aboutsummaryrefslogtreecommitdiff
path: root/llvm/test/CodeGen/AArch64
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/CodeGen/AArch64')
-rw-r--r--llvm/test/CodeGen/AArch64/GlobalISel/combine-freeze.mir47
-rw-r--r--llvm/test/CodeGen/AArch64/arm64-srl-and.ll42
-rw-r--r--llvm/test/CodeGen/AArch64/eor3.ll151
-rw-r--r--llvm/test/CodeGen/AArch64/hoist-and-by-const-from-lshr-in-eqcmp-zero.ll414
-rw-r--r--llvm/test/CodeGen/AArch64/hoist-and-by-const-from-shl-in-eqcmp-zero.ll424
-rw-r--r--llvm/test/CodeGen/AArch64/llvm.sincos.ll195
-rw-r--r--llvm/test/CodeGen/AArch64/signbit-test.ll22
-rw-r--r--llvm/test/CodeGen/AArch64/signed-truncation-check.ll434
-rw-r--r--llvm/test/CodeGen/AArch64/stackmap.ll4
9 files changed, 1337 insertions, 396 deletions
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/combine-freeze.mir b/llvm/test/CodeGen/AArch64/GlobalISel/combine-freeze.mir
index 6b84a84..1950e60 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/combine-freeze.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/combine-freeze.mir
@@ -1440,3 +1440,50 @@ body: |
%freeze:_(<4 x s32>) = G_FREEZE %extract
$q0 = COPY %freeze(<4 x s32>)
RET_ReallyLR implicit $x0
+...
+---
+name: ubfx_does_not_generate_poison
+body: |
+ bb.1:
+ liveins: $w0
+
+ ; CHECK-LABEL: name: ubfx_does_not_generate_poison
+ ; CHECK: liveins: $w0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x0
+ ; CHECK-NEXT: %c1:_(s64) = G_CONSTANT i64 1
+ ; CHECK-NEXT: [[FREEZE:%[0-9]+]]:_(s64) = G_FREEZE [[COPY]]
+ ; CHECK-NEXT: [[UBFX:%[0-9]+]]:_(s64) = G_UBFX [[FREEZE]], %c1(s64), %c1
+ ; CHECK-NEXT: $x0 = COPY [[UBFX]](s64)
+ ; CHECK-NEXT: RET_ReallyLR implicit $x0
+ %0:_(s64) = COPY $x0
+ %c1:_(s64) = G_CONSTANT i64 1
+ %1:_(s64) = G_UBFX %0, %c1, %c1
+ %2:_(s64) = G_FREEZE %1
+ $x0 = COPY %2(s64)
+ RET_ReallyLR implicit $x0
+
+...
+---
+name: sbfx_does_not_generate_poison
+body: |
+ bb.1:
+ liveins: $w0
+
+ ; CHECK-LABEL: name: sbfx_does_not_generate_poison
+ ; CHECK: liveins: $w0
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $x0
+ ; CHECK-NEXT: %c1:_(s64) = G_CONSTANT i64 1
+ ; CHECK-NEXT: [[FREEZE:%[0-9]+]]:_(s64) = G_FREEZE [[COPY]]
+ ; CHECK-NEXT: [[SBFX:%[0-9]+]]:_(s64) = G_SBFX [[FREEZE]], %c1(s64), %c1
+ ; CHECK-NEXT: $x0 = COPY [[SBFX]](s64)
+ ; CHECK-NEXT: RET_ReallyLR implicit $x0
+ %0:_(s64) = COPY $x0
+ %c1:_(s64) = G_CONSTANT i64 1
+ %1:_(s64) = G_SBFX %0, %c1, %c1
+ %2:_(s64) = G_FREEZE %1
+ $x0 = COPY %2(s64)
+ RET_ReallyLR implicit $x0
+
+...
diff --git a/llvm/test/CodeGen/AArch64/arm64-srl-and.ll b/llvm/test/CodeGen/AArch64/arm64-srl-and.ll
index b58f6ba..330f27b 100644
--- a/llvm/test/CodeGen/AArch64/arm64-srl-and.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-srl-and.ll
@@ -1,22 +1,38 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=aarch64-linux-gnu -O3 < %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnu -O3 < %s | FileCheck %s --check-prefixes=CHECK,CHECK-SD
+; RUN: llc -mtriple=aarch64-linux-gnu -O3 -global-isel < %s | FileCheck %s --check-prefixes=CHECK,CHECK-GI
; This used to miscompile:
; The 16-bit -1 should not become 32-bit -1 (sub w8, w8, #1).
