summaryrefslogtreecommitdiff
path: root/test/CodeGen/ARM
diff options
context:
space:
mode:
Diffstat (limited to 'test/CodeGen/ARM')
-rw-r--r--test/CodeGen/ARM/2012-08-30-select.ll7
-rw-r--r--test/CodeGen/ARM/GlobalISel/arm-instruction-select-cmp.mir373
-rw-r--r--test/CodeGen/ARM/GlobalISel/arm-irtranslator.ll7
-rw-r--r--test/CodeGen/ARM/GlobalISel/arm-isel.ll41
-rw-r--r--test/CodeGen/ARM/GlobalISel/arm-legalizer.mir84
-rw-r--r--test/CodeGen/ARM/GlobalISel/arm-regbankselect.mir30
-rw-r--r--test/CodeGen/ARM/alloca-align.ll2
-rw-r--r--test/CodeGen/ARM/constantfp.ll50
-rw-r--r--test/CodeGen/ARM/execute-only-big-stack-frame.ll4
-rw-r--r--test/CodeGen/ARM/fpoffset_overflow.mir12
-rw-r--r--test/CodeGen/ARM/misched-fusion-aes.ll203
-rw-r--r--test/CodeGen/ARM/v6m-umul-with-overflow.ll16
-rw-r--r--test/CodeGen/ARM/vector-promotion.ll4
-rw-r--r--test/CodeGen/ARM/xray-armv6-attribute-instrumentation.ll9
-rw-r--r--test/CodeGen/ARM/xray-armv7-attribute-instrumentation.ll9
15 files changed, 825 insertions, 26 deletions
diff --git a/test/CodeGen/ARM/2012-08-30-select.ll b/test/CodeGen/ARM/2012-08-30-select.ll
index dbedad2637b73..97b732beb4d79 100644
--- a/test/CodeGen/ARM/2012-08-30-select.ll
+++ b/test/CodeGen/ARM/2012-08-30-select.ll
@@ -2,10 +2,9 @@
; rdar://12201387
;CHECK-LABEL: select_s_v_v:
-;CHECK: itee ne
-;CHECK-NEXT: vmovne.i32
-;CHECK-NEXT: vmoveq
-;CHECK-NEXT: vmoveq
+;CHECK: vmov
+;CHECK-NEXT: vmov
+;CHECK: vmov.i32
;CHECK: bx
define <16 x i8> @select_s_v_v(<16 x i8> %vec, i32 %avail) {
entry:
diff --git a/test/CodeGen/ARM/GlobalISel/arm-instruction-select-cmp.mir b/test/CodeGen/ARM/GlobalISel/arm-instruction-select-cmp.mir
new file mode 100644
index 0000000000000..111375ece51ba
--- /dev/null
+++ b/test/CodeGen/ARM/GlobalISel/arm-instruction-select-cmp.mir
@@ -0,0 +1,373 @@
+# RUN: llc -O0 -mtriple arm-- -global-isel -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s
+--- |
+ define void @test_icmp_eq_s32() { ret void }
+ define void @test_icmp_ne_s32() { ret void }
+ define void @test_icmp_ugt_s32() { ret void }
+ define void @test_icmp_uge_s32() { ret void }
+ define void @test_icmp_ult_s32() { ret void }
+ define void @test_icmp_ule_s32() { ret void }
+ define void @test_icmp_sgt_s32() { ret void }
+ define void @test_icmp_sge_s32() { ret void }
+ define void @test_icmp_slt_s32() { ret void }
+ define void @test_icmp_sle_s32() { ret void }
+...
+---
+name: test_icmp_eq_s32
+# CHECK-LABEL: name: test_icmp_eq_s32
+legalized: true
+regBankSelected: true
+selected: false
+# CHECK: selected: true
+registers:
+ - { id: 0, class: gprb }
+ - { id: 1, class: gprb }
+ - { id: 2, class: gprb }
+ - { id: 3, class: gprb }
+body: |
+ bb.0:
+ liveins: %r0, %r1
+
+ %0(s32) = COPY %r0
+ ; CHECK: [[VREGX:%[0-9]+]] = COPY %r0
+
+ %1(s32) = COPY %r1
+ ; CHECK: [[VREGY:%[0-9]+]] = COPY %r1
+
+ %2(s1) = G_ICMP intpred(eq), %0(s32), %1
+ ; CHECK: [[ZERO:%[0-9]+]] = MOVi 0, 14, _, _
+ ; CHECK: CMPrr [[VREGX]], [[VREGY]], 14, _, implicit-def %cpsr
+ ; CHECK: [[RES:%[0-9]+]] = MOVCCi [[ZERO]], 1, 0, %cpsr
+
+ %3(s32) = G_ZEXT %2(s1)
+ ; CHECK: [[RET:%[0-9]+]] = ANDri [[RES]], 1, 14, _, _
+
+ %r0 = COPY %3(s32)
+ ; CHECK: %r0 = COPY [[RET]]
+
+ BX_RET 14, _, implicit %r0
+ ; CHECK: BX_RET 14, _, implicit %r0
+...
+---
+name: test_icmp_ne_s32
+# CHECK-LABEL: name: test_icmp_ne_s32
+legalized: true
+regBankSelected: true
+selected: false
+# CHECK: selected: true
+registers:
+ - { id: 0, class: gprb }
+ - { id: 1, class: gprb }
+ - { id: 2, class: gprb }
+ - { id: 3, class: gprb }
+body: |
+ bb.0:
+ liveins: %r0, %r1
+
+ %0(s32) = COPY %r0
+ ; CHECK: [[VREGX:%[0-9]+]] = COPY %r0
+
+ %1(s32) = COPY %r1
+ ; CHECK: [[VREGY:%[0-9]+]] = COPY %r1
+
+ %2(s1) = G_ICMP intpred(ne), %0(s32), %1
+ ; CHECK: [[ZERO:%[0-9]+]] = MOVi 0, 14, _, _
+ ; CHECK: CMPrr [[VREGX]], [[VREGY]], 14, _, implicit-def %cpsr
+ ; CHECK: [[RES:%[0-9]+]] = MOVCCi [[ZERO]], 1, 1, %cpsr
+
+ %3(s32) = G_ZEXT %2(s1)
+ ; CHECK: [[RET:%[0-9]+]] = ANDri [[RES]], 1, 14, _, _
+
+ %r0 = COPY %3(s32)
+ ; CHECK: %r0 = COPY [[RET]]
+
+ BX_RET 14, _, implicit %r0
+ ; CHECK: BX_RET 14, _, implicit %r0
+...
