forked from OSchip/llvm-project
561 lines
20 KiB
LLVM
561 lines
20 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -O3 -disable-peephole -mtriple=x86_64-unknown-unknown -mattr=+bmi < %s | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-unknown"
|
|
|
|
; Stack reload folding tests.
|
|
;
|
|
; By including a nop call with sideeffects we can force a partial register spill of the
|
|
; relevant registers and check that the reload is correctly folded into the instruction.
|
|
|
|
define i32 @stack_fold_andn_u32(i32 %a0, i32 %a1) {
|
|
; CHECK-LABEL: stack_fold_andn_u32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: pushq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: pushq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: pushq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: pushq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: pushq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: pushq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 56
|
|
; CHECK-NEXT: .cfi_offset %rbx, -56
|
|
; CHECK-NEXT: .cfi_offset %r12, -48
|
|
; CHECK-NEXT: .cfi_offset %r13, -40
|
|
; CHECK-NEXT: .cfi_offset %r14, -32
|
|
; CHECK-NEXT: .cfi_offset %r15, -24
|
|
; CHECK-NEXT: .cfi_offset %rbp, -16
|
|
; CHECK-NEXT: movl %esi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
|
; CHECK-NEXT: movl %edi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: movl {{[-0-9]+}}(%r{{[sb]}}p), %eax # 4-byte Reload
|
|
; CHECK-NEXT: andnl {{[-0-9]+}}(%r{{[sb]}}p), %eax, %eax # 4-byte Folded Reload
|
|
; CHECK-NEXT: popq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: popq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: popq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: popq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: popq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: popq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call i64 asm sideeffect "nop", "=x,~{rax},~{rbx},~{rcx},~{rdx},~{rsi},~{rdi},~{rbp},~{r8},~{r9},~{r10},~{r11},~{r12},~{r13},~{r14},~{r15}"()
|
|
%2 = xor i32 %a0, -1
|
|
%3 = and i32 %a1, %2
|
|
ret i32 %3
|
|
}
|
|
|
|
define i64 @stack_fold_andn_u64(i64 %a0, i64 %a1) {
|
|
; CHECK-LABEL: stack_fold_andn_u64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: pushq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: pushq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: pushq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: pushq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: pushq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: pushq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 56
|
|
; CHECK-NEXT: .cfi_offset %rbx, -56
|
|
; CHECK-NEXT: .cfi_offset %r12, -48
|
|
; CHECK-NEXT: .cfi_offset %r13, -40
|
|
; CHECK-NEXT: .cfi_offset %r14, -32
|
|
; CHECK-NEXT: .cfi_offset %r15, -24
|
|
; CHECK-NEXT: .cfi_offset %rbp, -16
|
|
; CHECK-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: movq %rdi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
|
|
; CHECK-NEXT: andnq {{[-0-9]+}}(%r{{[sb]}}p), %rax, %rax # 8-byte Folded Reload
|
|
; CHECK-NEXT: popq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: popq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: popq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: popq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: popq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: popq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call i64 asm sideeffect "nop", "=x,~{rax},~{rbx},~{rcx},~{rdx},~{rsi},~{rdi},~{rbp},~{r8},~{r9},~{r10},~{r11},~{r12},~{r13},~{r14},~{r15}"()
|
|
%2 = xor i64 %a0, -1
|
|
%3 = and i64 %a1, %2
|
|
ret i64 %3
|
|
}
|
|
|
|
define i32 @stack_fold_bextr_u32(i32 %a0, i32 %a1) {
|
|
; CHECK-LABEL: stack_fold_bextr_u32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: pushq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: pushq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: pushq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: pushq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: pushq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: pushq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 56
|
|
; CHECK-NEXT: .cfi_offset %rbx, -56
|
|
; CHECK-NEXT: .cfi_offset %r12, -48
|
|
; CHECK-NEXT: .cfi_offset %r13, -40
|
|
; CHECK-NEXT: .cfi_offset %r14, -32
|
|
; CHECK-NEXT: .cfi_offset %r15, -24
|
|
; CHECK-NEXT: .cfi_offset %rbp, -16
|
|
; CHECK-NEXT: movl %esi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
|
; CHECK-NEXT: movl %edi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: movl {{[-0-9]+}}(%r{{[sb]}}p), %eax # 4-byte Reload
|
|
; CHECK-NEXT: bextrl %eax, {{[-0-9]+}}(%r{{[sb]}}p), %eax # 4-byte Folded Reload
|
|