@g = global i16 0, align 4
define i32 @srl_and() {
-; CHECK-LABEL: srl_and:
-; CHECK: // %bb.0: // %entry
-; CHECK-NEXT: adrp x8, :got:g
-; CHECK-NEXT: mov w9, #50
-; CHECK-NEXT: ldr x8, [x8, :got_lo12:g]
-; CHECK-NEXT: ldrh w8, [x8]
-; CHECK-NEXT: eor w8, w8, w9
-; CHECK-NEXT: mov w9, #65535
-; CHECK-NEXT: add w8, w8, w9
-; CHECK-NEXT: and w0, w8, w8, lsr #16
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: srl_and:
+; CHECK-SD: // %bb.0: // %entry
+; CHECK-SD-NEXT: adrp x8, :got:g
+; CHECK-SD-NEXT: mov w9, #50 // =0x32
+; CHECK-SD-NEXT: ldr x8, [x8, :got_lo12:g]
+; CHECK-SD-NEXT: ldrh w8, [x8]
+; CHECK-SD-NEXT: eor w8, w8, w9
+; CHECK-SD-NEXT: mov w9, #65535 // =0xffff
+; CHECK-SD-NEXT: add w8, w8, w9
+; CHECK-SD-NEXT: and w0, w8, w8, lsr #16
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: srl_and:
+; CHECK-GI: // %bb.0: // %entry
+; CHECK-GI-NEXT: adrp x8, :got:g
+; CHECK-GI-NEXT: mov w9, #50 // =0x32
+; CHECK-GI-NEXT: ldr x8, [x8, :got_lo12:g]
+; CHECK-GI-NEXT: ldrh w8, [x8]
+; CHECK-GI-NEXT: eor w8, w8, w9
+; CHECK-GI-NEXT: mov w9, #65535 // =0xffff
+; CHECK-GI-NEXT: add w8, w9, w8, uxth
+; CHECK-GI-NEXT: and w9, w8, #0xffff
+; CHECK-GI-NEXT: cmp w8, w9
+; CHECK-GI-NEXT: cset w8, ne
+; CHECK-GI-NEXT: and w0, w9, w8
+; CHECK-GI-NEXT: ret
entry:
%0 = load i16, ptr @g, align 4
%1 = xor i16 %0, 50
@@ -29,3 +45,5 @@ entry:
ret i32 %and
}
+;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+; CHECK: {{.*}}
diff --git a/llvm/test/CodeGen/AArch64/eor3.ll b/llvm/test/CodeGen/AArch64/eor3.ll
index eccd091..594a73f 100644
--- a/llvm/test/CodeGen/AArch64/eor3.ll
+++ b/llvm/test/CodeGen/AArch64/eor3.ll
@@ -277,3 +277,154 @@ define <2 x i64> @eor3_vnot(<2 x i64> %0, <2 x i64> %1) {
ret <2 x i64> %4
}
+define <1 x i64> @eor3_1x64(<1 x i64> %0, <1 x i64> %1, <1 x i64> %2) {
+; SHA3-LABEL: eor3_1x64:
+; SHA3: // %bb.0:
+; SHA3-NEXT: // kill: def $d0 killed $d0 def $q0
+; SHA3-NEXT: // kill: def $d2 killed $d2 def $q2
+; SHA3-NEXT: // kill: def $d1 killed $d1 def $q1
+; SHA3-NEXT: eor3 v0.16b, v1.16b, v2.16b, v0.16b
+; SHA3-NEXT: // kill: def $d0 killed $d0 killed $q0
+; SHA3-NEXT: ret
+;
+; NOSHA3-LABEL: eor3_1x64:
+; NOSHA3: // %bb.0:
+; NOSHA3-NEXT: eor v1.8b, v1.8b, v2.8b
+; NOSHA3-NEXT: eor v0.8b, v1.8b, v0.8b
+; NOSHA3-NEXT: ret
+;
+; SVE2-LABEL: eor3_1x64:
+; SVE2: // %bb.0:
+; SVE2-NEXT: // kill: def $d1 killed $d1 def $z1
+; SVE2-NEXT: // kill: def $d2 killed $d2 def $z2
+; SVE2-NEXT: // kill: def $d0 killed $d0 def $z0
+; SVE2-NEXT: eor3 z1.d, z1.d, z2.d, z0.d
+; SVE2-NEXT: fmov d0, d1
+; SVE2-NEXT: ret
+;
+; SHA3-SVE2-LABEL: eor3_1x64:
+; SHA3-SVE2: // %bb.0:
+; SHA3-SVE2-NEXT: // kill: def $d0 killed $d0 def $q0
+; SHA3-SVE2-NEXT: // kill: def $d2 killed $d2 def $q2
+; SHA3-SVE2-NEXT: // kill: def $d1 killed $d1 def $q1
+; SHA3-SVE2-NEXT: eor3 v0.16b, v1.16b, v2.16b, v0.16b
+; SHA3-SVE2-NEXT: // kill: def $d0 killed $d0 killed $q0
+; SHA3-SVE2-NEXT: ret
+ %4 = xor <1 x i64> %1, %2
+ %5 = xor <1 x i64> %4, %0
+ ret <1 x i64> %5
+}
+
+define <2 x i32> @eor3_2x32(<2 x i32> %0, <2 x i32> %1, <2 x i32> %2) {
+; SHA3-LABEL: eor3_2x32:
+; SHA3: // %bb.0:
+; SHA3-NEXT: // kill: def $d0 killed $d0 def $q0
+; SHA3-NEXT: // kill: def $d2 killed $d2 def $q2
+; SHA3-NEXT: // kill: def $d1 killed $d1 def $q1
+; SHA3-NEXT: eor3 v0.16b, v1.16b, v2.16b, v0.16b
+; SHA3-NEXT: // kill: def $d0 killed $d0 killed $q0
+; SHA3-NEXT: ret
+;
