>> create mode 100644 gcc/testsuite/gcc.dg/pr108757-1.c > >>> create mode 100644 gcc/testsuite/gcc.dg/pr108757-2.c > >>> create mode 100644 gcc/testsuite/gcc.dg/pr108757.h > >>> > >>> diff --git a/gcc/gimple-match-head.cc b/gcc/gimple-match-head.cc > >>> index b08cd891a13..680a4cb2fc6 100644 > >>> --- a/gcc/gimple-match-head.cc > >>> +++ b/gcc/gimple-match-head.cc > >>> @@ -224,3 +224,57 @@ optimize_successive_divisions_p (tree divisor, tree inner_div) > >>> } > >>> return true; > >>> } > >>> + > >>> +/* Return true if "(X - N * M) / N + M" can be optimized into "X / N". > >>> + Otherwise return false. > >>> + > >>> + For unsigned, > >>> + If sign bit of M is 0 (clz is 0), valid range is [N*M, MAX]. > >>> + If sign bit of M is 1, valid range is [0, MAX - N*(-M)]. > >>> + > >>> + For signed, > >>> + If N*M > 0, valid range: [MIN+N*M, 0] + [N*M, MAX] > >>> + If N*M < 0, valid range: [MIN, -(-N*M)] + [0, MAX - (-N*M)]. */ > >>> + > >>> +static bool > >>> +optimize_x_minus_NM_div_N_plus_M (tree x, wide_int n, wide_int m, tree type) > >>> +{ > >>> + wide_int max = wi::max_value (type); > >>> + signop sgn = TYPE_SIGN (type); > >>> + wide_int nm; > >>> + wi::overflow_type ovf; > >>> + if (TYPE_UNSIGNED (type) && wi::clz (m) == 0) > >>> + nm = wi::mul (n, -m, sgn, &ovf); > >>> + else > >>> + nm = wi::mul (n, m, sgn, &ovf); > >>> + > >>> + if (ovf != wi::OVF_NONE) > >>> + return false; > >>> + > >>> + value_range vr0; > >>> + if (!get_range_query (cfun)->range_of_expr (vr0, x) || vr0.varying_p () > >>> + || vr0.undefined_p ()) > >>> + return false; > >>> + > >>> + wide_int wmin0 = vr0.lower_bound (); > >>> + wide_int wmax0 = vr0.upper_bound (); > >>> + wide_int min = wi::min_value (type); > >>> + > >>> + /* unsigned */ > >>> + if ((TYPE_UNSIGNED (type))) > >>> + /* M > 0 (clz != 0): [N*M, MAX], M < 0 : [0, MAX-N*(-M)] */ > >>> + return wi::clz (m) != 0 ? wi::ge_p (wmin0, nm, sgn) > >>> + : wi::le_p (wmax0, max - nm, sgn); > >>> + > >>> + /* signed, N*M > 0 */ > >>> + else if (wi::gt_p (nm, 0, sgn)) > >>> + /* [N*M, MAX] or [MIN+N*M, 0] */ > >>> + return wi::ge_p (wmin0, nm, sgn) > >>> + || (wi::ge_p (wmin0, min + nm, sgn) && wi::le_p (wmax0, 0, sgn)); > >>> + > >>> + /* signed, N*M < 0 */ > >>> + /* [MIN, N*M] or [0, MAX + N*M]*/ > >>> + else > >>> + return wi::le_p (wmax0, nm, sgn) > >>> + || (wi::ge_p (wmin0, 0, sgn) && wi::le_p (wmax0, max - (-nm), sgn)); > >>> +} > >>> diff --git a/gcc/match.pd b/gcc/match.pd > >>> index ceae1c34abc..1aaa5530577 100644 > >>> --- a/gcc/match.pd > >>> +++ b/gcc/match.pd > >>> @@ -881,6 +881,28 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) > >>> #endif > >>> )))) > >>> > >>> +#if GIMPLE > >>> +/* Simplify ((t + -N*M) / N + M) -> t / N. */ > >>> +(for div (trunc_div exact_div) > >>> + (simplify > >>> + (plus (div (plus @0 