; CHECK-NEXT: popq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: popq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: popq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: popq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: popq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: popq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call i64 asm sideeffect "nop", "=x,~{rax},~{rbx},~{rcx},~{rdx},~{rsi},~{rdi},~{rbp},~{r8},~{r9},~{r10},~{r11},~{r12},~{r13},~{r14},~{r15}"()
|
|
%2 = tail call i32 @llvm.x86.bmi.bextr.32(i32 %a0, i32 %a1)
|
|
ret i32 %2
|
|
}
|
|
declare i32 @llvm.x86.bmi.bextr.32(i32, i32)
|
|
|
|
define i64 @stack_fold_bextr_u64(i64 %a0, i64 %a1) {
|
|
; CHECK-LABEL: stack_fold_bextr_u64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: pushq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: pushq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: pushq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: pushq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: pushq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: pushq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 56
|
|
; CHECK-NEXT: .cfi_offset %rbx, -56
|
|
; CHECK-NEXT: .cfi_offset %r12, -48
|
|
; CHECK-NEXT: .cfi_offset %r13, -40
|
|
; CHECK-NEXT: .cfi_offset %r14, -32
|
|
; CHECK-NEXT: .cfi_offset %r15, -24
|
|
; CHECK-NEXT: .cfi_offset %rbp, -16
|
|
; CHECK-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: movq %rdi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
|
|
; CHECK-NEXT: bextrq %rax, {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Folded Reload
|
|
; CHECK-NEXT: popq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: popq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: popq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: popq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: popq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: popq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call i64 asm sideeffect "nop", "=x,~{rax},~{rbx},~{rcx},~{rdx},~{rsi},~{rdi},~{rbp},~{r8},~{r9},~{r10},~{r11},~{r12},~{r13},~{r14},~{r15}"()
|
|
%2 = tail call i64 @llvm.x86.bmi.bextr.64(i64 %a0, i64 %a1)
|
|
ret i64 %2
|
|
}
|
|
declare i64 @llvm.x86.bmi.bextr.64(i64, i64)
|
|
|
|
define i32 @stack_fold_blsi_u32(i32 %a0) {
|
|
; CHECK-LABEL: stack_fold_blsi_u32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: pushq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: pushq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: pushq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: pushq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: pushq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: pushq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 56
|
|
; CHECK-NEXT: .cfi_offset %rbx, -56
|
|
; CHECK-NEXT: .cfi_offset %r12, -48
|
|
; CHECK-NEXT: .cfi_offset %r13, -40
|
|
; CHECK-NEXT: .cfi_offset %r14, -32
|
|
; CHECK-NEXT: .cfi_offset %r15, -24
|
|
; CHECK-NEXT: .cfi_offset %rbp, -16
|
|
; CHECK-NEXT: movl %edi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: blsil {{[-0-9]+}}(%r{{[sb]}}p), %eax # 4-byte Folded Reload
|
|
; CHECK-NEXT: popq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: popq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: popq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: popq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: popq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: popq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call i64 asm sideeffect "nop", "=x,~{rax},~{rbx},~{rcx},~{rdx},~{rsi},~{rdi},~{rbp},~{r8},~{r9},~{r10},~{r11},~{r12},~{r13},~{r14},~{r15}"()
|
|
%2 = sub i32 0, %a0
|
|
%3 = and i32 %2, %a0
|
|
ret i32 %3
|
|
}
|
|
|
|
define i64 @stack_fold_blsi_u64(i64 %a0) {
|
|
; CHECK-LABEL: stack_fold_blsi_u64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: pushq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: pushq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: pushq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: pushq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: pushq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: pushq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 56
|
|
; CHECK-NEXT: .cfi_offset %rbx, -56
|
|
; CHECK-NEXT: .cfi_offset %r12, -48
|
|
; CHECK-NEXT: .cfi_offset %r13, -40
|
|
; CHECK-NEXT: .cfi_offset %r14, -32
|
|
; CHECK-NEXT: .cfi_offset %r15, -24
|
|
; CHECK-NEXT: .cfi_offset %rbp, -16
|
|
; CHECK-NEXT: movq %rdi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: blsiq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Folded Reload
|
|
