Use SetLenOnDrop in Vec::truncate() by lnicola · Pull Request #52908 · rust-lang/rust (original) (raw)
…chton
Use SetLenOnDrop in Vec::truncate()
This avoids a redundant length check in some cases when calling
Vec::truncate or Vec::clear.
Fixes rust-lang#51802
Note that the generated code still seems suboptimal. I tested with the following functions:
#[no_mangle]
pub extern fn foo(x: &mut Vec<u8>) {
x.clear();
}
#[no_mangle]
pub extern fn bar(x: &mut Vec<u8>) {
x.truncate(5);
}
#[no_mangle]
pub extern fn baz(x: &mut Vec<u8>, n: usize) {
x.truncate(n);
}
#[no_mangle]
pub extern fn foo_string(x: &mut Vec<String>) {
x.clear();
}
#[no_mangle]
pub extern fn bar_string(x: &mut Vec<String>) {
x.truncate(5);
}
#[no_mangle]
pub extern fn baz_string(x: &mut Vec<String>, n: usize) {
x.truncate(n);
}Old output
00000000000460a0 <foo>:
460a0: 48 83 7f 10 00 cmpq $0x0,0x10(%rdi)
460a5: 74 08 je 460af <foo+0xf>
460a7: 48 c7 47 10 00 00 00 movq $0x0,0x10(%rdi)
460ae: 00
460af: c3 retq
00000000000460b0 <bar>:
460b0: 48 83 7f 10 06 cmpq $0x6,0x10(%rdi)
460b5: 72 08 jb 460bf <bar+0xf>
460b7: 48 c7 47 10 05 00 00 movq $0x5,0x10(%rdi)
460be: 00
460bf: c3 retq
00000000000460c0 <baz>:
460c0: 48 39 77 10 cmp %rsi,0x10(%rdi)
460c4: 76 04 jbe 460ca <baz+0xa>
460c6: 48 89 77 10 mov %rsi,0x10(%rdi)
460ca: c3 retq
460cb: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1)
00000000000460d0 <foo_string>:
460d0: 41 57 push %r15
460d2: 41 56 push %r14
460d4: 53 push %rbx
460d5: 48 8b 47 10 mov 0x10(%rdi),%rax
460d9: 48 85 c0 test %rax,%rax
460dc: 74 4a je 46128 <foo_string+0x58>
460de: 49 89 fe mov %rdi,%r14
460e1: 48 8b 0f mov (%rdi),%rcx
460e4: 48 8d 14 40 lea (%rax,%rax,2),%rdx
460e8: 48 8d 58 ff lea -0x1(%rax),%rbx
460ec: 4c 8d 3c d1 lea (%rcx,%rdx,8),%r15
460f0: 49 83 c7 f0 add $0xfffffffffffffff0,%r15
460f4: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
460fb: 00 00 00
460fe: 66 90 xchg %ax,%ax
46100: 49 89 5e 10 mov %rbx,0x10(%r14)
46104: 49 8b 37 mov (%r15),%rsi
46107: 48 85 f6 test %rsi,%rsi
4610a: 74 0e je 4611a <foo_string+0x4a>
4610c: 49 8b 7f f8 mov -0x8(%r15),%rdi
46110: ba 01 00 00 00 mov $0x1,%edx
46115: e8 a6 e9 ff ff callq 44ac0 <__rust_dealloc@plt>
4611a: 48 83 c3 ff add $0xffffffffffffffff,%rbx
4611e: 49 83 c7 e8 add $0xffffffffffffffe8,%r15
46122: 48 83 fb ff cmp $0xffffffffffffffff,%rbx
46126: 75 d8 jne 46100 <foo_string+0x30>
46128: 5b pop %rbx
46129: 41 5e pop %r14
4612b: 41 5f pop %r15
4612d: c3 retq
4612e: 66 90 xchg %ax,%ax
0000000000046130 <bar_string>:
46130: 41 57 push %r15
46132: 41 56 push %r14
46134: 53 push %rbx
46135: 4c 8b 7f 10 mov 0x10(%rdi),%r15
46139: 49 83 ff 06 cmp $0x6,%r15
4613d: 72 49 jb 46188 <bar_string+0x58>
4613f: 49 89 fe mov %rdi,%r14
46142: 48 8b 07 mov (%rdi),%rax
46145: 4b 8d 0c 7f lea (%r15,%r15,2),%rcx
46149: 48 8d 1c c8 lea (%rax,%rcx,8),%rbx
4614d: 48 83 c3 f0 add $0xfffffffffffffff0,%rbx
46151: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
46158: 00 00 00
4615b: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1)
46160: 49 83 c7 ff add $0xffffffffffffffff,%r15
46164: 4d 89 7e 10 mov %r15,0x10(%r14)
