[llvm] ae81400 - [X86] keylocker-intrinsics.ll - replace X32 checks with X86. NFC.
Simon Pilgrim via llvm-commits
llvm-commits at lists.llvm.org
Fri Jan 5 05:39:19 PST 2024
Author: Simon Pilgrim
Date: 2024-01-05T13:38:44Z
New Revision: ae81400a0fad6040483f1af5947388aecca5c3f7
URL: https://github.com/llvm/llvm-project/commit/ae81400a0fad6040483f1af5947388aecca5c3f7
DIFF: https://github.com/llvm/llvm-project/commit/ae81400a0fad6040483f1af5947388aecca5c3f7.diff
LOG: [X86] keylocker-intrinsics.ll - replace X32 checks with X86. NFC.
We try to use X32 for gnux32 triples only.
Added:
Modified:
llvm/test/CodeGen/X86/keylocker-intrinsics.ll
Removed:
################################################################################
diff --git a/llvm/test/CodeGen/X86/keylocker-intrinsics.ll b/llvm/test/CodeGen/X86/keylocker-intrinsics.ll
index 3892d84e57db82..f01411c64acb08 100644
--- a/llvm/test/CodeGen/X86/keylocker-intrinsics.ll
+++ b/llvm/test/CodeGen/X86/keylocker-intrinsics.ll
@@ -1,8 +1,8 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -verify-machineinstrs -mtriple=x86_64-unkown-unknown -mattr=+kl,widekl | FileCheck %s --check-prefix=X64
-; RUN: llc < %s -verify-machineinstrs -mtriple=i386-unkown-unknown -mattr=+kl,widekl -mattr=+avx2 | FileCheck %s --check-prefix=X32
+; RUN: llc < %s -verify-machineinstrs -mtriple=i386-unkown-unknown -mattr=+kl,widekl -mattr=+avx2 | FileCheck %s --check-prefix=X86
; RUN: llc < %s -verify-machineinstrs -mtriple=x86_64-unkown-unknown -mattr=+widekl | FileCheck %s --check-prefix=X64
-; RUN: llc < %s -verify-machineinstrs -mtriple=i386-unkown-unknown -mattr=+widekl -mattr=+avx2 | FileCheck %s --check-prefix=X32
+; RUN: llc < %s -verify-machineinstrs -mtriple=i386-unkown-unknown -mattr=+widekl -mattr=+avx2 | FileCheck %s --check-prefix=X86
declare void @llvm.x86.loadiwkey(<2 x i64>, <2 x i64>, <2 x i64>, i32)
declare { i32, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } @llvm.x86.encodekey128(i32, <2 x i64>)
@@ -23,11 +23,11 @@ define void @test_loadiwkey(i32 %ctl, <2 x i64> %intkey, <2 x i64> %enkey_lo, <2
; X64-NEXT: loadiwkey %xmm2, %xmm1
; X64-NEXT: retq
;
-; X32-LABEL: test_loadiwkey:
-; X32: # %bb.0: # %entry
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: loadiwkey %xmm2, %xmm1
-; X32-NEXT: retl
+; X86-LABEL: test_loadiwkey:
+; X86: # %bb.0: # %entry
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: loadiwkey %xmm2, %xmm1
+; X86-NEXT: retl
entry:
tail call void @llvm.x86.loadiwkey(<2 x i64> %intkey, <2 x i64> %enkey_lo, <2 x i64> %enkey_hi, i32 %ctl)
ret void
@@ -42,19 +42,19 @@ define i32 @test_encodekey128_u32(i32 %htype, <2 x i64> %key, ptr nocapture %h0,
; X64-NEXT: movaps %xmm2, (%rcx)
; X64-NEXT: retq
;
-; X32-LABEL: test_encodekey128_u32:
-; X32: # %bb.0: # %entry
-; X32-NEXT: pushl %esi
-; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT: movl {{[0-9]+}}(%esp), %edx
-; X32-NEXT: movl {{[0-9]+}}(%esp), %esi
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: encodekey128 %eax, %eax