+; NOSHA3-LABEL: eor3_2x32:
+; NOSHA3: // %bb.0:
+; NOSHA3-NEXT: eor v1.8b, v1.8b, v2.8b
+; NOSHA3-NEXT: eor v0.8b, v1.8b, v0.8b
+; NOSHA3-NEXT: ret
+;
+; SVE2-LABEL: eor3_2x32:
+; SVE2: // %bb.0:
+; SVE2-NEXT: // kill: def $d1 killed $d1 def $z1
+; SVE2-NEXT: // kill: def $d2 killed $d2 def $z2
+; SVE2-NEXT: // kill: def $d0 killed $d0 def $z0
+; SVE2-NEXT: eor3 z1.d, z1.d, z2.d, z0.d
+; SVE2-NEXT: fmov d0, d1
+; SVE2-NEXT: ret
+;
+; SHA3-SVE2-LABEL: eor3_2x32:
+; SHA3-SVE2: // %bb.0:
+; SHA3-SVE2-NEXT: // kill: def $d0 killed $d0 def $q0
+; SHA3-SVE2-NEXT: // kill: def $d2 killed $d2 def $q2
+; SHA3-SVE2-NEXT: // kill: def $d1 killed $d1 def $q1
+; SHA3-SVE2-NEXT: eor3 v0.16b, v1.16b, v2.16b, v0.16b
+; SHA3-SVE2-NEXT: // kill: def $d0 killed $d0 killed $q0
+; SHA3-SVE2-NEXT: ret
+ %4 = xor <2 x i32> %1, %2
+ %5 = xor <2 x i32> %4, %0
+ ret <2 x i32> %5
+}
+
+define <4 x i16> @eor3_4x16(<4 x i16> %0, <4 x i16> %1, <4 x i16> %2) {
+; SHA3-LABEL: eor3_4x16:
+; SHA3: // %bb.0:
+; SHA3-NEXT: // kill: def $d0 killed $d0 def $q0
+; SHA3-NEXT: // kill: def $d2 killed $d2 def $q2
+; SHA3-NEXT: // kill: def $d1 killed $d1 def $q1
+; SHA3-NEXT: eor3 v0.16b, v1.16b, v2.16b, v0.16b
+; SHA3-NEXT: // kill: def $d0 killed $d0 killed $q0
+; SHA3-NEXT: ret
+;
+; NOSHA3-LABEL: eor3_4x16:
+; NOSHA3: // %bb.0:
+; NOSHA3-NEXT: eor v1.8b, v1.8b, v2.8b
+; NOSHA3-NEXT: eor v0.8b, v1.8b, v0.8b
+; NOSHA3-NEXT: ret
+;
+; SVE2-LABEL: eor3_4x16:
+; SVE2: // %bb.0:
+; SVE2-NEXT: // kill: def $d1 killed $d1 def $z1
+; SVE2-NEXT: // kill: def $d2 killed $d2 def $z2
+; SVE2-NEXT: // kill: def $d0 killed $d0 def $z0
+; SVE2-NEXT: eor3 z1.d, z1.d, z2.d, z0.d
+; SVE2-NEXT: fmov d0, d1
+; SVE2-NEXT: ret
+;
+; SHA3-SVE2-LABEL: eor3_4x16:
+; SHA3-SVE2: // %bb.0:
+; SHA3-SVE2-NEXT: // kill: def $d0 killed $d0 def $q0
+; SHA3-SVE2-NEXT: // kill: def $d2 killed $d2 def $q2
+; SHA3-SVE2-NEXT: // kill: def $d1 killed $d1 def $q1
+; SHA3-SVE2-NEXT: eor3 v0.16b, v1.16b, v2.16b, v0.16b
+; SHA3-SVE2-NEXT: // kill: def $d0 killed $d0 killed $q0
+; SHA3-SVE2-NEXT: ret
+ %4 = xor <4 x i16> %1, %2
+ %5 = xor <4 x i16> %4, %0
+ ret <4 x i16> %5
+}
+
+define <8 x i8> @eor3_8x8(<8 x i8> %0, <8 x i8> %1, <8 x i8> %2) {
+; SHA3-LABEL: eor3_8x8:
+; SHA3: // %bb.0:
+; SHA3-NEXT: // kill: def $d0 killed $d0 def $q0
+; SHA3-NEXT: // kill: def $d2 killed $d2 def $q2
+; SHA3-NEXT: // kill: def $d1 killed $d1 def $q1
+; SHA3-NEXT: eor3 v0.16b, v1.16b, v2.16b, v0.16b
+; SHA3-NEXT: // kill: def $d0 killed $d0 killed $q0
+; SHA3-NEXT: ret
+;
+; NOSHA3-LABEL: eor3_8x8:
+; NOSHA3: // %bb.0:
+; NOSHA3-NEXT: eor v1.8b, v1.8b, v2.8b
+; NOSHA3-NEXT: eor v0.8b, v1.8b, v0.8b
+; NOSHA3-NEXT: ret
+;
+; SVE2-LABEL: eor3_8x8:
+; SVE2: // %bb.0:
+; SVE2-NEXT: // kill: def $d1 killed $d1 def $z1
+; SVE2-NEXT: // kill: def $d2 killed $d2 def $z2
+; SVE2-NEXT: // kill: def $d0 killed $d0 def $z0
+; SVE2-NEXT: eor3 z1.d, z1.d, z2.d, z0.d
+; SVE2-NEXT: fmov d0, d1
+; SVE2-NEXT: ret
+;
+; SHA3-SVE2-LABEL: eor3_8x8:
+; SHA3-SVE2: // %bb.0:
+; SHA3-SVE2-NEXT: // kill: def $d0 killed $d0 def $q0
+; SHA3-SVE2-NEXT: // kill: def $d2 killed $d2 def $q2
+; SHA3-SVE2-NEXT: // kill: def $d1 killed $d1 def $q1
+; SHA3-SVE2-NEXT: eor3 v0.16b, v1.16b, v2.16b, v0.16b
+; SHA3-SVE2-NEXT: // kill: def $d0 killed $d0 killed $q0
+; SHA3-SVE2-NEXT: ret
+ %4 = xor <8 x i8> %1, %2
+ %5 = xor <8 x i8> %4, %0
+ ret <8 x i8> %5
+}