; CHECK-NEXT: popq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: popq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: popq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: popq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: popq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: popq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call i64 asm sideeffect "nop", "=x,~{rax},~{rbx},~{rcx},~{rdx},~{rsi},~{rdi},~{rbp},~{r8},~{r9},~{r10},~{r11},~{r12},~{r13},~{r14},~{r15}"()
|
|
%2 = sub i64 0, %a0
|
|
%3 = and i64 %2, %a0
|
|
ret i64 %3
|
|
}
|
|
|
|
define i32 @stack_fold_blsmsk_u32(i32 %a0) {
|
|
; CHECK-LABEL: stack_fold_blsmsk_u32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: pushq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: pushq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: pushq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: pushq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: pushq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: pushq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 56
|
|
; CHECK-NEXT: .cfi_offset %rbx, -56
|
|
; CHECK-NEXT: .cfi_offset %r12, -48
|
|
; CHECK-NEXT: .cfi_offset %r13, -40
|
|
; CHECK-NEXT: .cfi_offset %r14, -32
|
|
; CHECK-NEXT: .cfi_offset %r15, -24
|
|
; CHECK-NEXT: .cfi_offset %rbp, -16
|
|
; CHECK-NEXT: movl %edi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: blsmskl {{[-0-9]+}}(%r{{[sb]}}p), %eax # 4-byte Folded Reload
|
|
; CHECK-NEXT: popq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: popq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: popq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: popq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: popq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: popq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call i64 asm sideeffect "nop", "=x,~{rax},~{rbx},~{rcx},~{rdx},~{rsi},~{rdi},~{rbp},~{r8},~{r9},~{r10},~{r11},~{r12},~{r13},~{r14},~{r15}"()
|
|
%2 = sub i32 %a0, 1
|
|
%3 = xor i32 %2, %a0
|
|
ret i32 %3
|
|
}
|
|
|
|
define i64 @stack_fold_blsmsk_u64(i64 %a0) {
|
|
; CHECK-LABEL: stack_fold_blsmsk_u64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: pushq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: pushq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: pushq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: pushq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: pushq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: pushq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 56
|
|
; CHECK-NEXT: .cfi_offset %rbx, -56
|
|
; CHECK-NEXT: .cfi_offset %r12, -48
|
|
; CHECK-NEXT: .cfi_offset %r13, -40
|
|
; CHECK-NEXT: .cfi_offset %r14, -32
|
|
; CHECK-NEXT: .cfi_offset %r15, -24
|
|
; CHECK-NEXT: .cfi_offset %rbp, -16
|
|
; CHECK-NEXT: movq %rdi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: blsmskq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Folded Reload
|
|
; CHECK-NEXT: popq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: popq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: popq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: popq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: popq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: popq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call i64 asm sideeffect "nop", "=x,~{rax},~{rbx},~{rcx},~{rdx},~{rsi},~{rdi},~{rbp},~{r8},~{r9},~{r10},~{r11},~{r12},~{r13},~{r14},~{r15}"()
|
|
%2 = sub i64 %a0, 1
|
|
%3 = xor i64 %2, %a0
|
|
ret i64 %3
|
|
}
|
|
|
|
define i32 @stack_fold_blsr_u32(i32 %a0) {
|
|
; CHECK-LABEL: stack_fold_blsr_u32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: pushq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: pushq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: pushq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: pushq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: pushq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: pushq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 56
|
|
; CHECK-NEXT: .cfi_offset %rbx, -56
|
|
; CHECK-NEXT: .cfi_offset %r12, -48
|
|
; CHECK-NEXT: .cfi_offset %r13, -40
|
|
; CHECK-NEXT: .cfi_offset %r14, -32
|
|
; CHECK-NEXT: .cfi_offset %r15, -24
|
|
; CHECK-NEXT: .cfi_offset %rbp, -16
|
|
; CHECK-NEXT: movl %edi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: blsrl {{[-0-9]+}}(%r{{[sb]}}p), %eax # 4-byte Folded Reload
|
|
; CHECK-NEXT: popq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: popq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: popq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: popq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: popq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: popq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call i64 asm sideeffect "nop", "=x,~{rax},~{rbx},~{rcx},~{rdx},~{rsi},~{rdi},~{rbp},~{r8},~{r9},~{r10},~{r11},~{r12},~{r13},~{r14},~{r15}"()