-; X32-NEXT: vmovaps %xmm0, (%esi)
-; X32-NEXT: vmovaps %xmm1, (%edx)
-; X32-NEXT: vmovaps %xmm2, (%ecx)
-; X32-NEXT: popl %esi
-; X32-NEXT: retl
+; X86-LABEL: test_encodekey128_u32:
+; X86: # %bb.0: # %entry
+; X86-NEXT: pushl %esi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: encodekey128 %eax, %eax
+; X86-NEXT: vmovaps %xmm0, (%esi)
+; X86-NEXT: vmovaps %xmm1, (%edx)
+; X86-NEXT: vmovaps %xmm2, (%ecx)
+; X86-NEXT: popl %esi
+; X86-NEXT: retl
entry:
%0 = tail call { i32, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } @llvm.x86.encodekey128(i32 %htype, <2 x i64> %key)
%1 = extractvalue { i32, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } %0, 1
@@ -77,23 +77,23 @@ define i32 @test_encodekey256_u32(i32 %htype, <2 x i64> %key_lo, <2 x i64> %key_
; X64-NEXT: movaps %xmm3, (%r8)
; X64-NEXT: retq
;
-; X32-LABEL: test_encodekey256_u32:
-; X32: # %bb.0: # %entry
-; X32-NEXT: pushl %edi
-; X32-NEXT: pushl %esi
-; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT: movl {{[0-9]+}}(%esp), %edx
-; X32-NEXT: movl {{[0-9]+}}(%esp), %esi
-; X32-NEXT: movl {{[0-9]+}}(%esp), %edi
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: encodekey256 %eax, %eax
-; X32-NEXT: vmovaps %xmm0, (%edi)
-; X32-NEXT: vmovaps %xmm1, (%esi)
-; X32-NEXT: vmovaps %xmm2, (%edx)
-; X32-NEXT: vmovaps %xmm3, (%ecx)
-; X32-NEXT: popl %esi
-; X32-NEXT: popl %edi
-; X32-NEXT: retl
+; X86-LABEL: test_encodekey256_u32:
+; X86: # %bb.0: # %entry
+; X86-NEXT: pushl %edi
+; X86-NEXT: pushl %esi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: encodekey256 %eax, %eax
+; X86-NEXT: vmovaps %xmm0, (%edi)
+; X86-NEXT: vmovaps %xmm1, (%esi)
+; X86-NEXT: vmovaps %xmm2, (%edx)
+; X86-NEXT: vmovaps %xmm3, (%ecx)
+; X86-NEXT: popl %esi
+; X86-NEXT: popl %edi
+; X86-NEXT: retl
entry:
%0 = tail call { i32, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } @llvm.x86.encodekey256(i32 %htype, <2 x i64> %key_lo, <2 x i64> %key_hi)
%1 = extractvalue { i32, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } %0, 1
@@ -116,14 +116,14 @@ define i8 @test_mm_aesenc128kl_u8(<2 x i64> %data, ptr %h, ptr %out) {
; X64-NEXT: movaps %xmm0, (%rsi)
; X64-NEXT: retq
;
-; X32-LABEL: test_mm_aesenc128kl_u8:
-; X32: # %bb.0: # %entry
-; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: aesenc128kl (%eax), %xmm0
-; X32-NEXT: sete %al
-; X32-NEXT: vmovaps %xmm0, (%ecx)
-; X32-NEXT: retl
+; X86-LABEL: test_mm_aesenc128kl_u8:
+; X86: # %bb.0: # %entry
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: aesenc128kl (%eax), %xmm0
+; X86-NEXT: sete %al
+; X86-NEXT: vmovaps %xmm0, (%ecx)
+; X86-NEXT: retl
entry:
%0 = tail call { i8, <2 x i64> } @llvm.x86.aesenc128kl(<2 x i64> %data, ptr %h)
%1 = extractvalue { i8, <2 x i64> } %0, 1
@@ -140,14 +140,14 @@ define i8 @test_mm_aesdec128kl_u8(<2 x i64> %data, ptr %h, ptr %out) {
; X64-NEXT: movaps %xmm0, (%rsi)
; X64-NEXT: retq
;
-; X32-LABEL: test_mm_aesdec128kl_u8:
-; X32: # %bb.0: # %entry
-; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: aesdec128kl (%eax), %xmm0