+---
+name: test_icmp_ugt_s32
+# CHECK-LABEL: name: test_icmp_ugt_s32
+legalized: true
+regBankSelected: true
+selected: false
+# CHECK: selected: true
+registers:
+ - { id: 0, class: gprb }
+ - { id: 1, class: gprb }
+ - { id: 2, class: gprb }
+ - { id: 3, class: gprb }
+body: |
+ bb.0:
+ liveins: %r0, %r1
+
+ %0(s32) = COPY %r0
+ ; CHECK: [[VREGX:%[0-9]+]] = COPY %r0
+
+ %1(s32) = COPY %r1
+ ; CHECK: [[VREGY:%[0-9]+]] = COPY %r1
+
+ %2(s1) = G_ICMP intpred(ugt), %0(s32), %1
+ ; CHECK: [[ZERO:%[0-9]+]] = MOVi 0, 14, _, _
+ ; CHECK: CMPrr [[VREGX]], [[VREGY]], 14, _, implicit-def %cpsr
+ ; CHECK: [[RES:%[0-9]+]] = MOVCCi [[ZERO]], 1, 8, %cpsr
+
+ %3(s32) = G_ZEXT %2(s1)
+ ; CHECK: [[RET:%[0-9]+]] = ANDri [[RES]], 1, 14, _, _
+
+ %r0 = COPY %3(s32)
+ ; CHECK: %r0 = COPY [[RET]]
+
+ BX_RET 14, _, implicit %r0
+ ; CHECK: BX_RET 14, _, implicit %r0
+...
+---
+name: test_icmp_uge_s32
+# CHECK-LABEL: name: test_icmp_uge_s32
+legalized: true
+regBankSelected: true
+selected: false
+# CHECK: selected: true
+registers:
+ - { id: 0, class: gprb }
+ - { id: 1, class: gprb }
+ - { id: 2, class: gprb }
+ - { id: 3, class: gprb }
+body: |
+ bb.0:
+ liveins: %r0, %r1
+
+ %0(s32) = COPY %r0
+ ; CHECK: [[VREGX:%[0-9]+]] = COPY %r0
+
+ %1(s32) = COPY %r1
+ ; CHECK: [[VREGY:%[0-9]+]] = COPY %r1
+
+ %2(s1) = G_ICMP intpred(uge), %0(s32), %1
+ ; CHECK: [[ZERO:%[0-9]+]] = MOVi 0, 14, _, _
+ ; CHECK: CMPrr [[VREGX]], [[VREGY]], 14, _, implicit-def %cpsr
+ ; CHECK: [[RES:%[0-9]+]] = MOVCCi [[ZERO]], 1, 2, %cpsr
+
+ %3(s32) = G_ZEXT %2(s1)
+ ; CHECK: [[RET:%[0-9]+]] = ANDri [[RES]], 1, 14, _, _
+
+ %r0 = COPY %3(s32)
+ ; CHECK: %r0 = COPY [[RET]]
+
+ BX_RET 14, _, implicit %r0
+ ; CHECK: BX_RET 14, _, implicit %r0
+...
+---
+name: test_icmp_ult_s32
+# CHECK-LABEL: name: test_icmp_ult_s32
+legalized: true
+regBankSelected: true
+selected: false
+# CHECK: selected: true
+registers:
+ - { id: 0, class: gprb }
+ - { id: 1, class: gprb }
+ - { id: 2, class: gprb }
+ - { id: 3, class: gprb }
+body: |
+ bb.0:
+ liveins: %r0, %r1
+
+ %0(s32) = COPY %r0
+ ; CHECK: [[VREGX:%[0-9]+]] = COPY %r0
+
+ %1(s32) = COPY %r1
+ ; CHECK: [[VREGY:%[0-9]+]] = COPY %r1
+
+ %2(s1) = G_ICMP intpred(ult), %0(s32), %1
+ ; CHECK: [[ZERO:%[0-9]+]] = MOVi 0, 14, _, _
+ ; CHECK: CMPrr [[VREGX]], [[VREGY]], 14, _, implicit-def %cpsr
+ ; CHECK: [[RES:%[0-9]+]] = MOVCCi [[ZERO]], 1, 3, %cpsr
+
+ %3(s32) = G_ZEXT %2(s1)
+ ; CHECK: [[RET:%[0-9]+]] = ANDri [[RES]], 1, 14, _, _
+
+ %r0 = COPY %3(s32)
+ ; CHECK: %r0 = COPY [[RET]]
+
+ BX_RET 14, _, implicit %r0
+ ; CHECK: BX_RET 14, _, implicit %r0
+...
+---
+name: test_icmp_ule_s32
+# CHECK-LABEL: name: test_icmp_ule_s32
+legalized: true
+regBankSelected: true
+selected: false
+# CHECK: selected: true
+registers:
+ - { id: 0, class: gprb }
+ - { id: 1, class: gprb }
+ - { id: 2, class: gprb }
+ - { id: 3, class: gprb }
+body: |
+ bb.0:
+ liveins: %r0, %r1
+
+ %0(s32) = COPY %r0
+ ; CHECK: [[VREGX:%[0-9]+]] = COPY %r0
+
+ %1(s32) = COPY %r1
+ ; CHECK: [[VREGY:%[0-9]+]] = COPY %r1
+
+ %2(s1) = G_ICMP intpred(ule), %0(s32), %1
+ ; CHECK: [[ZERO:%[0-9]+]] = MOVi 0, 14, _, _
+ ; CHECK: CMPrr [[VREGX]], [[VREGY]], 14, _, implicit-def %cpsr
+ ; CHECK: [[RES:%[0-9]+]] = MOVCCi [[ZERO]], 1, 9, %cpsr
+
+ %3(s32) = G_ZEXT %2(s1)
+ ; CHECK: [[RET:%[0-9]+]] = ANDri [[RES]], 1, 14, _, _
+
+ %r0 = COPY %3(s32)
+ ; CHECK: %r0 = COPY [[RET]]
+
+ BX_RET 14, _, implicit %r0
+ ; CHECK: BX_RET 14, _, implicit %r0
+...
+---
+name: test_icmp_sgt_s32
+# CHECK-LABEL: name: test_icmp_sgt_s32
+legalized: true
+regBankSelected: true
+selected: false
+# CHECK: selected: true
+registers:
+ - { id: 0, class: gprb }
+ - { id: 1, class: gprb }
+ - { id: 2, class: gprb }
+ - { id: 3, class: gprb }
+body: |
+ bb.0:
+ liveins: %r0, %r1
+
+ %0(s32) = COPY %r0
+ ; CHECK: [[VREGX:%[0-9]+]] = COPY %r0
+
+ %1(s32) = COPY %r1
+ ; CHECK: [[VREGY:%[0-9]+]] = COPY %r1
+
+ %2(s1) = G_ICMP intpred(sgt), %0(s32), %1
+ ; CHECK: [[ZERO:%[0-9]+]] = MOVi 0, 14, _, _
+ ; CHECK: CMPrr [[VREGX]], [[VREGY]], 14, _, implicit-def %cpsr
+ ; CHECK: [[RES:%[0-9]+]] = MOVCCi [[ZERO]], 1, 12, %cpsr
+
+ %3(s32) = G_ZEXT %2(s1)
+ ; CHECK: [[RET:%[0-9]+]] = ANDri [[RES]], 1, 14, _, _
+
+ %r0 = COPY %3(s32)
+ ; CHECK: %r0 = COPY [[RET]]
+
+ BX_RET 14, _, implicit %r0
+ ; CHECK: BX_RET 14, _, implicit %r0
+...
