| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
and-with-constant operations.
This fixes rdar://8808586 which observed that we used to compile:
union xy {
struct x { _Bool b[15]; } x;
__attribute__((packed))
struct y {
__attribute__((packed)) unsigned long b0to7;
__attribute__((packed)) unsigned int b8to11;
__attribute__((packed)) unsigned short b12to13;
__attribute__((packed)) unsigned char b14;
} y;
};
struct x
foo(union xy *xy)
{
return xy->x;
}
into:
_foo: ## @foo
movq (%rdi), %rax
movabsq $1095216660480, %rcx ## imm = 0xFF00000000
andq %rax, %rcx
movabsq $-72057594037927936, %rdx ## imm = 0xFF00000000000000
andq %rax, %rdx
movzbl %al, %esi
orq %rdx, %rsi
movq %rax, %rdx
andq $65280, %rdx ## imm = 0xFF00
orq %rsi, %rdx
movq %rax, %rsi
andq $16711680, %rsi ## imm = 0xFF0000
orq %rdx, %rsi
movl %eax, %edx
andl $-16777216, %edx ## imm = 0xFFFFFFFFFF000000
orq %rsi, %rdx
orq %rcx, %rdx
movabsq $280375465082880, %rcx ## imm = 0xFF0000000000
movq %rax, %rsi
andq %rcx, %rsi
orq %rdx, %rsi
movabsq $71776119061217280, %r8 ## imm = 0xFF000000000000
andq %r8, %rax
orq %rsi, %rax
movzwl 12(%rdi), %edx
movzbl 14(%rdi), %esi
shlq $16, %rsi
orl %edx, %esi
movq %rsi, %r9
shlq $32, %r9
movl 8(%rdi), %edx
orq %r9, %rdx
andq %rdx, %rcx
movzbl %sil, %esi
shlq $32, %rsi
orq %rcx, %rsi
movl %edx, %ecx
andl $-16777216, %ecx ## imm = 0xFFFFFFFFFF000000
orq %rsi, %rcx
movq %rdx, %rsi
andq $16711680, %rsi ## imm = 0xFF0000
orq %rcx, %rsi
movq %rdx, %rcx
andq $65280, %rcx ## imm = 0xFF00
orq %rsi, %rcx
movzbl %dl, %esi
orq %rcx, %rsi
andq %r8, %rdx
orq %rsi, %rdx
ret
We now compile this into:
_foo: ## @foo
## BB#0: ## %entry
movzwl 12(%rdi), %eax
movzbl 14(%rdi), %ecx
shlq $16, %rcx
orl %eax, %ecx
shlq $32, %rcx
movl 8(%rdi), %edx
orq %rcx, %rdx
movq (%rdi), %rax
ret
A small improvement :-)
llvm-svn: 123520
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
by the SRoA "promote to large integer" code, eliminating
some type conversions like this:
%94 = zext i16 %93 to i32 ; <i32> [#uses=2]
%96 = lshr i32 %94, 8 ; <i32> [#uses=1]
%101 = trunc i32 %96 to i8 ; <i8> [#uses=1]
This also unblocks other xforms from happening, now clang is able to compile:
struct S { float A, B, C, D; };
float foo(struct S A) { return A.A + A.B+A.C+A.D; }
into:
_foo: ## @foo
## BB#0: ## %entry
pshufd $1, %xmm0, %xmm2
addss %xmm0, %xmm2
movdqa %xmm1, %xmm3
addss %xmm2, %xmm3
pshufd $1, %xmm1, %xmm0
addss %xmm3, %xmm0
ret
on x86-64, instead of:
_foo: ## @foo
## BB#0: ## %entry
movd %xmm0, %rax
shrq $32, %rax
movd %eax, %xmm2
addss %xmm0, %xmm2
movapd %xmm1, %xmm3
addss %xmm2, %xmm3
movd %xmm1, %rax
shrq $32, %rax
movd %eax, %xmm0
addss %xmm3, %xmm0
ret
This seems pretty close to optimal to me, at least without
using horizontal adds. This also triggers in lots of other
code, including SPEC.
llvm-svn: 112278
|