-; X32-NEXT: sete %al
-; X32-NEXT: vmovaps %xmm0, (%ecx)
-; X32-NEXT: retl
+; X86-LABEL: test_mm_aesdec128kl_u8:
+; X86: # %bb.0: # %entry
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: aesdec128kl (%eax), %xmm0
+; X86-NEXT: sete %al
+; X86-NEXT: vmovaps %xmm0, (%ecx)
+; X86-NEXT: retl
entry:
%0 = tail call { i8, <2 x i64> } @llvm.x86.aesdec128kl(<2 x i64> %data, ptr %h)
%1 = extractvalue { i8, <2 x i64> } %0, 1
@@ -164,14 +164,14 @@ define i8 @test_mm_aesenc256kl_u8(<2 x i64> %data, ptr %h, ptr %out) {
; X64-NEXT: movaps %xmm0, (%rsi)
; X64-NEXT: retq
;
-; X32-LABEL: test_mm_aesenc256kl_u8:
-; X32: # %bb.0: # %entry
-; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: aesenc256kl (%eax), %xmm0
-; X32-NEXT: sete %al
-; X32-NEXT: vmovaps %xmm0, (%ecx)
-; X32-NEXT: retl
+; X86-LABEL: test_mm_aesenc256kl_u8:
+; X86: # %bb.0: # %entry
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: aesenc256kl (%eax), %xmm0
+; X86-NEXT: sete %al
+; X86-NEXT: vmovaps %xmm0, (%ecx)
+; X86-NEXT: retl
entry:
%0 = tail call { i8, <2 x i64> } @llvm.x86.aesenc256kl(<2 x i64> %data, ptr %h)
%1 = extractvalue { i8, <2 x i64> } %0, 1
@@ -188,14 +188,14 @@ define i8 @test_mm_aesdec256kl_u8(<2 x i64> %data, ptr %h, ptr %out) {
; X64-NEXT: movaps %xmm0, (%rsi)
; X64-NEXT: retq
;
-; X32-LABEL: test_mm_aesdec256kl_u8:
-; X32: # %bb.0: # %entry
-; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: aesdec256kl (%eax), %xmm0
-; X32-NEXT: sete %al
-; X32-NEXT: vmovaps %xmm0, (%ecx)
-; X32-NEXT: retl
+; X86-LABEL: test_mm_aesdec256kl_u8:
+; X86: # %bb.0: # %entry
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: aesdec256kl (%eax), %xmm0
+; X86-NEXT: sete %al
+; X86-NEXT: vmovaps %xmm0, (%ecx)
+; X86-NEXT: retl
entry:
%0 = tail call { i8, <2 x i64> } @llvm.x86.aesdec256kl(<2 x i64> %data, ptr %h)
%1 = extractvalue { i8, <2 x i64> } %0, 1
@@ -224,39 +224,39 @@ define i8 @test_mm_aesencwide128kl_u8(ptr %p, <2 x i64> %v0, <2 x i64> %v1, <2 x
; X64-NEXT: popq %rbx
; X64-NEXT: retq
;
-; X32-LABEL: test_mm_aesencwide128kl_u8:
-; X32: # %bb.0: # %entry
-; X32-NEXT: pushl %ebp
-; X32-NEXT: movl %esp, %ebp
-; X32-NEXT: andl $-16, %esp
-; X32-NEXT: subl $16, %esp
-; X32-NEXT: vmovaps 24(%ebp), %xmm3
-; X32-NEXT: vmovaps 40(%ebp), %xmm4
-; X32-NEXT: vmovaps 56(%ebp), %xmm5
-; X32-NEXT: vmovaps 72(%ebp), %xmm6
-; X32-NEXT: vmovaps 88(%ebp), %xmm7
-; X32-NEXT: movl 8(%ebp), %eax
-; X32-NEXT: aesencwide128kl (%eax)
-; X32-NEXT: movl 104(%ebp), %eax
-; X32-NEXT: vmovaps %xmm0, (%eax)
-; X32-NEXT: movl 108(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 112(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 116(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 120(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 124(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 128(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 132(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: sete %al
-; X32-NEXT: movl %ebp, %esp