+---
+name: test_icmp_sge_s32
+# CHECK-LABEL: name: test_icmp_sge_s32
+legalized: true
+regBankSelected: true
+selected: false
+# CHECK: selected: true
+registers:
+ - { id: 0, class: gprb }
+ - { id: 1, class: gprb }
+ - { id: 2, class: gprb }
+ - { id: 3, class: gprb }
+body: |
+ bb.0:
+ liveins: %r0, %r1
+
+ %0(s32) = COPY %r0
+ ; CHECK: [[VREGX:%[0-9]+]] = COPY %r0
+
+ %1(s32) = COPY %r1
+ ; CHECK: [[VREGY:%[0-9]+]] = COPY %r1
+
+ %2(s1) = G_ICMP intpred(sge), %0(s32), %1
+ ; CHECK: [[ZERO:%[0-9]+]] = MOVi 0, 14, _, _
+ ; CHECK: CMPrr [[VREGX]], [[VREGY]], 14, _, implicit-def %cpsr
+ ; CHECK: [[RES:%[0-9]+]] = MOVCCi [[ZERO]], 1, 10, %cpsr
+
+ %3(s32) = G_ZEXT %2(s1)
+ ; CHECK: [[RET:%[0-9]+]] = ANDri [[RES]], 1, 14, _, _
+
+ %r0 = COPY %3(s32)
+ ; CHECK: %r0 = COPY [[RET]]
+
+ BX_RET 14, _, implicit %r0
+ ; CHECK: BX_RET 14, _, implicit %r0
+...
+---
+name: test_icmp_slt_s32
+# CHECK-LABEL: name: test_icmp_slt_s32
+legalized: true
+regBankSelected: true
+selected: false
+# CHECK: selected: true
+registers:
+ - { id: 0, class: gprb }
+ - { id: 1, class: gprb }
+ - { id: 2, class: gprb }
+ - { id: 3, class: gprb }
+body: |
+ bb.0:
+ liveins: %r0, %r1
+
+ %0(s32) = COPY %r0
+ ; CHECK: [[VREGX:%[0-9]+]] = COPY %r0
+
+ %1(s32) = COPY %r1
+ ; CHECK: [[VREGY:%[0-9]+]] = COPY %r1
+
+ %2(s1) = G_ICMP intpred(slt), %0(s32), %1
+ ; CHECK: [[ZERO:%[0-9]+]] = MOVi 0, 14, _, _
+ ; CHECK: CMPrr [[VREGX]], [[VREGY]], 14, _, implicit-def %cpsr
+ ; CHECK: [[RES:%[0-9]+]] = MOVCCi [[ZERO]], 1, 11, %cpsr
+
+ %3(s32) = G_ZEXT %2(s1)
+ ; CHECK: [[RET:%[0-9]+]] = ANDri [[RES]], 1, 14, _, _
+
+ %r0 = COPY %3(s32)
+ ; CHECK: %r0 = COPY [[RET]]
+
+ BX_RET 14, _, implicit %r0
+ ; CHECK: BX_RET 14, _, implicit %r0
+...
+---
+name: test_icmp_sle_s32
+# CHECK-LABEL: name: test_icmp_sle_s32
+legalized: true
+regBankSelected: true
+selected: false
+# CHECK: selected: true
+registers:
+ - { id: 0, class: gprb }
+ - { id: 1, class: gprb }
+ - { id: 2, class: gprb }
+ - { id: 3, class: gprb }
+body: |
+ bb.0:
+ liveins: %r0, %r1
+
+ %0(s32) = COPY %r0
+ ; CHECK: [[VREGX:%[0-9]+]] = COPY %r0
+
+ %1(s32) = COPY %r1
+ ; CHECK: [[VREGY:%[0-9]+]] = COPY %r1
+
+ %2(s1) = G_ICMP intpred(sle), %0(s32), %1
+ ; CHECK: [[ZERO:%[0-9]+]] = MOVi 0, 14, _, _
+ ; CHECK: CMPrr [[VREGX]], [[VREGY]], 14, _, implicit-def %cpsr
+ ; CHECK: [[RES:%[0-9]+]] = MOVCCi [[ZERO]], 1, 13, %cpsr
+
+ %3(s32) = G_ZEXT %2(s1)
+ ; CHECK: [[RET:%[0-9]+]] = ANDri [[RES]], 1, 14, _, _
+
+ %r0 = COPY %3(s32)
+ ; CHECK: %r0 = COPY [[RET]]
+
+ BX_RET 14, _, implicit %r0
+ ; CHECK: BX_RET 14, _, implicit %r0
+...
diff --git a/test/CodeGen/ARM/GlobalISel/arm-irtranslator.ll b/test/CodeGen/ARM/GlobalISel/arm-irtranslator.ll
index 6663a9210b870..0ff8d52e94c62 100644
--- a/test/CodeGen/ARM/GlobalISel/arm-irtranslator.ll
+++ b/test/CodeGen/ARM/GlobalISel/arm-irtranslator.ll
@@ -1009,8 +1009,11 @@ define i32 @test_constantstruct_v2s32_s32_s32() {
; CHECK: [[VEC:%[0-9]+]](<2 x s32>) = G_MERGE_VALUES [[C1]](s32), [[C2]](s32)
; CHECK: [[C3:%[0-9]+]](s32) = G_CONSTANT i32 3
; CHECK: [[C4:%[0-9]+]](s32) = G_CONSTANT i32 4
-; CHECK: [[CS:%[0-9]+]](s128) = G_SEQUENCE [[VEC]](<2 x s32>), 0, [[C3]](s32), 64, [[C4]](s32), 96
-; CHECK: [[EXT:%[0-9]+]](<2 x s32>) = G_EXTRACT [[CS]](s128), 0
+; CHECK: [[C5:%[0-9]+]](s128) = IMPLICIT_DEF
+; CHECK: [[C6:%[0-9]+]](s128) = G_INSERT [[C5]], [[VEC]](<2 x s32>), 0
+; CHECK: [[C7:%[0-9]+]](s128) = G_INSERT [[C6]], [[C3]](s32), 64
+; CHECK: [[C8:%[0-9]+]](s128) = G_INSERT [[C7]], [[C4]](s32), 96
+; CHECK: [[EXT:%[0-9]+]](<2 x s32>) = G_EXTRACT [[C8]](s128), 0
; CHECK: G_EXTRACT_VECTOR_ELT [[EXT]](<2 x s32>)
%vec = extractvalue %struct.v2s32.s32.s32 {<2 x i32><i32 1, i32 2>, i32 3, i32 4}, 0
%elt = extractelement <2 x i32> %vec, i32 0
diff --git a/test/CodeGen/ARM/GlobalISel/arm-isel.ll b/test/CodeGen/ARM/GlobalISel/arm-isel.ll
index 6ddc29a3bbbae..76fb39ecea013 100644
--- a/test/CodeGen/ARM/GlobalISel/arm-isel.ll
+++ b/test/CodeGen/ARM/GlobalISel/arm-isel.ll
@@ -359,3 +359,44 @@ entry:
%v = fadd double %f0, %f1
ret double %v
}
+
+define arm_aapcscc i32 @test_cmp_i32_eq(i32 %a, i32 %b) {
