If we're loading a vector constant that is known to be zero in the upper elements, then attempt to shrink the constant and just scalar load the lower 32/64 bits. Always chose the vzload/broadcast with the smallest constant load, and prefer vzload over broadcasts for same bitwidth to avoid domain flips (mainly a AVX1 issue). Fixes #73783
18 lines
544 B
LLVM
18 lines
544 B
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=i386-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X86
|
|
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X64
|
|
|
|
define <2 x i64> @test1() nounwind {
|
|
; X86-LABEL: test1:
|
|
; X86: # %bb.0:
|
|
; X86-NEXT: movss {{.*#+}} xmm0 = [1,0,0,0]
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: test1:
|
|
; X64: # %bb.0:
|
|
; X64-NEXT: movss {{.*#+}} xmm0 = [1,0,0,0]
|
|
; X64-NEXT: retq
|
|
ret <2 x i64> < i64 1, i64 0 >
|
|
}
|
|
|