46168: 48 8b 33 mov (%rbx),%rsi
4616b: 48 85 f6 test %rsi,%rsi
4616e: 74 0e je 4617e <bar_string+0x4e>
46170: 48 8b 7b f8 mov -0x8(%rbx),%rdi
46174: ba 01 00 00 00 mov $0x1,%edx
46179: e8 42 e9 ff ff callq 44ac0 <__rust_dealloc@plt>
4617e: 48 83 c3 e8 add $0xffffffffffffffe8,%rbx
46182: 49 83 ff 05 cmp $0x5,%r15
46186: 77 d8 ja 46160 <bar_string+0x30>
46188: 5b pop %rbx
46189: 41 5e pop %r14
4618b: 41 5f pop %r15
4618d: c3 retq
4618e: 66 90 xchg %ax,%ax
0000000000046190 <baz_string>:
46190: 41 57 push %r15
46192: 41 56 push %r14
46194: 41 54 push %r12
46196: 53 push %rbx
46197: 50 push %rax
46198: 4c 8b 67 10 mov 0x10(%rdi),%r12
4619c: 49 39 f4 cmp %rsi,%r12
4619f: 76 46 jbe 461e7 <baz_string+0x57>
461a1: 49 89 f6 mov %rsi,%r14
461a4: 49 89 ff mov %rdi,%r15
461a7: 48 8b 07 mov (%rdi),%rax
461aa: 4b 8d 0c 64 lea (%r12,%r12,2),%rcx
461ae: 48 8d 1c c8 lea (%rax,%rcx,8),%rbx
461b2: 48 83 c3 f0 add $0xfffffffffffffff0,%rbx
461b6: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
461bd: 00 00 00
461c0: 49 83 c4 ff add $0xffffffffffffffff,%r12
461c4: 4d 89 67 10 mov %r12,0x10(%r15)
461c8: 48 8b 33 mov (%rbx),%rsi
461cb: 48 85 f6 test %rsi,%rsi
461ce: 74 0e je 461de <baz_string+0x4e>
461d0: 48 8b 7b f8 mov -0x8(%rbx),%rdi
461d4: ba 01 00 00 00 mov $0x1,%edx
461d9: e8 e2 e8 ff ff callq 44ac0 <__rust_dealloc@plt>
461de: 48 83 c3 e8 add $0xffffffffffffffe8,%rbx
461e2: 4d 39 f4 cmp %r14,%r12
461e5: 77 d9 ja 461c0 <baz_string+0x30>
461e7: 48 83 c4 08 add $0x8,%rsp
461eb: 5b pop %rbx
461ec: 41 5c pop %r12
461ee: 41 5e pop %r14
461f0: 41 5f pop %r15
461f2: c3 retq
461f3: 90 nop
461f4: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
461fb: 00 00 00
461fe: 66 90 xchg %ax,%axNew output
0000000000084d10 <foo>:
84d10: 48 c7 47 10 00 00 00 movq $0x0,0x10(%rdi)
84d17: 00
84d18: c3 retq
84d19: 0f 1f 80 00 00 00 00 nopl 0x0(%rax)
0000000000084d20 <bar>:
84d20: 48 8b 47 10 mov 0x10(%rdi),%rax
84d24: 48 83 f8 05 cmp $0x5,%rax
84d28: b9 05 00 00 00 mov $0x5,%ecx
84d2d: 48 0f 42 c8 cmovb %rax,%rcx
84d31: 48 89 4f 10 mov %rcx,0x10(%rdi)
84d35: c3 retq
84d36: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
84d3d: 00 00 00
0000000000084d40 <baz>:
84d40: 48 8b 47 10 mov 0x10(%rdi),%rax
84d44: 48 39 f0 cmp %rsi,%rax
84d47: 48 0f 47 c6 cmova %rsi,%rax
84d4b: 48 89 47 10 mov %rax,0x10(%rdi)
84d4f: c3 retq
0000000000084d50 <foo_string>:
84d50: 41 57 push %r15
84d52: 41 56 push %r14
84d54: 53 push %rbx
84d55: 49 89 fe mov %rdi,%r14
84d58: 4c 8b 7f 10 mov 0x10(%rdi),%r15
84d5c: 4d 85 ff test %r15,%r15
84d5f: 74 2f je 84d90 <foo_string+0x40>
84d61: 49 8b 06 mov (%r14),%rax
84d64: 4b 8d 0c 7f lea (%r15,%r15,2),%rcx
84d68: 48 8d 1c c8 lea (%rax,%rcx,8),%rbx
84d6c: 48 83 c3 f0 add $0xfffffffffffffff0,%rbx
84d70: 48 8b 33 mov (%rbx),%rsi
84d73: 48 85 f6 test %rsi,%rsi
84d76: 74 0e je 84d86 <foo_string+0x36>
84d78: 48 8b 7b f8 mov -0x8(%rbx),%rdi
84d7c: ba 01 00 00 00 mov $0x1,%edx
84d81: e8 1a b1 ff ff callq 7fea0 <__rust_dealloc@plt>
84d86: 48 83 c3 e8 add $0xffffffffffffffe8,%rbx
84d8a: 49 83 c7 ff add $0xffffffffffffffff,%r15