+; CHECK-LABEL: test_cmp_i32_eq:
+; CHECK: mov [[V:r[0-9]+]], #0
+; CHECK: cmp r0, r1
+; CHECK: moveq [[V]], #1
+; CHECK: and r0, [[V]], #1
+; CHECK: bx lr
+entry:
+ %v = icmp eq i32 %a, %b
+ %r = zext i1 %v to i32
+ ret i32 %r
+}
+
+define arm_aapcscc i32 @test_cmp_ptr_neq(double *%a, double *%b) {
+; CHECK-LABEL: test_cmp_ptr_neq:
+; CHECK: mov [[V:r[0-9]+]], #0
+; CHECK: cmp r0, r1
+; CHECK: movne [[V]], #1
+; CHECK: and r0, [[V]], #1
+; CHECK: bx lr
+entry:
+ %v = icmp ne double * %a, %b
+ %r = zext i1 %v to i32
+ ret i32 %r
+}
+
+define arm_aapcscc i32 @test_cmp_i16_slt(i16 %a, i16 %b) {
+; CHECK-LABEL: test_cmp_i16_slt:
+; CHECK-DAG: sxth r0, r0
+; CHECK-DAG: sxth r1, r1
+; CHECK-DAG: mov [[V:r[0-9]+]], #0
+; CHECK: cmp r0, r1
+; CHECK: movlt [[V]], #1
+; CHECK: and r0, [[V]], #1
+; CHECK: bx lr
+entry:
+ %v = icmp slt i16 %a, %b
+ %r = zext i1 %v to i32
+ ret i32 %r
+}
diff --git a/test/CodeGen/ARM/GlobalISel/arm-legalizer.mir b/test/CodeGen/ARM/GlobalISel/arm-legalizer.mir
index c6f6ca81c2795..2def31eb15929 100644
--- a/test/CodeGen/ARM/GlobalISel/arm-legalizer.mir
+++ b/test/CodeGen/ARM/GlobalISel/arm-legalizer.mir
@@ -35,6 +35,10 @@
define void @test_constants() { ret void }
+ define void @test_icmp_s8() { ret void }
+ define void @test_icmp_s16() { ret void }
+ define void @test_icmp_s32() { ret void }
+
define void @test_fadd_s32() #0 { ret void }
define void @test_fadd_s64() #0 { ret void }
@@ -691,6 +695,86 @@ body: |
BX_RET 14, _, implicit %r0
...
---
+name: test_icmp_s8
+# CHECK-LABEL: name: test_icmp_s8
+legalized: false
+# CHECK: legalized: true
+regBankSelected: false
+selected: false
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: _ }
+ - { id: 1, class: _ }
+ - { id: 2, class: _ }
+ - { id: 3, class: _ }
+body: |
+ bb.0:
+ liveins: %r0, %r1
+
+ %0(s8) = COPY %r0
+ %1(s8) = COPY %r1
+ %2(s1) = G_ICMP intpred(ne), %0(s8), %1
+ ; G_ICMP with s8 should widen
+ ; CHECK: {{%[0-9]+}}(s1) = G_ICMP intpred(ne), {{%[0-9]+}}(s32), {{%[0-9]+}}
+ ; CHECK-NOT: {{%[0-9]+}}(s1) = G_ICMP intpred(ne), {{%[0-9]+}}(s8), {{%[0-9]+}}
+ %3(s32) = G_ZEXT %2(s1)
+ %r0 = COPY %3(s32)
+ BX_RET 14, _, implicit %r0
+...
+---
+name: test_icmp_s16
+# CHECK-LABEL: name: test_icmp_s16
+legalized: false
+# CHECK: legalized: true
+regBankSelected: false
+selected: false
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: _ }
+ - { id: 1, class: _ }
+ - { id: 2, class: _ }
+ - { id: 3, class: _ }
+body: |
+ bb.0:
+ liveins: %r0, %r1
+
+ %0(s16) = COPY %r0
+ %1(s16) = COPY %r1
+ %2(s1) = G_ICMP intpred(slt), %0(s16), %1
+ ; G_ICMP with s16 should widen
+ ; CHECK: {{%[0-9]+}}(s1) = G_ICMP intpred(slt), {{%[0-9]+}}(s32), {{%[0-9]+}}
+ ; CHECK-NOT: {{%[0-9]+}}(s1) = G_ICMP intpred(slt), {{%[0-9]+}}(s16), {{%[0-9]+}}
+ %3(s32) = G_ZEXT %2(s1)
+ %r0 = COPY %3(s32)
+ BX_RET 14, _, implicit %r0
+...
+---
+name: test_icmp_s32
+# CHECK-LABEL: name: test_icmp_s32
+legalized: false
+# CHECK: legalized: true
+regBankSelected: false
+selected: false
+tracksRegLiveness: true
+registers:
+ - { id: 0, class: _ }
+ - { id: 1, class: _ }
+ - { id: 2, class: _ }
+ - { id: 3, class: _ }
+body: |
+ bb.0:
+ liveins: %r0, %r1
+
+ %0(s32) = COPY %r0
+ %1(s32) = COPY %r1
+ %2(s1) = G_ICMP intpred(eq), %0(s32), %1
+ ; G_ICMP with s32 is legal, so we should find it unchanged in the output
+ ; CHECK: {{%[0-9]+}}(s1) = G_ICMP intpred(eq), {{%[0-9]+}}(s32), {{%[0-9]+}}
+ %3(s32) = G_ZEXT %2(s1)
+ %r0 = COPY %3(s32)
+ BX_RET 14, _, implicit %r0
+...
+---
name: test_fadd_s32
# CHECK-LABEL: name: test_fadd_s32
legalized: false
diff --git a/test/CodeGen/ARM/GlobalISel/arm-regbankselect.mir b/test/CodeGen/ARM/GlobalISel/arm-regbankselect.mir
index cc1df80c60191..d97dd60bac223 100644
--- a/test/CodeGen/ARM/GlobalISel/arm-regbankselect.mir
+++ b/test/CodeGen/ARM/GlobalISel/arm-regbankselect.mir
@@ -34,6 +34,8 @@
define void @test_trunc_s32_16() { ret void }
+ define void @test_icmp_eq_s32() { ret void }
+
define void @test_fadd_s32() #0 { ret void }
define void @test_fadd_s64() #0 { ret void }
@@ -711,6 +713,34 @@ body: |
BX_RET 14, _, implicit %r0
...
