+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx,+slow-unaligned-mem-32 | FileCheck %s --check-prefix=AVXSLOW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx,-slow-unaligned-mem-32 | FileCheck %s --check-prefix=AVXFAST
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx2 | FileCheck %s --check-prefix=AVX2
ret <8 x float> %v3
}
+; If the first load is 32-byte aligned, then the loads should be merged in all cases.
+
+define <8 x float> @combine_16_byte_loads_aligned(<4 x float>* %ptr) {
+; AVXSLOW-LABEL: combine_16_byte_loads_aligned:
+; AVXSLOW: # BB#0:
+; AVXSLOW-NEXT: vmovaps 48(%rdi), %ymm0
+; AVXSLOW-NEXT: retq
+;
+; AVXFAST-LABEL: combine_16_byte_loads_aligned:
+; AVXFAST: # BB#0:
+; AVXFAST-NEXT: vmovaps 48(%rdi), %ymm0
+; AVXFAST-NEXT: retq
+;
+; AVX2-LABEL: combine_16_byte_loads_aligned:
+; AVX2: # BB#0:
+; AVX2-NEXT: vmovaps 48(%rdi), %ymm0
+; AVX2-NEXT: retq
+ %ptr1 = getelementptr inbounds <4 x float>, <4 x float>* %ptr, i64 3
+ %ptr2 = getelementptr inbounds <4 x float>, <4 x float>* %ptr, i64 4
+ %v1 = load <4 x float>, <4 x float>* %ptr1, align 32
+ %v2 = load <4 x float>, <4 x float>* %ptr2, align 1
+ %v3 = shufflevector <4 x float> %v1, <4 x float> %v2, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+ ret <8 x float> %v3
+}
+
; Swap the order of the shufflevector operands to ensure that the pattern still matches.
define <8 x float> @combine_16_byte_loads_no_intrinsic_swap(<4 x float>* %ptr) {