-; X32-NEXT: popl %ebp
-; X32-NEXT: retl
+; X86-LABEL: test_mm_aesencwide128kl_u8:
+; X86: # %bb.0: # %entry
+; X86-NEXT: pushl %ebp
+; X86-NEXT: movl %esp, %ebp
+; X86-NEXT: andl $-16, %esp
+; X86-NEXT: subl $16, %esp
+; X86-NEXT: vmovaps 24(%ebp), %xmm3
+; X86-NEXT: vmovaps 40(%ebp), %xmm4
+; X86-NEXT: vmovaps 56(%ebp), %xmm5
+; X86-NEXT: vmovaps 72(%ebp), %xmm6
+; X86-NEXT: vmovaps 88(%ebp), %xmm7
+; X86-NEXT: movl 8(%ebp), %eax
+; X86-NEXT: aesencwide128kl (%eax)
+; X86-NEXT: movl 104(%ebp), %eax
+; X86-NEXT: vmovaps %xmm0, (%eax)
+; X86-NEXT: movl 108(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 112(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 116(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 120(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 124(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 128(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 132(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: sete %al
+; X86-NEXT: movl %ebp, %esp
+; X86-NEXT: popl %ebp
+; X86-NEXT: retl
entry:
%0 = call { i8, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } @llvm.x86.aesencwide128kl(ptr %p, <2 x i64> %v0, <2 x i64> %v1, <2 x i64> %v2, <2 x i64> %v3, <2 x i64> %v4, <2 x i64> %v5, <2 x i64> %v6, <2 x i64> %v7)
%1 = extractvalue { i8, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } %0, 1
@@ -299,39 +299,39 @@ define i8 @test_mm_aesdecwide128kl_u8(ptr %p, <2 x i64> %v0, <2 x i64> %v1, <2 x
; X64-NEXT: popq %rbx
; X64-NEXT: retq
;
-; X32-LABEL: test_mm_aesdecwide128kl_u8:
-; X32: # %bb.0: # %entry
-; X32-NEXT: pushl %ebp
-; X32-NEXT: movl %esp, %ebp
-; X32-NEXT: andl $-16, %esp
-; X32-NEXT: subl $16, %esp
-; X32-NEXT: vmovaps 24(%ebp), %xmm3
-; X32-NEXT: vmovaps 40(%ebp), %xmm4
-; X32-NEXT: vmovaps 56(%ebp), %xmm5
-; X32-NEXT: vmovaps 72(%ebp), %xmm6
-; X32-NEXT: vmovaps 88(%ebp), %xmm7
-; X32-NEXT: movl 8(%ebp), %eax
-; X32-NEXT: aesdecwide128kl (%eax)
-; X32-NEXT: movl 104(%ebp), %eax
-; X32-NEXT: vmovaps %xmm0, (%eax)
-; X32-NEXT: movl 108(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 112(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 116(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 120(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 124(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 128(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 132(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: sete %al
-; X32-NEXT: movl %ebp, %esp
-; X32-NEXT: popl %ebp
-; X32-NEXT: retl
+; X86-LABEL: test_mm_aesdecwide128kl_u8:
+; X86: # %bb.0: # %entry
+; X86-NEXT: pushl %ebp
+; X86-NEXT: movl %esp, %ebp
+; X86-NEXT: andl $-16, %esp
+; X86-NEXT: subl $16, %esp
+; X86-NEXT: vmovaps 24(%ebp), %xmm3
+; X86-NEXT: vmovaps 40(%ebp), %xmm4
+; X86-NEXT: vmovaps 56(%ebp), %xmm5
+; X86-NEXT: vmovaps 72(%ebp), %xmm6
+; X86-NEXT: vmovaps 88(%ebp), %xmm7
+; X86-NEXT: movl 8(%ebp), %eax
+; X86-NEXT: aesdecwide128kl (%eax)
+; X86-NEXT: movl 104(%ebp), %eax
+; X86-NEXT: vmovaps %xmm0, (%eax)
