From 0603375cbcdd81ce7eef925a3cfd4fdc297b50f7 Mon Sep 17 00:00:00 2001 From: Kyrylo Tkachov Date: Tue, 24 Apr 2018 16:58:49 +0000 Subject: [PATCH] [AArch64] PR target/85512: Tighten SIMD right shift immediate constraints In this testcase it is possible to generate an invalid SISD shift of zero: Error: immediate value out of range 1 to 64 at operand 3 -- `sshr v9.2s,v0.2s,0' The SSHR and USHR instructions require a shift from 1 up to the element size. However our constraints on the scalar shifts that generate these patterns allow a shift amount of zero as well. The pure GP-reg ASR and LSR instructions allow a shift amount of zero. It is unlikely that a shift of zero will survive till the end of compilation, but it's not impossible, as this PR shows. The patch tightens up the constraints in the offending patterns by adding two new constraints that allow shift amounts [1,32] and [1,64] and using them in *aarch64_ashr_sisd_or_int_3 and *aarch64_lshr_sisd_or_int_3. The left-shift SISD instructions SHL and USHL allow a shift amount of zero so don't need adjustment The vector shift patterns that map down to SSHR and USHR already enforce the correct immediate range. PR target/85512 * config/aarch64/constraints.md (Usg, Usj): New constraints. * config/aarch64/iterators.md (cmode_simd): New mode attribute. * config/aarch64/aarch64.md (*aarch64_ashr_sisd_or_int_3): Use the above on operand 2. Reindent. (*aarch64_lshr_sisd_or_int_3): Likewise. * gcc.dg/pr85512.c: New test. From-SVN: r259614 --- gcc/ChangeLog | 9 ++++++ gcc/config/aarch64/aarch64.md | 10 ++++--- gcc/config/aarch64/constraints.md | 14 +++++++++ gcc/config/aarch64/iterators.md | 3 ++ gcc/testsuite/ChangeLog | 5 ++++ gcc/testsuite/gcc.dg/pr85512.c | 47 +++++++++++++++++++++++++++++++ 6 files changed, 84 insertions(+), 4 deletions(-) create mode 100644 gcc/testsuite/gcc.dg/pr85512.c diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 44214209796..1837b262189 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,12 @@ +2018-04-24 Kyrylo Tkachov + + PR target/85512 + * config/aarch64/constraints.md (Usg, Usj): New constraints. + * config/aarch64/iterators.md (cmode_simd): New mode attribute. + * config/aarch64/aarch64.md (*aarch64_ashr_sisd_or_int_3): + Use the above on operand 2. Reindent. + (*aarch64_lshr_sisd_or_int_3): Likewise. + 2018-04-24 H.J. Lu PR target/85485 diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md index 10fcde6a1b6..32a0e1f3685 100644 --- a/gcc/config/aarch64/aarch64.md +++ b/gcc/config/aarch64/aarch64.md @@ -4403,7 +4403,8 @@ [(set (match_operand:GPI 0 "register_operand" "=r,r,w,&w,&w") (lshiftrt:GPI (match_operand:GPI 1 "register_operand" "r,r,w,w,w") - (match_operand:QI 2 "aarch64_reg_or_shift_imm_" "Us,r,Us,w,0")))] + (match_operand:QI 2 "aarch64_reg_or_shift_imm_" + "Us,r,Us,w,0")))] "" "@ lsr\t%0, %1, %2 @@ -4448,9 +4449,10 @@ ;; Arithmetic right shift using SISD or Integer instruction (define_insn "*aarch64_ashr_sisd_or_int_3" [(set (match_operand:GPI 0 "register_operand" "=r,r,w,&w,&w") - (ashiftrt:GPI - (match_operand:GPI 1 "register_operand" "r,r,w,w,w") - (match_operand:QI 2 "aarch64_reg_or_shift_imm_di" "Us,r,Us,w,0")))] + (ashiftrt:GPI + (match_operand:GPI 1 "register_operand" "r,r,w,w,w") + (match_operand:QI 2 "aarch64_reg_or_shift_imm_di" + "Us,r,Us,w,0")))] "" "@ asr\t%0, %1, %2 diff --git a/gcc/config/aarch64/constraints.md b/gcc/config/aarch64/constraints.md index f052103e859..b5da997e7ba 100644 --- a/gcc/config/aarch64/constraints.md +++ b/gcc/config/aarch64/constraints.md @@ -153,6 +153,20 @@ (match_test "!