---
+name: test_icmp_eq_s32
+# CHECK-LABEL: name: test_icmp_eq_s32
+legalized: true
+regBankSelected: false
+selected: false
+# CHECK: registers:
+# CHECK: - { id: 0, class: gprb, preferred-register: '' }
+# CHECK: - { id: 1, class: gprb, preferred-register: '' }
+# CHECK: - { id: 2, class: gprb, preferred-register: '' }
+
+registers:
+ - { id: 0, class: _ }
+ - { id: 1, class: _ }
+ - { id: 2, class: _ }
+ - { id: 3, class: _ }
+body: |
+ bb.0:
+ liveins: %r0, %r1
+
+ %0(s32) = COPY %r0
+ %1(s32) = COPY %r1
+ %2(s1) = G_ICMP intpred(eq), %0(s32), %1
+ %3(s32) = G_ZEXT %2(s1)
+ %r0 = COPY %3(s32)
+ BX_RET 14, _, implicit %r0
+
+...
+---
name: test_fadd_s32
# CHECK-LABEL: name: test_fadd_s32
legalized: true
diff --git a/test/CodeGen/ARM/alloca-align.ll b/test/CodeGen/ARM/alloca-align.ll
index 3bba156f0ee06..6186d137ef7fd 100644
--- a/test/CodeGen/ARM/alloca-align.ll
+++ b/test/CodeGen/ARM/alloca-align.ll
@@ -12,7 +12,7 @@ declare void @bar(i32*, [20000 x i8]* byval)
; And a base pointer getting used.
; CHECK: mov r6, sp
; Which is passed to the call
-; CHECK: add [[REG:r[0-9]+]], r6, #19456
+; CHECK: add [[REG:r[0-9]+|lr]], r6, #19456
; CHECK: add r0, [[REG]], #536
; CHECK: bl bar
define void @foo([20000 x i8]* %addr) {
diff --git a/test/CodeGen/ARM/constantfp.ll b/test/CodeGen/ARM/constantfp.ll
index b5aeadc05eba4..0b431f47f50bf 100644
--- a/test/CodeGen/ARM/constantfp.ll
+++ b/test/CodeGen/ARM/constantfp.ll
@@ -11,6 +11,9 @@
; RUN: llc -mtriple=thumbv7meb -arm-execute-only -mcpu=cortex-m4 %s -o - \
; RUN: | FileCheck --check-prefix=CHECK-XO-FLOAT --check-prefix=CHECK-XO-DOUBLE-BE %s
+; RUN: llc -mtriple=thumbv7m -arm-execute-only -mcpu=cortex-m4 -relocation-model=ropi %s -o - \
+; RUN: | FileCheck --check-prefix=CHECK-XO-ROPI %s
+
; RUN: llc -mtriple=thumbv8m.main -mattr=fp-armv8 %s -o - \
; RUN: | FileCheck --check-prefix=CHECK-NO-XO %s
@@ -20,6 +23,8 @@
; RUN: llc -mtriple=thumbv8m.maineb -arm-execute-only -mattr=fp-armv8 %s -o - \
; RUN: | FileCheck --check-prefix=CHECK-XO-FLOAT --check-prefix=CHECK-XO-DOUBLE-BE %s
+; RUN: llc -mtriple=thumbv8m.main -arm-execute-only -mattr=fp-armv8 -relocation-model=ropi %s -o - \
+; RUN: | FileCheck --check-prefix=CHECK-XO-ROPI %s
define arm_aapcs_vfpcc float @test_vmov_f32() {
; CHECK-LABEL: test_vmov_f32:
@@ -176,3 +181,48 @@ define arm_aapcs_vfpcc double @lower_const_f64_xo() {
; CHECK-XO-DOUBLE-BE-NOT: vldr
ret double 3.140000e-01
}
+
+; This is a target independent optimization, performed by the
+; DAG Combiner, which promotes floating point literals into
+; constant pools:
+;
+; (a cond b) ? 1.0f : 2.0f -> load (ConstPoolAddr + ((a cond b) ? 0 : 4)
+;
+; We need to make sure that the constant pools are placed in
+; the data section when generating execute-only code:
+
+define arm_aapcs_vfpcc float @lower_fpconst_select(float %f) {
+
+; CHECK-NO-XO-LABEL: lower_fpconst_select
+; CHECK-NO-XO: adr [[REG:r[0-9]+]], [[LABEL:.?LCPI[0-9]+_[0-9]+]]
+; CHECK-NO-XO: vldr {{s[0-9]+}}, {{[[]}}[[REG]]{{[]]}}
+; CHECK-NO-XO-NOT: .rodata
+; CHECK-NO-XO: [[LABEL]]:
+; CHECK-NO-XO: .long 1335165689
+; CHECK-NO-XO: .long 1307470632
+
+; CHECK-XO-FLOAT-LABEL: lower_fpconst_select
+; CHECK-XO-FLOAT: movw [[REG:r[0-9]+]], :lower16:[[LABEL:.?LCP[0-9]+_[0-9]+]]
+; CHECK-XO-FLOAT: movt [[REG]], :upper16:[[LABEL]]
+; CHECK-XO-FLOAT: vldr {{s[0-9]+}}, {{[[]}}[[REG]]{{[]]}}
+; CHECK-XO-FLOAT: .rodata
+; CHECK-XO-FLOAT-NOT: .text
+; CHECK-XO-FLOAT: [[LABEL]]:
+; CHECK-XO-FLOAT: .long 1335165689
+; CHECK-XO-FLOAT: .long 1307470632
+
+; CHECK-XO-ROPI-LABEL: lower_fpconst_select
+; CHECK-XO-ROPI: movw [[REG:r[0-9]+]], :lower16:([[LABEL1:.?LCP[0-9]+_[0-9]+]]-([[LABEL2:.?LPC[0-9]+_[0-9]+]]+4))
+; CHECK-XO-ROPI: movt [[REG]], :upper16:([[LABEL1]]-([[LABEL2]]+4))
+; CHECK-XO-ROPI: [[LABEL2]]:
+; CHECK-XO-ROPI: vldr {{s[0-9]+}}, {{[[]}}[[REG]]{{[]]}}
+; CHECK-XO-ROPI: .rodata
+; CHECK-XO-ROPI-NOT: .text
+; CHECK-XO-ROPI: [[LABEL1]]:
+; CHECK-XO-ROPI: .long 1335165689
+; CHECK-XO-ROPI: .long 1307470632
+
+ %cmp = fcmp nnan oeq float %f, 0.000000e+00
+ %sel = select i1 %cmp, float 5.000000e+08, float 5.000000e+09
+ ret float %sel
+}
diff --git a/test/CodeGen/ARM/execute-only-big-stack-frame.ll b/test/CodeGen/ARM/execute-only-big-stack-frame.ll
index fb498a81e390a..0fe67f9863a58 100644
--- a/test/CodeGen/ARM/execute-only-big-stack-frame.ll
+++ b/test/CodeGen/ARM/execute-only-big-stack-frame.ll
@@ -10,10 +10,10 @@ define i8 @test_big_stack_frame() {
; CHECK-SUBW-ADDW-NOT: ldr {{r[0-9]+}}, .{{.*}}
; CHECK-SUBW-ADDW: sub.w sp, sp, #65536
; CHECK-SUBW-ADDW-NOT: ldr {{r[0-9]+}}, .{{.*}}
-; CHECK-SUBW-ADDW: add.w [[REG1:r[0-9]+]], sp, #255
+; CHECK-SUBW-ADDW: add.w [[REG1:r[0-9]+|lr]], sp, #255
; CHECK-SUBW-ADDW: add.w {{r[0-9]+}}, [[REG1]], #65280
; CHECK-SUBW-ADDW-NOT: ldr {{r[0-9]+}}, .{{.*}}
-; CHECK-SUBW-ADDW: add.w lr, sp, #61440
+; CHECK-SUBW-ADDW: add.w [[REGX:r[0-9]+|lr]], sp, #61440
; CHECK-SUBW-ADDW-NOT: ldr {{r[0-9]+}}, .{{.*}}
; CHECK-SUBW-ADDW: add.w sp, sp, #65536
diff --git a/test/CodeGen/ARM/fpoffset_overflow.mir b/test/CodeGen/ARM/fpoffset_overflow.mir