diff --git a/llvm/test/CodeGen/AArch64/hoist-and-by-const-from-lshr-in-eqcmp-zero.ll b/llvm/test/CodeGen/AArch64/hoist-and-by-const-from-lshr-in-eqcmp-zero.ll
index c3fdc7d..8438f0b0 100644
--- a/llvm/test/CodeGen/AArch64/hoist-and-by-const-from-lshr-in-eqcmp-zero.ll
+++ b/llvm/test/CodeGen/AArch64/hoist-and-by-const-from-lshr-in-eqcmp-zero.ll
@@ -1,5 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=aarch64-unknown-unknown < %s | FileCheck %s --check-prefix=CHECK
+; RUN: llc -mtriple=aarch64-unknown-unknown < %s | FileCheck %s --check-prefixes=CHECK,CHECK-SD
+; RUN: llc -mtriple=aarch64-unknown-unknown -global-isel < %s | FileCheck %s --check-prefixes=CHECK,CHECK-GI
; We are looking for the following pattern here:
; (X & (C l>> Y)) ==/!= 0
@@ -13,12 +14,21 @@
; i8 scalar
define i1 @scalar_i8_signbit_eq(i8 %x, i8 %y) nounwind {
-; CHECK-LABEL: scalar_i8_signbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsl w8, w0, w1
-; CHECK-NEXT: tst w8, #0x80
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i8_signbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsl w8, w0, w1
+; CHECK-SD-NEXT: tst w8, #0x80
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i8_signbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #128 // =0x80
+; CHECK-GI-NEXT: and w9, w1, #0xff
+; CHECK-GI-NEXT: lsr w8, w8, w9
+; CHECK-GI-NEXT: tst w8, w0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = lshr i8 128, %y
%t1 = and i8 %t0, %x
%res = icmp eq i8 %t1, 0
@@ -26,12 +36,21 @@ define i1 @scalar_i8_signbit_eq(i8 %x, i8 %y) nounwind {
}
define i1 @scalar_i8_lowestbit_eq(i8 %x, i8 %y) nounwind {
-; CHECK-LABEL: scalar_i8_lowestbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsl w8, w0, w1
-; CHECK-NEXT: tst w8, #0x1
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i8_lowestbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsl w8, w0, w1
+; CHECK-SD-NEXT: tst w8, #0x1
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i8_lowestbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #1 // =0x1
+; CHECK-GI-NEXT: and w9, w1, #0xff
+; CHECK-GI-NEXT: lsr w8, w8, w9
+; CHECK-GI-NEXT: tst w8, w0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = lshr i8 1, %y
%t1 = and i8 %t0, %x
%res = icmp eq i8 %t1, 0
@@ -39,12 +58,21 @@ define i1 @scalar_i8_lowestbit_eq(i8 %x, i8 %y) nounwind {
}
define i1 @scalar_i8_bitsinmiddle_eq(i8 %x, i8 %y) nounwind {
-; CHECK-LABEL: scalar_i8_bitsinmiddle_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsl w8, w0, w1
-; CHECK-NEXT: tst w8, #0x18
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i8_bitsinmiddle_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsl w8, w0, w1
+; CHECK-SD-NEXT: tst w8, #0x18
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i8_bitsinmiddle_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #24 // =0x18
+; CHECK-GI-NEXT: and w9, w1, #0xff
+; CHECK-GI-NEXT: lsr w8, w8, w9
+; CHECK-GI-NEXT: tst w8, w0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = lshr i8 24, %y
%t1 = and i8 %t0, %x
%res = icmp eq i8 %t1, 0
@@ -54,12 +82,21 @@ define i1 @scalar_i8_bitsinmiddle_eq(i8 %x, i8 %y) nounwind {
; i16 scalar
define i1 @scalar_i16_signbit_eq(i16 %x, i16 %y) nounwind {
-; CHECK-LABEL: scalar_i16_signbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsl w8, w0, w1
-; CHECK-NEXT: tst w8, #0x8000
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i16_signbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsl w8, w0, w1