(aarch64_is_noplt_call_p (op) || aarch64_is_long_call_p (op))"))) +(define_constraint "Usg" + "@internal + A constraint that matches an immediate right shift constant in SImode + suitable for a SISD instruction." + (and (match_code "const_int") + (match_test "IN_RANGE (ival, 1, 32)"))) + +(define_constraint "Usj" + "@internal + A constraint that matches an immediate right shift constant in DImode + suitable for a SISD instruction." + (and (match_code "const_int") + (match_test "IN_RANGE (ival, 1, 64)"))) + (define_constraint "UsM" "@internal A constraint that matches the immediate constant -1." diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md index fa181794392..25991d97836 100644 --- a/gcc/config/aarch64/iterators.md +++ b/gcc/config/aarch64/iterators.md @@ -589,6 +589,9 @@ ;; Map a mode to a specific constraint character. (define_mode_attr cmode [(QI "q") (HI "h") (SI "s") (DI "d")]) +;; Map modes to Usg and Usj constraints for SISD right shifts +(define_mode_attr cmode_simd [(SI "g") (DI "j")]) + (define_mode_attr Vtype [(V8QI "8b") (V16QI "16b") (V4HI "4h") (V8HI "8h") (V2SI "2s") (V4SI "4s") diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 7d551408cdb..ff4b5fbe283 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,8 @@ +2018-04-24 Kyrylo Tkachov + + PR target/85512 + * gcc.dg/pr85512.c: New test. + PR target/85485 * g++.dg/cet-notrack-1.C (dg-options): Remove -mcet. diff --git a/gcc/testsuite/gcc.dg/pr85512.c b/gcc/testsuite/gcc.dg/pr85512.c new file mode 100644 index 00000000000..b581f833938 --- /dev/null +++ b/gcc/testsuite/gcc.dg/pr85512.c @@ -0,0 +1,47 @@ +/* { dg-do assemble } */ +/* { dg-options "-O -fno-if-conversion" } */ + +typedef unsigned char u8; +typedef unsigned short u16; +typedef unsigned int u32; +typedef unsigned long long u64; +u64 +bar0(u8 u8_0, u16 u16_0, u32 u32_0, u64 u64_0, u8 u8_1, u16 u16_1, u32 u32_1, u64 u64_1, u8 u8_2, u16 u16_2, u32 u32_2, u64 u64_2, u8 u8_3, u16 u16_3, u32 u32_3, u64 u64_3); +u64 +bar1(u8 u8_0, u16 u16_0, u32 u32_0, u64 u64_0, u8 u8_1, u16 u16_1, u32 u32_1, u64 u64_1, u8 u8_2, u16 u16_2, u32 u32_2, u64 u64_2, u8 u8_3, u16 u16_3, u32 u32_3, u64 u64_3); +u64 +bar2(u8 u8_0, u16 u16_0, u32 u32_0, u64 u64_0, u8 u8_1, u16 u16_1, u32 u32_1, u64 u64_1, u8 u8_2, u16 u16_2, u32 u32_2, u64 u64_2, u8 u8_3, u16 u16_3, u32 u32_3, u64 u64_3); +u64 +bar0(u8 u8_0, u16 u16_0, u32 u32_0, u64 u64_0, u8 u8_1, u16 u16_1, u32 u32_1, u64 u64_1, u8 u8_2, u16 u16_2, u32 u32_2, u64 u64_2, u8 u8_3, u16 u16_3, u32 u32_3, u64 u64_3) +{ +l0: u32_2 += __builtin_add_overflow_p((u32)(u64)u32_0, (u16)-(u32)u64_2, (u64)-(u64)(unsigned)__builtin_parityll((u16)(u16)(((u64)0x1a6cb5b10 << 0)))); + u8_3 <<= __builtin_add_overflow((u16)~(u32)u64_2, (u16)(u8)(unsigned)__builtin_popcountll((u16)-(u8)(((u64)0x725582 << 0))), &u32_1); + u64_1 -= (u8)~(u8)(0); + u16_3 = (u16_3 >> ((u32)~(u8)(1) & 15)) | (u16_3 << ((16 - ((u32)~(u8)(1) & 15)) & 15)); + u8_2 = __builtin_mul_overflow((u64)(u8)__builtin_bswap32((u32)-(u32)u16_0), (u64)(u16)u16_2, &u8_3) ? (u64)~(u8)u8_3 : (u16)(u16)(((u64)0x7ffffff << 0)); + u32_0 *= (u8)(u8)(((u64)0x1ffffffffffffff << 0)); + u32_1 >>= (u64)~(u64)(((u64)0x61bf860d09fb3a << 0)) >= (u8)(u16)(unsigned)__builtin_parityll((u16)(u8)(((u64)0x6 << 0))); + u16_0 >>= __builtin_add_overflow_p((u64)-(u8)(((u64)0x68b4dda55e3 << 0)), (u16)(u64)__builtin_bswap64((u16)~(u32)__builtin_bswap32((u32)(u32)u8_3)), (u64)(u16)u16_1); + u64_0 += (u8)-(u64)(((u64)0xcc88a5c0292b6ba0 << 0)); + u32_0 += __builtin_mul_overflow((u8)-(u64)(((u64)0xc89172ea72a << 0)), (u64)(u64)u8_2, &u8_3); + u64_0 >>= __builtin_add_overflow((u32)-(u64)(0), (u32)-(u16)u8_1, &u8_2); + u16_1 >>= (u32)(u64)u16_1 & 15; + u16_3 ^= (u16)~(u16)(1); + u32_2 &= (u16)-(u32)(0); +l1: u32_3 = (u32_3 >> ((u64)(u32)u32_1 & 31)) | (u32_3 << ((32 - ((u64)(u32)u32_1 & 31)) & 31)); + u64_1 |= (u64)~(u64)(unsigned)__builtin_parityll((u8)-(u32)u32_1); + u8_3 *= __builtin_add_overflow((u64)-(u32)(((u64)0xffff << 0)), (u32)~(u64)(((u64)0x117e3e << 0)), &u32_2); + u16_3 = (u16_3 << ((u64)~(u8)(((u64)0xf78e81 << 0)) & 15)) | (u16_3 >> ((16 - ((u64)~(u8)(((u64)0xf78e81 << 0)) & 15)) & 15)); + u64_1 = (u64)(u16)bar1((u8)((u32)(u64)(((u64)0x3ffffff << 0))), (u16)((u8)(u16)(((u64)0x5b << 0))), (u32)((u32)~(u8)(1)), (u64)((u8)(u16)(unsigned)__builtin_clrsb((u32)~(u32)(unsigned)__builtin_clrsbll((u8)(u16)(((u64)0xffffffff << 0))))), (u8)((u8)-(u64)(((u64)0x3e43180756484 << 0))), (u16)((u8)(u16)(((u64)0x7 << 0))), (u32)((u64)(u32)(((u64)0x285fa35c89 << 0))), (u64)((u32)(u8)(((u64)0x3ffff << 0))), (u8)((u16)-(u32)(((u64)0x73d01 << 0))), (u16)((u16)-(u16)(((u64)0x1fffffffffffff << 0))), (u32)((u16)(u64)(0)), (u64)((u16)(u32)(((u64)0x4c << 0))), (u8)((u64)-(u64)(((u64)0x3fffffffffffff << 0))), (u16)((u16)~(u16)(((u64)0xfffffffff << 0))), (u32)((u64)(u16)(((u64)0x7edb0cc1c << 0))), (u64)((u32)(u64)(((u64)0x1ffffffffff << 0)))) > (u16)-(u64)(((u64)0x7 << 0)) ? (u16)(u8)u64_2 : (u64)(u16)u32_2; + u32_0 >>= (u8)(u16)(((u64)0x32 << 0)) != (u16)-(u64)u16_3; + u16_1 *= __builtin_mul_overflow_p((u64)(u32)u32_1, (u16)(u8)(((u64)0x4ad149d89bf0be6 << 0)), (u64)(u32)(((u64)0x1bd7589 << 0))); + u8_1 &= (u64)-(u64)u8_0; + u16_3 %= (u16)(u16)(unsigned)__builtin_clrsbll((u32)~(u32)(((u64)0x3db8721fd79 << 0))); + u8_3 >>= (u32)(u8)u8_1 & 7; + u64_1 |= (u8)-(u64)(unsigned)__builtin_ffsll((u32)-(u64)bar2((u8)((u16)(u16)(((u64)0x3 << 0))), (u16)((u32)-(u8)(((u64)0x86af5 << 0))), (u32)((u16)-(u64)__builtin_bswap64((u64)-(u64)(0))), (u64)((u16)(u16)(((u64)0x75138426ec84c6 << 0))), (u8)((u64)(u32)(((u64)0x7fffffffff << 0))), (u16)((u32)~(u8)(((u64)0x71aa939dbdf3 << 0))), (u32)((u16)(u32)(((u64)0x8776ee7dbb651a2d << 0))), (u64)((u8)(u64)(0)), (u8)((u16)(u8)(unsigned)__builtin_clrsbll((u16)~(u32)(((u64)0x8df94655ec8430 << 0)))), (u16)((u16)-(u64)(unsigned)__builtin_clrsbll((u32)(u64)(((u64)0x3090a532 << 0)))), (u32)((u16)~(u16)(1)), (u64)((u8)(u32)(((u64)0x7fffffffffff << 0))), (u8)((u32)~(u64)(0)), (u16)((u8)~(u8)(unsigned)__builtin_ffs((u64)(u64)(0))), (u32)((u16)-(u8)(((u64)0x5dfe702 << 0))), (u64)((u8)(u64)(((u64)0x68f2a584e0 << 0))))); + u32_3 >>= (u32)-(u32)u32_2 & 31; + u8_3 = (u8_3 >> ((u32)-(u8)u8_1 & 7)) | (u8_3 << ((8 - ((u32)-(u8)u8_1 & 7)) & 7)); + u8_2 >>= (u16)-(u64)u64_3 & 7; + u32_1 = (u32_1 >> ((u16)(u16)(1) & 31)) | (u32_1 << ((32 - ((u16)(u16)(1) & 31)) & 31)); + return u8_0 + u16_0 + u32_0 + u64_0 + u8_1 + u16_1 + u32_1 + u64_1 + u8_2 + u16_2 + u32_2 + u64_2 + u8_3 + u16_3 + u32_3 + u64_3; +} -- 2.30.2