INTEGER_CST@1) INTEGER_CST@2) INTEGER_CST@3) > >>> + (with {wide_int n = wi::to_wide (@2); wide_int m = wi::to_wide (@3);} > >>> + (if (INTEGRAL_TYPE_P (type) > >>> + && n * m == -wi::to_wide (@1) > >>> + && optimize_x_minus_NM_div_N_plus_M (@0, n, m, type)) > >>> + (div @0 @2))))) > >>> + > >>> +/* Simplify ((t + -(M<<N)) >> N + M) -> t >> N. */ > >>> +(simplify > >>> + (plus (rshift (plus @0 INTEGER_CST@1) INTEGER_CST@2) INTEGER_CST@3) > >>> + (with {wide_int n = wi::to_wide (@2); wide_int m = wi::to_wide (@3);} > >>> + (if (INTEGRAL_TYPE_P (type) > >>> + && (m << n) == -wi::to_wide (@1) > >>> + && optimize_x_minus_NM_div_N_plus_M (@0, > >>> + wi::one (TYPE_PRECISION (type)) << n, m, type)) > >>> + (rshift @0 @2)))) > >>> +#endif > >>> + > >>> (for op (negate abs) > >>> /* Simplify cos(-x) and cos(|x|) -> cos(x). Similarly for cosh. */ > >>> (for coss (COS COSH) > >>> diff --git a/gcc/testsuite/gcc.dg/pr108757-1.c b/gcc/testsuite/gcc.dg/pr108757-1.c > >>> new file mode 100644 > >>> index 00000000000..349318a7c82 > >>> --- /dev/null > >>> +++ b/gcc/testsuite/gcc.dg/pr108757-1.c > >>> @@ -0,0 +1,17 @@ > >>> +/* PR tree-optimization/108757 */ > >>> +/* { dg-do compile } */ > >>> +/* { dg-options "-O2 -fdump-tree-optimized" } */ > >>> + > >>> +#include <limits.h> > >>> +#define N 4 > >>> +#define M 3 > >>> +#define GAP 0 > >>> +typedef unsigned int UINT; > >>> +typedef int INT; > >>> +#define UMAX UINT_MAX > >>> +#define IMAX INT_MAX > >>> +#define IMIN INT_MIN > >>> +#include "pr108757.h" > >>> + > >>> +/* { dg-final { scan-tree-dump-not " = x_\[0-9\]\\(D\\) \\+ " "optimized" } } */ > >>> +/* { dg-final { scan-tree-dump-not " = b_\[0-9\] \\+ " "optimized" } } */ > >>> diff --git a/gcc/testsuite/gcc.dg/pr108757-2.c b/gcc/testsuite/gcc.dg/pr108757-2.c > >>> new file mode 100644 > >>> index 00000000000..7302e9c606c > >>> --- /dev/null > >>> +++ b/gcc/testsuite/gcc.dg/pr108757-2.c > >>> @@ -0,0 +1,18 @@ > >>> +/* PR tree-optimization/108757 */ > >>> +/* { dg-do compile } */ > >>> +/* { dg-options "-O2 -fdump-tree-optimized" } */ > >>> + > >>> +#include <limits.h> > >>> +#define N 4 > >>> +#define M 3 > >>> +#define GAP 2 > >>> +typedef unsigned int UINT; > >>> +typedef int INT; > >>> +#define UMAX UINT_MAX > >>> +#define IMAX INT_MAX > >>> +#define IMIN INT_MIN > >>> +#include "pr108757.h" > >>> + > >>> +/* { dg-final { scan-tree-dump-times " = x_\[0-9\]\\(D\\) \\+ " 16 "optimized" } } */ > >>> +/* { dg-final { scan-tree-dump-times " = b_\[0-9\] \\+ " 16 "optimized" } } */ > >>> + > >>> diff --git a/gcc/testsuite/gcc.dg/pr108757.h b/gcc/testsuite/gcc.dg/pr108757.h > >>> new file mode 100644 > >>> index 00000000000..9e12d106aad > >>> --- /dev/null > >>> +++ b/gcc/testsuite/gcc.dg/pr108757.h > >>> @@ -0,0 +1,160 @@ > >>> +#define NOINLINE __attribute__ ((noinline)) > >>> +UINT