+; CHECK-SD-NEXT: tst w8, #0x8000
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i16_signbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #32768 // =0x8000
+; CHECK-GI-NEXT: and w9, w1, #0xffff
+; CHECK-GI-NEXT: lsr w8, w8, w9
+; CHECK-GI-NEXT: tst w8, w0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = lshr i16 32768, %y
%t1 = and i16 %t0, %x
%res = icmp eq i16 %t1, 0
@@ -67,12 +104,21 @@ define i1 @scalar_i16_signbit_eq(i16 %x, i16 %y) nounwind {
}
define i1 @scalar_i16_lowestbit_eq(i16 %x, i16 %y) nounwind {
-; CHECK-LABEL: scalar_i16_lowestbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsl w8, w0, w1
-; CHECK-NEXT: tst w8, #0x1
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i16_lowestbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsl w8, w0, w1
+; CHECK-SD-NEXT: tst w8, #0x1
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i16_lowestbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #1 // =0x1
+; CHECK-GI-NEXT: and w9, w1, #0xffff
+; CHECK-GI-NEXT: lsr w8, w8, w9
+; CHECK-GI-NEXT: tst w8, w0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = lshr i16 1, %y
%t1 = and i16 %t0, %x
%res = icmp eq i16 %t1, 0
@@ -80,12 +126,21 @@ define i1 @scalar_i16_lowestbit_eq(i16 %x, i16 %y) nounwind {
}
define i1 @scalar_i16_bitsinmiddle_eq(i16 %x, i16 %y) nounwind {
-; CHECK-LABEL: scalar_i16_bitsinmiddle_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsl w8, w0, w1
-; CHECK-NEXT: tst w8, #0xff0
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i16_bitsinmiddle_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsl w8, w0, w1
+; CHECK-SD-NEXT: tst w8, #0xff0
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i16_bitsinmiddle_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #4080 // =0xff0
+; CHECK-GI-NEXT: and w9, w1, #0xffff
+; CHECK-GI-NEXT: lsr w8, w8, w9
+; CHECK-GI-NEXT: tst w8, w0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = lshr i16 4080, %y
%t1 = and i16 %t0, %x
%res = icmp eq i16 %t1, 0
@@ -95,12 +150,20 @@ define i1 @scalar_i16_bitsinmiddle_eq(i16 %x, i16 %y) nounwind {
; i32 scalar
define i1 @scalar_i32_signbit_eq(i32 %x, i32 %y) nounwind {
-; CHECK-LABEL: scalar_i32_signbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsl w8, w0, w1
-; CHECK-NEXT: tst w8, #0x80000000
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i32_signbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsl w8, w0, w1
+; CHECK-SD-NEXT: tst w8, #0x80000000
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i32_signbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #-2147483648 // =0x80000000
+; CHECK-GI-NEXT: lsr w8, w8, w1
+; CHECK-GI-NEXT: tst w8, w0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = lshr i32 2147483648, %y
%t1 = and i32 %t0, %x
%res = icmp eq i32 %t1, 0
@@ -108,12 +171,20 @@ define i1 @scalar_i32_signbit_eq(i32 %x, i32 %y) nounwind {
}
define i1 @scalar_i32_lowestbit_eq(i32 %x, i32 %y) nounwind {
-; CHECK-LABEL: scalar_i32_lowestbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsl w8, w0, w1
-; CHECK-NEXT: tst w8, #0x1
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i32_lowestbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsl w8, w0, w1
+; CHECK-SD-NEXT: tst w8, #0x1
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i32_lowestbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #1 // =0x1
+; CHECK-GI-NEXT: lsr w8, w8, w1