index 9c6cd931b1532..4f3524bf7d117 100644
--- a/test/CodeGen/ARM/fpoffset_overflow.mir
+++ b/test/CodeGen/ARM/fpoffset_overflow.mir
@@ -3,10 +3,10 @@
# This should trigger an emergency spill in the register scavenger because the
# frame offset into the large argument is too large.
# CHECK-LABEL: name: func0
-# CHECK: t2STRi12 killed %r7, %sp, 0, 14, _ :: (store 4 into %stack.0)
-# CHECK: %r7 = t2ADDri killed %sp, 4096, 14, _, _
-# CHECK: %r11 = t2LDRi12 killed %r7, 36, 14, _ :: (load 4)
-# CHECK: %r7 = t2LDRi12 %sp, 0, 14, _ :: (load 4 from %stack.0)
+# CHECK: t2STRi12 killed [[SPILLED:%r[0-9]+]], %sp, 0, 14, _ :: (store 4 into %stack.0)
+# CHECK: [[SPILLED]] = t2ADDri killed %sp, 4096, 14, _, _
+# CHECK: %sp = t2LDRi12 killed [[SPILLED]], 40, 14, _ :: (load 4)
+# CHECK: [[SPILLED]] = t2LDRi12 %sp, 0, 14, _ :: (load 4 from %stack.0)
name: func0
tracksRegLiveness: true
fixedStack:
@@ -23,6 +23,7 @@ body: |
%r4 = IMPLICIT_DEF
%r5 = IMPLICIT_DEF
%r6 = IMPLICIT_DEF
+ %r7 = IMPLICIT_DEF
%r8 = IMPLICIT_DEF
%r9 = IMPLICIT_DEF
%r10 = IMPLICIT_DEF
@@ -30,7 +31,7 @@ body: |
%r12 = IMPLICIT_DEF
%lr = IMPLICIT_DEF
- %r11 = t2LDRi12 %fixed-stack.0, 0, 14, _ :: (load 4)
+ %sp = t2LDRi12 %fixed-stack.0, 0, 14, _ :: (load 4)
KILL %r0
KILL %r1
@@ -39,6 +40,7 @@ body: |
KILL %r4
KILL %r5
KILL %r6
+ KILL %r7
KILL %r8
KILL %r9
KILL %r10
diff --git a/test/CodeGen/ARM/misched-fusion-aes.ll b/test/CodeGen/ARM/misched-fusion-aes.ll
new file mode 100644
index 0000000000000..d3558ab4abb07
--- /dev/null
+++ b/test/CodeGen/ARM/misched-fusion-aes.ll
@@ -0,0 +1,203 @@
+; RUN: llc %s -o - -mtriple=armv8 -mattr=+crypto,+fuse-aes -enable-misched -disable-post-ra | FileCheck %s
+
+declare <16 x i8> @llvm.arm.neon.aese(<16 x i8> %d, <16 x i8> %k)
+declare <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %d)
+declare <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %d, <16 x i8> %k)
+declare <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %d)
+
+define void @aesea(<16 x i8>* %a0, <16 x i8>* %b0, <16 x i8>* %c0, <16 x i8> %d, <16 x i8> %e) {
+ %d0 = load <16 x i8>, <16 x i8>* %a0
+ %a1 = getelementptr inbounds <16 x i8>, <16 x i8>* %a0, i64 1
+ %d1 = load <16 x i8>, <16 x i8>* %a1
+ %a2 = getelementptr inbounds <16 x i8>, <16 x i8>* %a0, i64 2
+ %d2 = load <16 x i8>, <16 x i8>* %a2
+ %a3 = getelementptr inbounds <16 x i8>, <16 x i8>* %a0, i64 3
+ %d3 = load <16 x i8>, <16 x i8>* %a3
+ %k0 = load <16 x i8>, <16 x i8>* %b0
+ %e00 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %d0, <16 x i8> %k0)
+ %f00 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e00)
+ %e01 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %d1, <16 x i8> %k0)
+ %f01 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e01)
+ %e02 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %d2, <16 x i8> %k0)
+ %f02 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e02)
+ %e03 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %d3, <16 x i8> %k0)
+ %f03 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e03)
+ %b1 = getelementptr inbounds <16 x i8>, <16 x i8>* %b0, i64 1
+ %k1 = load <16 x i8>, <16 x i8>* %b1
+ %e10 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f00, <16 x i8> %k1)
+ %f10 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e00)
+ %e11 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f01, <16 x i8> %k1)
+ %f11 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e01)
+ %e12 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f02, <16 x i8> %k1)
+ %f12 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e02)
+ %e13 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f03, <16 x i8> %k1)
+ %f13 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e03)
+ %b2 = getelementptr inbounds <16 x i8>, <16 x i8>* %b0, i64 2
+ %k2 = load <16 x i8>, <16 x i8>* %b2
+ %e20 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f10, <16 x i8> %k2)
+ %f20 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e10)
+ %e21 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f11, <16 x i8> %k2)
+ %f21 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e11)
+ %e22 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f12, <16 x i8> %k2)
+ %f22 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e12)
+ %e23 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f13, <16 x i8> %k2)
+ %f23 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e13)
+ %b3 = getelementptr inbounds <16 x i8>, <16 x i8>* %b0, i64 3
+ %k3 = load <16 x i8>, <16 x i8>* %b3
+ %e30 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f20, <16 x i8> %k3)
+ %f30 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e20)
+ %e31 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f21, <16 x i8> %k3)
+ %f31 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e21)
+ %e32 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f22, <16 x i8> %k3)
+ %f32 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e22)
+ %e33 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f23, <16 x i8> %k3)
+ %f33 = call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %e23)
+ %g0 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f30, <16 x i8> %d)
+ %h0 = xor <16 x i8> %g0, %e
+ %g1 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f31, <16 x i8> %d)
+ %h1 = xor <16 x i8> %g1, %e
+ %g2 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f32, <16 x i8> %d)
+ %h2 = xor <16 x i8> %g2, %e
+ %g3 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %f33, <16 x i8> %d)
