TheRock/compiler/amd-llvm/llvm/test/CodeGen/X86/x86-64-double-precision-shift-right.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=bdver1 | FileCheck %s

; Verify that for the architectures that are known to have poor latency
; double precision shift instructions we generate alternative sequence
; of instructions with lower latencies instead of shrd instruction.

;uint64_t rshift1(uint64_t a, uint64_t b)
;{
;    return (a >> 1) | (b << 63);
;}

define i64 @rshift1(i64 %a, i64 %b) nounwind readnone uwtable {
; CHECK-LABEL: rshift1:
; CHECK:       # %bb.0:
; CHECK-NEXT:    shrq %rdi
; CHECK-NEXT:    shlq $63, %rsi
; CHECK-NEXT:    leaq (%rsi,%rdi), %rax
; CHECK-NEXT:    retq
  %1 = lshr i64 %a, 1
  %2 = shl i64 %b, 63
  %3 = or i64 %2, %1
  ret i64 %3
}

;uint64_t rshift2(uint64_t a, uint64_t b)
;{
;    return (a >> 2) | (b << 62);
;}

define i64 @rshift2(i64 %a, i64 %b) nounwind readnone uwtable {
; CHECK-LABEL: rshift2:
; CHECK:       # %bb.0:
; CHECK-NEXT:    shrq $2, %rdi
; CHECK-NEXT:    shlq $62, %rsi
; CHECK-NEXT:    leaq (%rsi,%rdi), %rax
; CHECK-NEXT:    retq
  %1 = lshr i64 %a, 2
  %2 = shl i64 %b, 62
  %3 = or i64 %2, %1
  ret i64 %3
}

;uint64_t rshift7(uint64_t a, uint64_t b)
;{
;    return (a >> 7) | (b << 57);
;}

define i64 @rshift7(i64 %a, i64 %b) nounwind readnone uwtable {
; CHECK-LABEL: rshift7:
; CHECK:       # %bb.0:
; CHECK-NEXT:    shrq $7, %rdi
; CHECK-NEXT:    shlq $57, %rsi
; CHECK-NEXT:    leaq (%rsi,%rdi), %rax
; CHECK-NEXT:    retq
  %1 = lshr i64 %a, 7
  %2 = shl i64 %b, 57
  %3 = or i64 %2, %1
  ret i64 %3
}

;uint64_t rshift63(uint64_t a, uint64_t b)
;{
;    return (a >> 63) | (b << 1);
;}

define i64 @rshift63(i64 %a, i64 %b) nounwind readnone uwtable {
; CHECK-LABEL: rshift63:
; CHECK:       # %bb.0:
; CHECK-NEXT:    shrq $63, %rdi
; CHECK-NEXT:    leaq (%rdi,%rsi,2), %rax
; CHECK-NEXT:    retq
  %1 = lshr i64 %a, 63
  %2 = shl i64 %b, 1
  %3 = or i64 %2, %1
  ret i64 %3
}