NOINLINE > >>> +opt_u1 (UINT x) > >>> +{ > >>> + if (x < (M * N) - GAP) > >>> + return 0; > >>> + UINT a = x - (M * N); > >>> + UINT b = a / N; > >>> + return b + M; > >>> +} > >>> + > >>> +UINT NOINLINE > >>> +opt_u2 (UINT x) > >>> +{ > >>> + if (x > (UMAX - (M * N) + GAP)) > >>> + return 0; > >>> + UINT a = x + (M * N); > >>> + UINT b = a / N; > >>> + return b - M; > >>> +} > >>> + > >>> +INT NOINLINE > >>> +opt_s1 (INT x) > >>> +{ > >>> + if (x < (M * N) - GAP) > >>> + return 0; > >>> + INT a = x - (M * N); > >>> + INT b = a / N; > >>> + return b + M; > >>> +} > >>> + > >>> +INT NOINLINE > >>> +opt_s2 (INT x) > >>> +{ > >>> + if (x < IMIN + (M * N) - GAP || x > 0) > >>> + return 0; > >>> + INT a = x - (M * N); > >>> + INT b = a / N; > >>> + return b + M; > >>> +} > >>> + > >>> +INT NOINLINE > >>> +opt_s3 (INT x) > >>> +{ > >>> + if (x < (M * N) - GAP) > >>> + return 0; > >>> + INT a = x - (M * N); > >>> + INT b = a / -N; > >>> + return b + -M; > >>> +} > >>> + > >>> +INT NOINLINE > >>> +opt_s4 (INT x) > >>> +{ > >>> + if (x < IMIN + (M * N) - GAP || x > 0) > >>> + return 0; > >>> + INT a = x - (M * N); > >>> + INT b = a / -N; > >>> + return b + -M; > >>> +} > >>> + > >>> +INT NOINLINE > >>> +opt_s5 (INT x) > >>> +{ > >>> + if (x > (-M * N) + GAP) > >>> + return 0; > >>> + INT a = x - (-M * N); > >>> + INT b = a / N; > >>> + return b + -M; > >>> +} > >>> + > >>> +INT NOINLINE > >>> +opt_s6 (INT x) > >>> +{ > >>> + if (x > IMAX - (M * N) + GAP || x < 0) > >>> + return 0; > >>> + INT a = x - (-M * N); > >>> + INT b = a / N; > >>> + return b + -M; > >>> +} > >>> + > >>> +INT NOINLINE > >>> +opt_s7 (INT x) > >>> +{ > >>> + if (x > (M * -N) + GAP) > >>> + return 0; > >>> + INT a = x - (M * -N); > >>> + INT b = a / -N; > >>> + return b + M; > >>> +} > >>> + > >>> +INT NOINLINE > >>> +opt_s8 (INT x) > >>> +{ > >>> + if (x > IMAX - (M * N) + GAP || x < 0) > >>> + return 0; > >>> + INT a = x - (M * -N); > >>> + INT b = a / -N; > >>> + return b + M; > >>> +} > >>> + > >>> +UINT NOINLINE > >>> +opt_u3 (UINT x) > >>> +{ > >>> + if (x < (M << N) - GAP) > >>> + return 0; > >>> + UINT a = x - (M << N); > >>> + UINT b = a >> N; > >>> + return b + M; > >>> +} > >>> + > >>> +UINT NOINLINE > >>> +opt_u4 (UINT x) > >>> +{ > >>> + if (x > (UMAX - (M << N)) + GAP) > >>> + return 0; > >>> + UINT a = x + (M << N); > >>> + UINT b = a >> N; > >>> + return b - M; > >>> +} > >>> + > >>> +INT NOINLINE > >>> +opt_s9 (INT x) > >>> +{ > >>> + if (x < (M << N) - GAP) > >>> + return 0; > >>> + INT a = x - (M << N); > >>> + INT b = a >> N; > >>> + return b + M; > >>> +} > >>> + > >>> +INT NOINLINE > >>> +opt_s10 (INT x) > >>> +{ > >>> + if (x < IMIN + (M << N) - GAP || x > 0) > >>> + return 0; > >>> + INT a = x - (M << N); > >>> + INT b = a >> N; > >>> + return b + M; > >>> +} > >>> + > >>> +INT NOINLINE > >>> +opt_s11 (INT x) > >>> +{ > >>> + if (x > (-M << N) + GAP) > >>> + return 0; > >>> + INT a = x - (-M << N); > >>> + INT b = a >> N; > >>> + return b + -M; > >>> +} > >>> + > >>> +INT NOINLINE > >>> +opt_s12 (INT x) > >>> +{ > >>> + if (x > IMAX - (M << N) + GAP || x < 0) > >>> + return 0; > >>> + INT a = x - (-M << N); > >>> + INT b = a >> N; > >>> + return b + -M; > >>> +} > >>> >