+; CHECK-GI-NEXT: tst w8, w0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = lshr i32 1, %y
%t1 = and i32 %t0, %x
%res = icmp eq i32 %t1, 0
@@ -121,12 +192,20 @@ define i1 @scalar_i32_lowestbit_eq(i32 %x, i32 %y) nounwind {
}
define i1 @scalar_i32_bitsinmiddle_eq(i32 %x, i32 %y) nounwind {
-; CHECK-LABEL: scalar_i32_bitsinmiddle_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsl w8, w0, w1
-; CHECK-NEXT: tst w8, #0xffff00
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i32_bitsinmiddle_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsl w8, w0, w1
+; CHECK-SD-NEXT: tst w8, #0xffff00
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i32_bitsinmiddle_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #16776960 // =0xffff00
+; CHECK-GI-NEXT: lsr w8, w8, w1
+; CHECK-GI-NEXT: tst w8, w0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = lshr i32 16776960, %y
%t1 = and i32 %t0, %x
%res = icmp eq i32 %t1, 0
@@ -136,12 +215,20 @@ define i1 @scalar_i32_bitsinmiddle_eq(i32 %x, i32 %y) nounwind {
; i64 scalar
define i1 @scalar_i64_signbit_eq(i64 %x, i64 %y) nounwind {
-; CHECK-LABEL: scalar_i64_signbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsl x8, x0, x1
-; CHECK-NEXT: tst x8, #0x8000000000000000
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i64_signbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsl x8, x0, x1
+; CHECK-SD-NEXT: tst x8, #0x8000000000000000
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i64_signbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov x8, #-9223372036854775808 // =0x8000000000000000
+; CHECK-GI-NEXT: lsr x8, x8, x1
+; CHECK-GI-NEXT: tst x8, x0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = lshr i64 9223372036854775808, %y
%t1 = and i64 %t0, %x
%res = icmp eq i64 %t1, 0
@@ -149,12 +236,20 @@ define i1 @scalar_i64_signbit_eq(i64 %x, i64 %y) nounwind {
}
define i1 @scalar_i64_lowestbit_eq(i64 %x, i64 %y) nounwind {
-; CHECK-LABEL: scalar_i64_lowestbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsl x8, x0, x1
-; CHECK-NEXT: tst x8, #0x1
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i64_lowestbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsl x8, x0, x1
+; CHECK-SD-NEXT: tst x8, #0x1
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i64_lowestbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #1 // =0x1
+; CHECK-GI-NEXT: lsr x8, x8, x1
+; CHECK-GI-NEXT: tst x8, x0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = lshr i64 1, %y
%t1 = and i64 %t0, %x
%res = icmp eq i64 %t1, 0
@@ -162,12 +257,20 @@ define i1 @scalar_i64_lowestbit_eq(i64 %x, i64 %y) nounwind {
}
define i1 @scalar_i64_bitsinmiddle_eq(i64 %x, i64 %y) nounwind {
-; CHECK-LABEL: scalar_i64_bitsinmiddle_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsl x8, x0, x1
-; CHECK-NEXT: tst x8, #0xffffffff0000
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i64_bitsinmiddle_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsl x8, x0, x1
+; CHECK-SD-NEXT: tst x8, #0xffffffff0000
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i64_bitsinmiddle_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov x8, #281474976645120 // =0xffffffff0000
+; CHECK-GI-NEXT: lsr x8, x8, x1
+; CHECK-GI-NEXT: tst x8, x0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = lshr i64 281474976645120, %y
%t1 = and i64 %t0, %x
%res = icmp eq i64 %t1, 0
@@ -179,14 +282,24 @@ define i1 @scalar_i64_bitsinmiddle_eq(i64 %x, i64 %y) nounwind {