+ %h3 = xor <16 x i8> %g3, %e
+ store <16 x i8> %h0, <16 x i8>* %c0
+ %c1 = getelementptr inbounds <16 x i8>, <16 x i8>* %c0, i64 1
+ store <16 x i8> %h1, <16 x i8>* %c1
+ %c2 = getelementptr inbounds <16 x i8>, <16 x i8>* %c0, i64 2
+ store <16 x i8> %h2, <16 x i8>* %c2
+ %c3 = getelementptr inbounds <16 x i8>, <16 x i8>* %c0, i64 3
+ store <16 x i8> %h3, <16 x i8>* %c3
+ ret void
+
+; CHECK-LABEL: aesea:
+; CHECK: aese.8 [[QA:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesmc.8 {{q[0-9][0-9]?}}, [[QA]]
+; CHECK: aese.8 [[QB:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesmc.8 {{q[0-9][0-9]?}}, [[QB]]
+; CHECK: aese.8 [[QC:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesmc.8 {{q[0-9][0-9]?}}, [[QC]]
+; CHECK: aese.8 [[QD:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesmc.8 {{q[0-9][0-9]?}}, [[QD]]
+; CHECK: aese.8 [[QE:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesmc.8 {{q[0-9][0-9]?}}, [[QE]]
+; CHECK: aese.8 [[QF:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesmc.8 {{q[0-9][0-9]?}}, [[QF]]
+; CHECK: aese.8 {{q[0-9][0-9]?}}, {{q[0-9][0-9]?}}
+; CHECK: aese.8 [[QG:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesmc.8 {{q[0-9][0-9]?}}, [[QG]]
+; CHECK: aese.8 {{q[0-9][0-9]?}}, {{q[0-9][0-9]?}}
+; CHECK: aese.8 [[QH:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesmc.8 {{q[0-9][0-9]?}}, [[QH]]
+}
+
+define void @aesda(<16 x i8>* %a0, <16 x i8>* %b0, <16 x i8>* %c0, <16 x i8> %d, <16 x i8> %e) {
+ %d0 = load <16 x i8>, <16 x i8>* %a0
+ %a1 = getelementptr inbounds <16 x i8>, <16 x i8>* %a0, i64 1
+ %d1 = load <16 x i8>, <16 x i8>* %a1
+ %a2 = getelementptr inbounds <16 x i8>, <16 x i8>* %a0, i64 2
+ %d2 = load <16 x i8>, <16 x i8>* %a2
+ %a3 = getelementptr inbounds <16 x i8>, <16 x i8>* %a0, i64 3
+ %d3 = load <16 x i8>, <16 x i8>* %a3
+ %k0 = load <16 x i8>, <16 x i8>* %b0
+ %e00 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %d0, <16 x i8> %k0)
+ %f00 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e00)
+ %e01 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %d1, <16 x i8> %k0)
+ %f01 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e01)
+ %e02 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %d2, <16 x i8> %k0)
+ %f02 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e02)
+ %e03 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %d3, <16 x i8> %k0)
+ %f03 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e03)
+ %b1 = getelementptr inbounds <16 x i8>, <16 x i8>* %b0, i64 1
+ %k1 = load <16 x i8>, <16 x i8>* %b1
+ %e10 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f00, <16 x i8> %k1)
+ %f10 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e00)
+ %e11 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f01, <16 x i8> %k1)
+ %f11 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e01)
+ %e12 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f02, <16 x i8> %k1)
+ %f12 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e02)
+ %e13 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f03, <16 x i8> %k1)
+ %f13 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e03)
+ %b2 = getelementptr inbounds <16 x i8>, <16 x i8>* %b0, i64 2
+ %k2 = load <16 x i8>, <16 x i8>* %b2
+ %e20 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f10, <16 x i8> %k2)
+ %f20 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e10)
+ %e21 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f11, <16 x i8> %k2)
+ %f21 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e11)
+ %e22 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f12, <16 x i8> %k2)
+ %f22 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e12)
+ %e23 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f13, <16 x i8> %k2)
+ %f23 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e13)
+ %b3 = getelementptr inbounds <16 x i8>, <16 x i8>* %b0, i64 3
+ %k3 = load <16 x i8>, <16 x i8>* %b3
+ %e30 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f20, <16 x i8> %k3)
+ %f30 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e20)
+ %e31 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f21, <16 x i8> %k3)
+ %f31 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e21)
+ %e32 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f22, <16 x i8> %k3)
+ %f32 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e22)
+ %e33 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f23, <16 x i8> %k3)
+ %f33 = call <16 x i8> @llvm.arm.neon.aesimc(<16 x i8> %e23)
+ %g0 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f30, <16 x i8> %d)
+ %h0 = xor <16 x i8> %g0, %e
+ %g1 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f31, <16 x i8> %d)
+ %h1 = xor <16 x i8> %g1, %e
+ %g2 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f32, <16 x i8> %d)
+ %h2 = xor <16 x i8> %g2, %e
+ %g3 = call <16 x i8> @llvm.arm.neon.aesd(<16 x i8> %f33, <16 x i8> %d)
+ %h3 = xor <16 x i8> %g3, %e
+ store <16 x i8> %h0, <16 x i8>* %c0
+ %c1 = getelementptr inbounds <16 x i8>, <16 x i8>* %c0, i64 1
+ store <16 x i8> %h1, <16 x i8>* %c1
+ %c2 = getelementptr inbounds <16 x i8>, <16 x i8>* %c0, i64 2
+ store <16 x i8> %h2, <16 x i8>* %c2
+ %c3 = getelementptr inbounds <16 x i8>, <16 x i8>* %c0, i64 3
+ store <16 x i8> %h3, <16 x i8>* %c3
+ ret void
+
+; CHECK-LABEL: aesda:
+; CHECK: aesd.8 [[QA:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesimc.8 {{q[0-9][0-9]?}}, [[QA]]
+; CHECK: aesd.8 [[QB:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesimc.8 {{q[0-9][0-9]?}}, [[QB]]