diff --git a/gcc/gimple-match-head.cc b/gcc/gimple-match-head.cc index b08cd891a13..680a4cb2fc6 100644 --- a/gcc/gimple-match-head.cc +++ b/gcc/gimple-match-head.cc @@ -224,3 +224,57 @@ optimize_successive_divisions_p (tree divisor, tree inner_div) } return true; } + +/* Return true if "(X - N * M) / N + M" can be optimized into "X / N". + Otherwise return false. + + For unsigned, + If sign bit of M is 0 (clz is 0), valid range is [N*M, MAX]. + If sign bit of M is 1, valid range is [0, MAX - N*(-M)]. + + For signed, + If N*M > 0, valid range: [MIN+N*M, 0] + [N*M, MAX] + If N*M < 0, valid range: [MIN, -(-N*M)] + [0, MAX - (-N*M)]. */ + +static bool +optimize_x_minus_NM_div_N_plus_M (tree x, wide_int n, wide_int m, tree type) +{ + wide_int max = wi::max_value (type); + signop sgn = TYPE_SIGN (type); + wide_int nm; + wi::overflow_type ovf; + if (TYPE_UNSIGNED (type) && wi::clz (m) == 0) + nm = wi::mul (n, -m, sgn, &ovf); + else + nm = wi::mul (n, m, sgn, &ovf); + + if (ovf != wi::OVF_NONE) + return false; + + value_range vr0; + if (!get_range_query (cfun)->range_of_expr (vr0, x) || vr0.varying_p () + || vr0.undefined_p ()) + return false; + + wide_int wmin0 = vr0.lower_bound (); + wide_int wmax0 = vr0.upper_bound (); + wide_int min = wi::min_value (type); + + /* unsigned */ + if ((TYPE_UNSIGNED (type))) + /* M > 0 (clz != 0): [N*M, MAX], M < 0 : [0, MAX-N*(-M)] */ + return wi::clz (m) != 0 ? wi::ge_p (wmin0, nm, sgn) + : wi::le_p (wmax0, max - nm, sgn); + + /* signed, N*M > 0 */ + else if (wi::gt_p (nm, 0, sgn)) + /* [N*M, MAX] or [MIN+N*M, 0] */ + return wi::ge_p (wmin0, nm, sgn) + || (wi::ge_p (wmin0, min + nm, sgn) && wi::le_p (wmax0, 0, sgn)); + + /* signed, N*M < 0 */ + /* [MIN, N*M] or [0, MAX + N*M]*/ + else + return wi::le_p (wmax0, nm, sgn) + || (wi::ge_p (wmin0, 0, sgn) && wi::le_p (wmax0, max - (-nm), sgn)); +} diff --git a/gcc/match.pd b/gcc/match.pd index ceae1c34abc..1aaa5530577 100644 --- a/gcc/match.pd +++ b/gcc/match.pd @@ -881,6 +881,28 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) #endif )))) +#if GIMPLE +/* Simplify ((t + -N*M) / N + M) -> t / N. */ +(for div (trunc_div exact_div) + (simplify + (plus (div (plus @0 INTEGER_CST@1) INTEGER_CST@2) INTEGER_CST@3) + (with {wide_int n = wi::to_wide (@2); wide_int m = wi::to_wide (@3);} + (if (INTEGRAL_TYPE_P (type) + && n * m == -wi::to_wide (@1) + && optimize_x_minus_NM_div_N_plus_M (@0, n, m, type)) + (div @0 @2))))) + +/* Simplify ((t + -(M<<N)) >> N + M) -> t >> N. */ +(simplify + (plus (rshift (plus @0 INTEGER_CST@1) INTEGER_CST@2) INTEGER_CST@3) + (with {wide_int n = wi::to_wide (@2); wide_int m = wi::to_wide (@3);} + (if (INTEGRAL_TYPE_P (type) + && (m << n) == -wi::to_wide (@1) + && optimize_x_minus_NM_div_N_plus_M (@0, + wi::one (TYPE_PRECISION (type)) << n, m, type)) + (rshift @0 @2)))) +#endif + (for op (negate abs) /* Simplify cos(-x) and cos(|x|) -> cos(x). Similarly for cosh. */ (for coss (COS COSH) diff --git a/gcc/testsuite/gcc.dg/pr108757-1.c b/gcc/testsuite/gcc.dg/pr108757-1.c new file mode 100644 index 00000000000..349318a7c82 --- /dev/null +++ b/gcc/testsuite/gcc.dg/pr108757-1.c @@ -0,0 +1,17 @@ +/* PR tree-optimization/108757 */ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-optimized" } */ + +#include <limits.h> +#define N 4 +#define M 3 +#define GAP 0 +typedef unsigned int UINT; +typedef int INT; +#define UMAX UINT_MAX +#define IMAX INT_MAX +#define IMIN INT_MIN +#include "pr108757.h" + +/* { dg-final { scan-tree-dump-not " = x_\[0-9\]\\(D\\) \\+ " "optimized" } } */ +/* { dg-final { scan-tree-dump-not " = b_\[0-9\] \\+ " "optimized" } } */ diff --git a/gcc/testsuite/gcc.dg/pr108757-2.c b/gcc/testsuite/gcc.dg/pr108757-2.c new file mode 100644 index 00000000000..7302e9c606c --- /dev/null +++ b/gcc/testsuite/gcc.dg/pr108757-2.c @@ -0,0 +1,18 @@ +/* PR tree-optimization/108757 */ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-optimized" } */ + +#include <limits.h> +#define N 4 +#define M 3 +#define GAP 2 +typedef unsigned int UINT; +typedef int INT; +#define UMAX UINT_MAX +#define IMAX INT_MAX +#define IMIN INT_MIN +#include "pr108757.h" + +/* { dg-final { scan-tree-dump-times " = x_\[0-9\]\\(D\\) \\+ " 16 "optimized" } } */ +/* { dg-final { scan-tree-dump-times " = b_\[0-9\] \\+ " 16 "optimized" } } */ + diff --git a/gcc/testsuite/gcc.dg/pr108757.h b/gcc/testsuite/gcc.dg/pr108757.h new file mode 100644 index 00000000000..9e12d106aad --- /dev/null +++ b/gcc/testsuite/gcc.dg/pr108757.h @@ -0,0 +1,160 @@ +#define NOINLINE __attribute__ ((noinline)) +UINT NOINLINE +opt_u1 (UINT x) +{ + if (x < (M * N) - GAP) + return 0; + UINT a = x - (M * N); + UINT b = a / N; + return b + M; +} + +UINT NOINLINE +opt_u2 (UINT x) +{ + if (x > (UMAX - (M * N) + GAP)) + return 0; + UINT a = x + (M * N); + UINT b = a / N; + return b - M; +} + +INT NOINLINE +opt_s1 (INT x) +{ + if (x < (M * N) - GAP) + return 0; + INT a = x - (M * N); + INT b = a / N; + return b + M; +} + +INT NOINLINE +opt_s2 (INT x) +{ + if (x < IMIN + (M * N) - GAP || x > 0) + return 0; + INT a = x - (M * N); + INT b = a / N; + return b + M; +} + +INT NOINLINE +opt_s3 (INT x) +{ + if (x < (M * N) - GAP) + return 0; + INT a = x - (M * N); + INT b = a / -N; + return b + -M; +} + +INT NOINLINE +opt_s4 (INT x) +{ + if (x < IMIN + (M * N) - GAP || x > 0) + return 0; + INT a = x - (M * N); + INT b = a / -N; + return b + -M; +} + +INT NOINLINE +opt_s5 (INT x) +{ + if (x > (-M * N) + GAP) + return 0; + INT a = x - (-M * N); + INT b = a / N; + return b + -M; +} + +INT NOINLINE +opt_s6 (INT x) +{ + if (x > IMAX - (M * N) + GAP || x < 0) + return 0; + INT a = x - (-M * N); + INT b = a / N; + return b + -M; +} + +INT NOINLINE +opt_s7 (INT x) +{ + if (x > (M * -N) + GAP) + return 0; + INT a = x - (M * -N); + INT b = a / -N; + return b + M; +} + +INT NOINLINE +opt_s8 (INT x) +{ + if (x > IMAX - (M * N) + GAP || x < 0) + return 0; + INT a = x - (M * -N); + INT b = a / -N; + return b + M; +} + +UINT NOINLINE +opt_u3 (UINT x) +{ + if (x < (M << N) - GAP) + return 0; + UINT a = x - (M << N); + UINT b = a >> N; + return b + M; +} + +UINT NOINLINE +opt_u4 (UINT x) +{ + if (x > (UMAX - (M << N)) + GAP) + return 0; + UINT a = x + (M << N); + UINT b = a >> N; + return b - M; +} + +INT NOINLINE +opt_s9 (INT x) +{ + if (x < (M << N) - GAP) + return 0; + INT a = x - (M << N); + INT b = a >> N; + return b + M; +} + +INT NOINLINE +opt_s10 (INT x) +{ + if (x < IMIN + (M << N) - GAP || x > 0) + return 0; + INT a = x - (M << N); + INT b = a >> N; + return b + M; +} + +INT NOINLINE +opt_s11 (INT x) +{ + if (x > (-M << N) + GAP) + return 0; + INT a = x - (-M << N); + INT b = a >> N; + return b + -M; +} + +INT NOINLINE +opt_s12 (INT x) +{ + if (x > IMAX - (M << N) + GAP || x < 0) + return 0; + INT a = x - (-M << N); + INT b = a >> N; + return b + -M; +}
Hi, This patch tries to optimize "(X - N * M) / N + M" to "X / N". As per the discussions in PR108757, we know this transformation is valid only under some conditions. For C code, "/" towards zero (trunc_div), and "X - N * M" maybe wrap/overflow/underflow. So, it is valid that "X - N * M" does not cross zero and does not wrap/overflow/underflow. This patch also handles the case when "N" is the power of 2, where "(X - N * M) / N" is "(X - N * M) >> log2(N)". Bootstrap & regtest pass on ppc64{,le} and x86_64. Is this ok for trunk? BR, Jeff (Jiufu) PR tree-optimization/108757 gcc/ChangeLog: * gimple-match-head.cc (optimize_x_minus_NM_div_N_plus_M): New function. * match.pd ((X - N * M) / N + M): New pattern. gcc/testsuite/ChangeLog: * gcc.dg/pr108757-1.c: New test. * gcc.dg/pr108757-2.c: New test. * gcc.dg/pr108757.h: New test. --- gcc/gimple-match-head.cc | 54 ++++++++++ gcc/match.pd | 22 ++++ gcc/testsuite/gcc.dg/pr108757-1.c | 17 ++++ gcc/testsuite/gcc.dg/pr108757-2.c | 18 ++++ gcc/testsuite/gcc.dg/pr108757.h | 160 ++++++++++++++++++++++++++++++ 5 files changed, 271 insertions(+) create mode 100644 gcc/testsuite/gcc.dg/pr108757-1.c create mode 100644 gcc/testsuite/gcc.dg/pr108757-2.c create mode 100644 gcc/testsuite/gcc.dg/pr108757.h