|
|
%2 = sub i32 %a0, 1
|
|
%3 = and i32 %2, %a0
|
|
ret i32 %3
|
|
}
|
|
|
|
define i64 @stack_fold_blsr_u64(i64 %a0) {
|
|
; CHECK-LABEL: stack_fold_blsr_u64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: pushq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: pushq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: pushq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: pushq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: pushq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: pushq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 56
|
|
; CHECK-NEXT: .cfi_offset %rbx, -56
|
|
; CHECK-NEXT: .cfi_offset %r12, -48
|
|
; CHECK-NEXT: .cfi_offset %r13, -40
|
|
; CHECK-NEXT: .cfi_offset %r14, -32
|
|
; CHECK-NEXT: .cfi_offset %r15, -24
|
|
; CHECK-NEXT: .cfi_offset %rbp, -16
|
|
; CHECK-NEXT: movq %rdi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: blsrq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Folded Reload
|
|
; CHECK-NEXT: popq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: popq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: popq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: popq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: popq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: popq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call i64 asm sideeffect "nop", "=x,~{rax},~{rbx},~{rcx},~{rdx},~{rsi},~{rdi},~{rbp},~{r8},~{r9},~{r10},~{r11},~{r12},~{r13},~{r14},~{r15}"()
|
|
%2 = sub i64 %a0, 1
|
|
%3 = and i64 %2, %a0
|
|
ret i64 %3
|
|
}
|
|
|
|
;TODO stack_fold_tzcnt_u16
|
|
|
|
define i32 @stack_fold_tzcnt_u32(i32 %a0) {
|
|
; CHECK-LABEL: stack_fold_tzcnt_u32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: pushq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: pushq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: pushq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: pushq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: pushq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: pushq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 56
|
|
; CHECK-NEXT: .cfi_offset %rbx, -56
|
|
; CHECK-NEXT: .cfi_offset %r12, -48
|
|
; CHECK-NEXT: .cfi_offset %r13, -40
|
|
; CHECK-NEXT: .cfi_offset %r14, -32
|
|
; CHECK-NEXT: .cfi_offset %r15, -24
|
|
; CHECK-NEXT: .cfi_offset %rbp, -16
|
|
; CHECK-NEXT: movl %edi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: tzcntl {{[-0-9]+}}(%r{{[sb]}}p), %eax # 4-byte Folded Reload
|
|
; CHECK-NEXT: popq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: popq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: popq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: popq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: popq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: popq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call i64 asm sideeffect "nop", "=x,~{rax},~{rbx},~{rcx},~{rdx},~{rsi},~{rdi},~{rbp},~{r8},~{r9},~{r10},~{r11},~{r12},~{r13},~{r14},~{r15}"()
|
|
%2 = tail call i32 @llvm.cttz.i32(i32 %a0, i1 0)
|
|
ret i32 %2
|
|
}
|
|
declare i32 @llvm.cttz.i32(i32, i1)
|
|
|
|
define i64 @stack_fold_tzcnt_u64(i64 %a0) {
|
|
; CHECK-LABEL: stack_fold_tzcnt_u64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: pushq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: pushq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: pushq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: pushq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: pushq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: pushq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 56
|
|
; CHECK-NEXT: .cfi_offset %rbx, -56
|
|
; CHECK-NEXT: .cfi_offset %r12, -48
|
|
; CHECK-NEXT: .cfi_offset %r13, -40
|
|
; CHECK-NEXT: .cfi_offset %r14, -32
|
|
; CHECK-NEXT: .cfi_offset %r15, -24
|
|
; CHECK-NEXT: .cfi_offset %rbp, -16
|
|
; CHECK-NEXT: movq %rdi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: tzcntq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Folded Reload
|
|
; CHECK-NEXT: popq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: popq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: popq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: popq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: popq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: popq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call i64 asm sideeffect "nop", "=x,~{rax},~{rbx},~{rcx},~{rdx},~{rsi},~{rdi},~{rbp},~{r8},~{r9},~{r10},~{r11},~{r12},~{r13},~{r14},~{r15}"()
|
|
%2 = tail call i64 @llvm.cttz.i64(i64 %a0, i1 0)
|
|
ret i64 %2
|
|
}
|
|
declare i64 @llvm.cttz.i64(i64, i1)
|