-; RUN: llc < %s -mtriple=i686-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck -check-prefix=X32 %s
-; RUN: llc < %s -mtriple=i386-pc-win32 -mcpu=corei7-avx -mattr=+avx | FileCheck -check-prefix=X32 %s
-; RUN: llc < %s -mtriple=x86_64-win32 -mcpu=corei7-avx -mattr=+avx | FileCheck -check-prefix=WIN64 %s
-; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck -check-prefix=X64 %s
+; RUN: llc < %s -mtriple=i686-apple-darwin -mattr=+avx | FileCheck -check-prefix=X32 %s
+; RUN: llc < %s -mtriple=i386-pc-win32 -mattr=+avx | FileCheck -check-prefix=X32 %s
+; RUN: llc < %s -mtriple=x86_64-win32 -mattr=+avx | FileCheck -check-prefix=WIN64 %s
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx | FileCheck -check-prefix=X64 %s
declare <16 x float> @func_float16_ptr(<16 x float>, <16 x float> *)
declare <16 x float> @func_float16(<16 x float>, <16 x float>)
%y = alloca <16 x float>, align 16
%x = fadd <16 x float> %a, %b
%1 = call intel_ocl_bicc <16 x float> @func_float16_ptr(<16 x float> %x, <16 x float>* %y)
- %2 = load <16 x float>* %y, align 16
+ %2 = load <16 x float>, <16 x float>* %y, align 16
%3 = fadd <16 x float> %2, %1
ret <16 x float> %3
}
%y = alloca <16 x float>, align 16
%x = fadd <16 x float> %a, %b
%1 = call intel_ocl_bicc <16 x float> @func_float16_ptr(<16 x float> %x, <16 x float>* %y)
- %2 = load <16 x float>* %y, align 16
+ %2 = load <16 x float>, <16 x float>* %y, align 16
%3 = fadd <16 x float> %1, %b
%4 = fadd <16 x float> %2, %3
ret <16 x float> %4
; WIN64: vmovaps {{.*(%rbp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; X64-LABEL: test_prolog_epilog
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Spill
; X64: call
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
define intel_ocl_bicc <16 x float> @test_prolog_epilog(<16 x float> %a, <16 x float> %b) nounwind {
%c = call <16 x float> @func_float16(<16 x float> %a, <16 x float> %b)
ret <16 x float> %c