+; CHECK: aesd.8 [[QC:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesimc.8 {{q[0-9][0-9]?}}, [[QC]]
+; CHECK: aesd.8 [[QD:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesimc.8 {{q[0-9][0-9]?}}, [[QD]]
+; CHECK: aesd.8 [[QE:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesimc.8 {{q[0-9][0-9]?}}, [[QE]]
+; CHECK: aesd.8 [[QF:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesimc.8 {{q[0-9][0-9]?}}, [[QF]]
+; CHECK: aesd.8 {{q[0-9][0-9]?}}, {{q[0-9][0-9]?}}
+; CHECK: aesd.8 [[QG:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesimc.8 {{q[0-9][0-9]?}}, [[QG]]
+; CHECK: aesd.8 {{q[0-9][0-9]?}}, {{q[0-9][0-9]?}}
+; CHECK: aesd.8 [[QH:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesimc.8 {{q[0-9][0-9]?}}, [[QH]]
+}
+
+define void @aes_load_store(<16 x i8> *%p1, <16 x i8> *%p2 , <16 x i8> *%p3) {
+entry:
+ %x1 = alloca <16 x i8>, align 16
+ %x2 = alloca <16 x i8>, align 16
+ %x3 = alloca <16 x i8>, align 16
+ %x4 = alloca <16 x i8>, align 16
+ %x5 = alloca <16 x i8>, align 16
+ %in1 = load <16 x i8>, <16 x i8>* %p1, align 16
+ store <16 x i8> %in1, <16 x i8>* %x1, align 16
+ %aese1 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %in1, <16 x i8> %in1) #2
+ store <16 x i8> %aese1, <16 x i8>* %x2, align 16
+ %in2 = load <16 x i8>, <16 x i8>* %p2, align 16
+ %aesmc1= call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %aese1) #2
+ store <16 x i8> %aesmc1, <16 x i8>* %x3, align 16
+ %aese2 = call <16 x i8> @llvm.arm.neon.aese(<16 x i8> %in1, <16 x i8> %in2) #2
+ store <16 x i8> %aese2, <16 x i8>* %x4, align 16
+ %aesmc2= call <16 x i8> @llvm.arm.neon.aesmc(<16 x i8> %aese2) #2
+ store <16 x i8> %aesmc2, <16 x i8>* %x5, align 16
+ ret void
+
+; CHECK-LABEL: aes_load_store:
+; CHECK: aese.8 [[QA:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesmc.8 {{q[0-9][0-9]?}}, [[QA]]
+; CHECK: aese.8 [[QB:q[0-9][0-9]?]], {{q[0-9][0-9]?}}
+; CHECK-NEXT: aesmc.8 {{q[0-9][0-9]?}}, [[QB]]
+}
diff --git a/test/CodeGen/ARM/v6m-umul-with-overflow.ll b/test/CodeGen/ARM/v6m-umul-with-overflow.ll
new file mode 100644
index 0000000000000..4e3146d711024
--- /dev/null
+++ b/test/CodeGen/ARM/v6m-umul-with-overflow.ll
@@ -0,0 +1,16 @@
+; RUN: llc < %s -mtriple=thumbv6m-none-eabi | FileCheck %s
+
+define i1 @unsigned_multiplication_did_overflow(i32, i32) {
+; CHECK-LABEL: unsigned_multiplication_did_overflow:
+entry-block:
+ %2 = tail call { i32, i1 } @llvm.umul.with.overflow.i32(i32 %0, i32 %1)
+ %3 = extractvalue { i32, i1 } %2, 1
+ ret i1 %3
+
+; CHECK: mov{{s?}} r2, r1
+; CHECK: mov{{s?}} r1, #0
+; CHECK: mov{{s?}} r3, {{#0|r1}}
+; CHECK: bl __aeabi_lmul
+}
+
+declare { i32, i1 } @llvm.umul.with.overflow.i32(i32, i32)
diff --git a/test/CodeGen/ARM/vector-promotion.ll b/test/CodeGen/ARM/vector-promotion.ll
index 1dabee386089d..9e2b35fe82584 100644
--- a/test/CodeGen/ARM/vector-promotion.ll
+++ b/test/CodeGen/ARM/vector-promotion.ll
@@ -53,8 +53,8 @@ define void @unsupportedInstructionForPromotion(<2 x i32>* %addr1, i32 %in2, i1*
; IR-BOTH: ret
;
; ASM-LABEL: unsupportedChainInDifferentBBs:
-; ASM: vldrne [[LOAD:d[0-9]+]], [r0]
-; ASM: vmovne.32 {{r[0-9]+}}, [[LOAD]]
+; ASM: vldr [[LOAD:d[0-9]+]], [r0]
+; ASM: vmov.32 {{r[0-9]+}}, [[LOAD]]
; ASM: bx
define void @unsupportedChainInDifferentBBs(<2 x i32>* %addr1, i32* %dest, i1 %bool) {
bb1:
diff --git a/test/CodeGen/ARM/xray-armv6-attribute-instrumentation.ll b/test/CodeGen/ARM/xray-armv6-attribute-instrumentation.ll
index 5e3c45c3454d8..5017de835b5da 100644
--- a/test/CodeGen/ARM/xray-armv6-attribute-instrumentation.ll
+++ b/test/CodeGen/ARM/xray-armv6-attribute-instrumentation.ll
@@ -24,14 +24,13 @@ define i32 @foo() nounwind noinline uwtable "function-instrument"="xray-always"
; CHECK-NEXT: bx lr
}
; CHECK: .p2align 4
-; CHECK-NEXT: .long {{.*}}Lxray_synthetic_0
; CHECK-NEXT: .long {{.*}}Lxray_fn_idx_synth_0
; CHECK-NEXT: .section {{.*}}xray_instr_map{{.*}}
-; CHECK-LABEL: Lxray_synthetic_0:
+; CHECK-LABEL: Lxray_sleds_start0:
; CHECK: .long {{.*}}Lxray_sled_0
; CHECK: .long {{.*}}Lxray_sled_1
-; CHECK-LABEL: Lxray_synthetic_end0:
+; CHECK-LABEL: Lxray_sleds_end0:
; CHECK: .section {{.*}}xray_fn_idx{{.*}}
; CHECK-LABEL: Lxray_fn_idx_synth_0:
-; CHECK: .long {{.*}}Lxray_synthetic_0
-; CHECK-NEXT: .long {{.*}}Lxray_synthetic_end0
+; CHECK: .long {{.*}}Lxray_sleds_start0
+; CHECK-NEXT: .long {{.*}}Lxray_sleds_end0
diff --git a/test/CodeGen/ARM/xray-armv7-attribute-instrumentation.ll b/test/CodeGen/ARM/xray-armv7-attribute-instrumentation.ll
index 739151fbdd5e5..118c02adeb8aa 100644
--- a/test/CodeGen/ARM/xray-armv7-attribute-instrumentation.ll
+++ b/test/CodeGen/ARM/xray-armv7-attribute-instrumentation.ll
@@ -24,15 +24,14 @@ define i32 @foo() nounwind noinline uwtable "function-instrument"="xray-always"
; CHECK-NEXT: bx lr
}
; CHECK: .p2align 4
-; CHECK-NEXT: .long {{.*}}Lxray_synthetic_0
; CHECK-NEXT: .long {{.*}}Lxray_fn_idx_synth_0
; CHECK-NEXT: .section {{.*}}xray_instr_map{{.*}}
-; CHECK-LABEL: Lxray_synthetic_0:
+; CHECK-LABEL: Lxray_sleds_start0:
; CHECK: .long {{.*}}Lxray_sled_0
; CHECK: .long {{.*}}Lxray_sled_1
-; CHECK-LABEL: Lxray_synthetic_end0:
+; CHECK-LABEL: Lxray_sleds_end0:
; CHECK: .section {{.*}}xray_fn_idx{{.*}}
; CHECK-LABEL: Lxray_fn_idx_synth_0:
-; CHECK: .long {{.*}}xray_synthetic_0
-; CHECK-NEXT: .long {{.*}}xray_synthetic_end0
+; CHECK: .long {{.*}}xray_sleds_start0
+; CHECK-NEXT: .long {{.*}}xray_sleds_end0
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-02 02:21:42 +0000