+; X86-NEXT: movl 108(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 112(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 116(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 120(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 124(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 128(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 132(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: sete %al
+; X86-NEXT: movl %ebp, %esp
+; X86-NEXT: popl %ebp
+; X86-NEXT: retl
entry:
%0 = call { i8, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } @llvm.x86.aesdecwide128kl(ptr %p, <2 x i64> %v0, <2 x i64> %v1, <2 x i64> %v2, <2 x i64> %v3, <2 x i64> %v4, <2 x i64> %v5, <2 x i64> %v6, <2 x i64> %v7)
%1 = extractvalue { i8, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } %0, 1
@@ -374,39 +374,39 @@ define i8 @test_mm_aesencwide256kl_u8(ptr %p, <2 x i64> %v0, <2 x i64> %v1, <2 x
; X64-NEXT: popq %rbx
; X64-NEXT: retq
;
-; X32-LABEL: test_mm_aesencwide256kl_u8:
-; X32: # %bb.0: # %entry
-; X32-NEXT: pushl %ebp
-; X32-NEXT: movl %esp, %ebp
-; X32-NEXT: andl $-16, %esp
-; X32-NEXT: subl $16, %esp
-; X32-NEXT: vmovaps 24(%ebp), %xmm3
-; X32-NEXT: vmovaps 40(%ebp), %xmm4
-; X32-NEXT: vmovaps 56(%ebp), %xmm5
-; X32-NEXT: vmovaps 72(%ebp), %xmm6
-; X32-NEXT: vmovaps 88(%ebp), %xmm7
-; X32-NEXT: movl 8(%ebp), %eax
-; X32-NEXT: aesencwide256kl (%eax)
-; X32-NEXT: movl 104(%ebp), %eax
-; X32-NEXT: vmovaps %xmm0, (%eax)
-; X32-NEXT: movl 108(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 112(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 116(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 120(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 124(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 128(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 132(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: sete %al
-; X32-NEXT: movl %ebp, %esp
-; X32-NEXT: popl %ebp
-; X32-NEXT: retl
+; X86-LABEL: test_mm_aesencwide256kl_u8:
+; X86: # %bb.0: # %entry
+; X86-NEXT: pushl %ebp
+; X86-NEXT: movl %esp, %ebp
+; X86-NEXT: andl $-16, %esp
+; X86-NEXT: subl $16, %esp
+; X86-NEXT: vmovaps 24(%ebp), %xmm3
+; X86-NEXT: vmovaps 40(%ebp), %xmm4
+; X86-NEXT: vmovaps 56(%ebp), %xmm5
+; X86-NEXT: vmovaps 72(%ebp), %xmm6
+; X86-NEXT: vmovaps 88(%ebp), %xmm7
+; X86-NEXT: movl 8(%ebp), %eax
+; X86-NEXT: aesencwide256kl (%eax)
+; X86-NEXT: movl 104(%ebp), %eax
+; X86-NEXT: vmovaps %xmm0, (%eax)
+; X86-NEXT: movl 108(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 112(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 116(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 120(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 124(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 128(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 132(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: sete %al
+; X86-NEXT: movl %ebp, %esp
+; X86-NEXT: popl %ebp
+; X86-NEXT: retl
entry:
%0 = call { i8, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } @llvm.x86.aesencwide256kl(ptr %p, <2 x i64> %v0, <2 x i64> %v1, <2 x i64> %v2, <2 x i64> %v3, <2 x i64> %v4, <2 x i64> %v5, <2 x i64> %v6, <2 x i64> %v7)
%1 = extractvalue { i8, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } %0, 1
@@ -449,39 +449,39 @@ define i8 @test_mm_aesdecwide256kl_u8(ptr %p, <2 x i64> %v0, <2 x i64> %v1, <2 x
; X64-NEXT: popq %rbx
; X64-NEXT: retq
;
-; X32-LABEL: test_mm_aesdecwide256kl_u8:
-; X32: # %bb.0: # %entry
-; X32-NEXT: pushl %ebp
-; X32-NEXT: movl %esp, %ebp
-; X32-NEXT: andl $-16, %esp
-; X32-NEXT: subl $16, %esp
-; X32-NEXT: vmovaps 24(%ebp), %xmm3
-; X32-NEXT: vmovaps 40(%ebp), %xmm4
-; X32-NEXT: vmovaps 56(%ebp), %xmm5
-; X32-NEXT: vmovaps 72(%ebp), %xmm6
-; X32-NEXT: vmovaps 88(%ebp), %xmm7
-; X32-NEXT: movl 8(%ebp), %eax
-; X32-NEXT: aesdecwide256kl (%eax)
-; X32-NEXT: movl 104(%ebp), %eax
-; X32-NEXT: vmovaps %xmm0, (%eax)
-; X32-NEXT: movl 108(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 112(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 116(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 120(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 124(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 128(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 132(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: sete %al
-; X32-NEXT: movl %ebp, %esp
-; X32-NEXT: popl %ebp
-; X32-NEXT: retl
+; X86-LABEL: test_mm_aesdecwide256kl_u8:
+; X86: # %bb.0: # %entry
+; X86-NEXT: pushl %ebp
+; X86-NEXT: movl %esp, %ebp
+; X86-NEXT: andl $-16, %esp
+; X86-NEXT: subl $16, %esp
+; X86-NEXT: vmovaps 24(%ebp), %xmm3
+; X86-NEXT: vmovaps 40(%ebp), %xmm4
+; X86-NEXT: vmovaps 56(%ebp), %xmm5
+; X86-NEXT: vmovaps 72(%ebp), %xmm6
+; X86-NEXT: vmovaps 88(%ebp), %xmm7
+; X86-NEXT: movl 8(%ebp), %eax
+; X86-NEXT: aesdecwide256kl (%eax)
+; X86-NEXT: movl 104(%ebp), %eax
+; X86-NEXT: vmovaps %xmm0, (%eax)
+; X86-NEXT: movl 108(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 112(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 116(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 120(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 124(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 128(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 132(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: sete %al
+; X86-NEXT: movl %ebp, %esp
+; X86-NEXT: popl %ebp
+; X86-NEXT: retl
entry:
%0 = call { i8, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } @llvm.x86.aesdecwide256kl(ptr %p, <2 x i64> %v0, <2 x i64> %v1, <2 x i64> %v2, <2 x i64> %v3, <2 x i64> %v4, <2 x i64> %v5, <2 x i64> %v6, <2 x i64> %v7)
%1 = extractvalue { i8, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } %0, 1
@@ -516,13 +516,13 @@ define i8 @test_mm_aesenc256kl_u8_global(<2 x i64> %data, ptr %out) {
; X64-NEXT: movaps %xmm0, (%rdi)
; X64-NEXT: retq
;
-; X32-LABEL: test_mm_aesenc256kl_u8_global:
-; X32: # %bb.0: # %entry
-; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT: aesenc256kl foo, %xmm0
-; X32-NEXT: sete %al
-; X32-NEXT: vmovaps %xmm0, (%ecx)
-; X32-NEXT: retl
+; X86-LABEL: test_mm_aesenc256kl_u8_global:
+; X86: # %bb.0: # %entry
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: aesenc256kl foo, %xmm0
+; X86-NEXT: sete %al
+; X86-NEXT: vmovaps %xmm0, (%ecx)
+; X86-NEXT: retl
entry:
%0 = tail call { i8, <2 x i64> } @llvm.x86.aesenc256kl(<2 x i64> %data, ptr @foo)
%1 = extractvalue { i8, <2 x i64> } %0, 1
@@ -548,38 +548,38 @@ define i8 @test_mm_aesdecwide256kl_u8_global(<2 x i64> %v0, <2 x i64> %v1, <2 x
; X64-NEXT: movaps %xmm1, (%r10)
; X64-NEXT: retq
;
-; X32-LABEL: test_mm_aesdecwide256kl_u8_global:
-; X32: # %bb.0: # %entry
-; X32-NEXT: pushl %ebp
-; X32-NEXT: movl %esp, %ebp
-; X32-NEXT: andl $-16, %esp
-; X32-NEXT: subl $16, %esp
-; X32-NEXT: movl 88(%ebp), %eax
-; X32-NEXT: vmovaps 8(%ebp), %xmm3
-; X32-NEXT: vmovaps 24(%ebp), %xmm4
-; X32-NEXT: vmovaps 40(%ebp), %xmm5
-; X32-NEXT: vmovaps 56(%ebp), %xmm6
-; X32-NEXT: vmovaps 72(%ebp), %xmm7
-; X32-NEXT: aesdecwide256kl foo
-; X32-NEXT: vmovaps %xmm0, (%eax)
-; X32-NEXT: movl 92(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 96(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 100(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 104(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 108(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 112(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: movl 116(%ebp), %eax
-; X32-NEXT: vmovaps %xmm1, (%eax)
-; X32-NEXT: sete %al
-; X32-NEXT: movl %ebp, %esp
-; X32-NEXT: popl %ebp
-; X32-NEXT: retl
+; X86-LABEL: test_mm_aesdecwide256kl_u8_global:
+; X86: # %bb.0: # %entry
+; X86-NEXT: pushl %ebp
+; X86-NEXT: movl %esp, %ebp
+; X86-NEXT: andl $-16, %esp
+; X86-NEXT: subl $16, %esp
+; X86-NEXT: movl 88(%ebp), %eax
+; X86-NEXT: vmovaps 8(%ebp), %xmm3
+; X86-NEXT: vmovaps 24(%ebp), %xmm4
+; X86-NEXT: vmovaps 40(%ebp), %xmm5
+; X86-NEXT: vmovaps 56(%ebp), %xmm6
+; X86-NEXT: vmovaps 72(%ebp), %xmm7
+; X86-NEXT: aesdecwide256kl foo
+; X86-NEXT: vmovaps %xmm0, (%eax)
+; X86-NEXT: movl 92(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 96(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 100(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 104(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 108(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 112(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: movl 116(%ebp), %eax
+; X86-NEXT: vmovaps %xmm1, (%eax)
+; X86-NEXT: sete %al
+; X86-NEXT: movl %ebp, %esp
+; X86-NEXT: popl %ebp
+; X86-NEXT: retl
entry:
%0 = call { i8, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } @llvm.x86.aesdecwide256kl(ptr @foo, <2 x i64> %v0, <2 x i64> %v1, <2 x i64> %v2, <2 x i64> %v3, <2 x i64> %v4, <2 x i64> %v5, <2 x i64> %v6, <2 x i64> %v7)
%1 = extractvalue { i8, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64>, <2 x i64> } %0, 1
More information about the llvm-commits
mailing list