;------------------------------------------------------------------------------;
define <4 x i1> @vec_4xi32_splat_eq(<4 x i32> %x, <4 x i32> %y) nounwind {
-; CHECK-LABEL: vec_4xi32_splat_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: movi v2.4s, #1
-; CHECK-NEXT: ushl v0.4s, v0.4s, v1.4s
-; CHECK-NEXT: and v0.16b, v0.16b, v2.16b
-; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
-; CHECK-NEXT: xtn v0.4h, v0.4s
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: vec_4xi32_splat_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: movi v2.4s, #1
+; CHECK-SD-NEXT: ushl v0.4s, v0.4s, v1.4s
+; CHECK-SD-NEXT: and v0.16b, v0.16b, v2.16b
+; CHECK-SD-NEXT: cmeq v0.4s, v0.4s, #0
+; CHECK-SD-NEXT: xtn v0.4h, v0.4s
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: vec_4xi32_splat_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: movi v2.4s, #1
+; CHECK-GI-NEXT: neg v1.4s, v1.4s
+; CHECK-GI-NEXT: ushl v1.4s, v2.4s, v1.4s
+; CHECK-GI-NEXT: and v0.16b, v1.16b, v0.16b
+; CHECK-GI-NEXT: cmeq v0.4s, v0.4s, #0
+; CHECK-GI-NEXT: xtn v0.4h, v0.4s
+; CHECK-GI-NEXT: ret
%t0 = lshr <4 x i32> <i32 1, i32 1, i32 1, i32 1>, %y
%t1 = and <4 x i32> %t0, %x
%res = icmp eq <4 x i32> %t1, <i32 0, i32 0, i32 0, i32 0>
@@ -211,44 +324,86 @@ define <4 x i1> @vec_4xi32_nonsplat_eq(<4 x i32> %x, <4 x i32> %y) nounwind {
}
define <4 x i1> @vec_4xi32_nonsplat_undef0_eq(<4 x i32> %x, <4 x i32> %y) nounwind {
-; CHECK-LABEL: vec_4xi32_nonsplat_undef0_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: movi v2.4s, #1
-; CHECK-NEXT: ushl v0.4s, v0.4s, v1.4s
-; CHECK-NEXT: and v0.16b, v0.16b, v2.16b
-; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
-; CHECK-NEXT: xtn v0.4h, v0.4s
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: vec_4xi32_nonsplat_undef0_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: movi v2.4s, #1
+; CHECK-SD-NEXT: ushl v0.4s, v0.4s, v1.4s
+; CHECK-SD-NEXT: and v0.16b, v0.16b, v2.16b
+; CHECK-SD-NEXT: cmeq v0.4s, v0.4s, #0
+; CHECK-SD-NEXT: xtn v0.4h, v0.4s
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: vec_4xi32_nonsplat_undef0_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #1 // =0x1
+; CHECK-GI-NEXT: neg v1.4s, v1.4s
+; CHECK-GI-NEXT: fmov s2, w8
+; CHECK-GI-NEXT: mov v2.s[1], w8
+; CHECK-GI-NEXT: mov v2.s[3], w8
+; CHECK-GI-NEXT: ushl v1.4s, v2.4s, v1.4s
+; CHECK-GI-NEXT: and v0.16b, v1.16b, v0.16b
+; CHECK-GI-NEXT: cmeq v0.4s, v0.4s, #0
+; CHECK-GI-NEXT: xtn v0.4h, v0.4s
+; CHECK-GI-NEXT: ret
%t0 = lshr <4 x i32> <i32 1, i32 1, i32 undef, i32 1>, %y
%t1 = and <4 x i32> %t0, %x
%res = icmp eq <4 x i32> %t1, <i32 0, i32 0, i32 0, i32 0>
ret <4 x i1> %res
}
define <4 x i1> @vec_4xi32_nonsplat_undef1_eq(<4 x i32> %x, <4 x i32> %y) nounwind {
-; CHECK-LABEL: vec_4xi32_nonsplat_undef1_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: movi v2.4s, #1
-; CHECK-NEXT: neg v1.4s, v1.4s
-; CHECK-NEXT: ushl v1.4s, v2.4s, v1.4s
-; CHECK-NEXT: and v0.16b, v1.16b, v0.16b
-; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
-; CHECK-NEXT: xtn v0.4h, v0.4s
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: vec_4xi32_nonsplat_undef1_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: movi v2.4s, #1
+; CHECK-SD-NEXT: neg v1.4s, v1.4s
+; CHECK-SD-NEXT: ushl v1.4s, v2.4s, v1.4s
+; CHECK-SD-NEXT: and v0.16b, v1.16b, v0.16b
+; CHECK-SD-NEXT: cmeq v0.4s, v0.4s, #0