84d8e: 75 e0 jne 84d70 <foo_string+0x20>
84d90: 49 c7 46 10 00 00 00 movq $0x0,0x10(%r14)
84d97: 00
84d98: 5b pop %rbx
84d99: 41 5e pop %r14
84d9b: 41 5f pop %r15
84d9d: c3 retq
84d9e: 66 90 xchg %ax,%ax
0000000000084da0 <bar_string>:
84da0: 41 57 push %r15
84da2: 41 56 push %r14
84da4: 53 push %rbx
84da5: 49 89 fe mov %rdi,%r14
84da8: 4c 8b 7f 10 mov 0x10(%rdi),%r15
84dac: 49 83 ff 06 cmp $0x6,%r15
84db0: 72 44 jb 84df6 <bar_string+0x56>
84db2: 49 8b 06 mov (%r14),%rax
84db5: 4b 8d 0c 7f lea (%r15,%r15,2),%rcx
84db9: 48 8d 1c c8 lea (%rax,%rcx,8),%rbx
84dbd: 48 83 c3 f0 add $0xfffffffffffffff0,%rbx
84dc1: 49 83 c7 fb add $0xfffffffffffffffb,%r15
84dc5: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
84dcc: 00 00 00
84dcf: 90 nop
84dd0: 48 8b 33 mov (%rbx),%rsi
84dd3: 48 85 f6 test %rsi,%rsi
84dd6: 74 0e je 84de6 <bar_string+0x46>
84dd8: 48 8b 7b f8 mov -0x8(%rbx),%rdi
84ddc: ba 01 00 00 00 mov $0x1,%edx
84de1: e8 ba b0 ff ff callq 7fea0 <__rust_dealloc@plt>
84de6: 48 83 c3 e8 add $0xffffffffffffffe8,%rbx
84dea: 49 83 c7 ff add $0xffffffffffffffff,%r15
84dee: 75 e0 jne 84dd0 <bar_string+0x30>
84df0: 41 bf 05 00 00 00 mov $0x5,%r15d
84df6: 4d 89 7e 10 mov %r15,0x10(%r14)
84dfa: 5b pop %rbx
84dfb: 41 5e pop %r14
84dfd: 41 5f pop %r15
84dff: c3 retq
0000000000084e00 <baz_string>:
84e00: 41 57 push %r15
84e02: 41 56 push %r14
84e04: 41 54 push %r12
84e06: 53 push %rbx
84e07: 50 push %rax
84e08: 49 89 ff mov %rdi,%r15
84e0b: 48 8b 47 10 mov 0x10(%rdi),%rax
84e0f: 49 89 c4 mov %rax,%r12
84e12: 49 29 f4 sub %rsi,%r12
84e15: 76 3c jbe 84e53 <baz_string+0x53>
84e17: 49 89 f6 mov %rsi,%r14
84e1a: 49 8b 0f mov (%r15),%rcx
84e1d: 48 8d 04 40 lea (%rax,%rax,2),%rax
84e21: 48 8d 1c c1 lea (%rcx,%rax,8),%rbx
84e25: 48 83 c3 f0 add $0xfffffffffffffff0,%rbx
84e29: 0f 1f 80 00 00 00 00 nopl 0x0(%rax)
84e30: 48 8b 33 mov (%rbx),%rsi
84e33: 48 85 f6 test %rsi,%rsi
84e36: 74 0e je 84e46 <baz_string+0x46>
84e38: 48 8b 7b f8 mov -0x8(%rbx),%rdi
84e3c: ba 01 00 00 00 mov $0x1,%edx
84e41: e8 5a b0 ff ff callq 7fea0 <__rust_dealloc@plt>
84e46: 48 83 c3 e8 add $0xffffffffffffffe8,%rbx
84e4a: 49 83 c4 ff add $0xffffffffffffffff,%r12
84e4e: 75 e0 jne 84e30 <baz_string+0x30>
84e50: 4c 89 f0 mov %r14,%rax
84e53: 49 89 47 10 mov %rax,0x10(%r15)
84e57: 48 83 c4 08 add $0x8,%rsp
84e5b: 5b pop %rbx
84e5c: 41 5c pop %r12
84e5e: 41 5e pop %r14
84e60: 41 5f pop %r15
84e62: c3 retq
84e63: 90 nop
84e64: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
84e6b: 00 00 00
84e6e: 66 90 xchg %ax,%axFor calling truncate with non-zero lengths on non-Drop types, it seems that a redundant load and comparison gets replaced with an awkward sequence with a conditional move. In the unknown length case, the new code is no longer awkward.
Maybe someone moderately proficient at assembly could tell if this looks like a win or not.
This came up when discussing replacing unsafe { vec.set_len(0) } with vec.clear() in a project where the author was worried about potential performance degradation. It might be worth replacing some unsafe code, even it it's trivial to see that it's actually safe.