+; CHECK-SD-NEXT: xtn v0.4h, v0.4s
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: vec_4xi32_nonsplat_undef1_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: movi d2, #0000000000000000
+; CHECK-GI-NEXT: movi v3.4s, #1
+; CHECK-GI-NEXT: neg v1.4s, v1.4s
+; CHECK-GI-NEXT: mov v2.s[1], wzr
+; CHECK-GI-NEXT: ushl v1.4s, v3.4s, v1.4s
+; CHECK-GI-NEXT: and v0.16b, v1.16b, v0.16b
+; CHECK-GI-NEXT: mov v2.s[3], wzr
+; CHECK-GI-NEXT: cmeq v0.4s, v0.4s, v2.4s
+; CHECK-GI-NEXT: xtn v0.4h, v0.4s
+; CHECK-GI-NEXT: ret
%t0 = lshr <4 x i32> <i32 1, i32 1, i32 1, i32 1>, %y
%t1 = and <4 x i32> %t0, %x
%res = icmp eq <4 x i32> %t1, <i32 0, i32 0, i32 undef, i32 0>
ret <4 x i1> %res
}
define <4 x i1> @vec_4xi32_nonsplat_undef2_eq(<4 x i32> %x, <4 x i32> %y) nounwind {
-; CHECK-LABEL: vec_4xi32_nonsplat_undef2_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: movi v2.4s, #1
-; CHECK-NEXT: neg v1.4s, v1.4s
-; CHECK-NEXT: ushl v1.4s, v2.4s, v1.4s
-; CHECK-NEXT: and v0.16b, v1.16b, v0.16b
-; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
-; CHECK-NEXT: xtn v0.4h, v0.4s
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: vec_4xi32_nonsplat_undef2_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: movi v2.4s, #1
+; CHECK-SD-NEXT: neg v1.4s, v1.4s
+; CHECK-SD-NEXT: ushl v1.4s, v2.4s, v1.4s
+; CHECK-SD-NEXT: and v0.16b, v1.16b, v0.16b
+; CHECK-SD-NEXT: cmeq v0.4s, v0.4s, #0
+; CHECK-SD-NEXT: xtn v0.4h, v0.4s
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: vec_4xi32_nonsplat_undef2_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #1 // =0x1
+; CHECK-GI-NEXT: movi d2, #0000000000000000
+; CHECK-GI-NEXT: neg v1.4s, v1.4s
+; CHECK-GI-NEXT: fmov s3, w8
+; CHECK-GI-NEXT: mov v3.s[1], w8
+; CHECK-GI-NEXT: mov v2.s[1], wzr
+; CHECK-GI-NEXT: mov v3.s[3], w8
+; CHECK-GI-NEXT: mov v2.s[3], wzr
+; CHECK-GI-NEXT: ushl v1.4s, v3.4s, v1.4s
+; CHECK-GI-NEXT: and v0.16b, v1.16b, v0.16b
+; CHECK-GI-NEXT: cmeq v0.4s, v0.4s, v2.4s
+; CHECK-GI-NEXT: xtn v0.4h, v0.4s
+; CHECK-GI-NEXT: ret
%t0 = lshr <4 x i32> <i32 1, i32 1, i32 undef, i32 1>, %y
%t1 = and <4 x i32> %t0, %x
%res = icmp eq <4 x i32> %t1, <i32 0, i32 0, i32 undef, i32 0>
@@ -260,11 +415,20 @@ define <4 x i1> @vec_4xi32_nonsplat_undef2_eq(<4 x i32> %x, <4 x i32> %y) nounwi
;------------------------------------------------------------------------------;
define i1 @scalar_i8_signbit_ne(i8 %x, i8 %y) nounwind {
-; CHECK-LABEL: scalar_i8_signbit_ne:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsl w8, w0, w1
-; CHECK-NEXT: ubfx w0, w8, #7, #1
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i8_signbit_ne:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsl w8, w0, w1
+; CHECK-SD-NEXT: ubfx w0, w8, #7, #1
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i8_signbit_ne:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #128 // =0x80
+; CHECK-GI-NEXT: and w9, w1, #0xff
+; CHECK-GI-NEXT: lsr w8, w8, w9
+; CHECK-GI-NEXT: tst w8, w0
+; CHECK-GI-NEXT: cset w0, ne
+; CHECK-GI-NEXT: ret
%t0 = lshr i8 128, %y
%t1 = and i8 %t0, %x
%res = icmp ne i8 %t1, 0 ; we are perfectly happy with 'ne' predicate
@@ -315,14 +479,24 @@ define i1 @scalar_i8_bitsinmiddle_slt(i8 %x, i8 %y) nounwind {
}
define i1 @scalar_i8_signbit_eq_with_nonzero(i8 %x, i8 %y) nounwind {
-; CHECK-LABEL: scalar_i8_signbit_eq_with_nonzero:
-; CHECK: // %bb.0:
-; CHECK-NEXT: mov w8, #128 // =0x80
-; CHECK-NEXT: lsr w8, w8, w1
-; CHECK-NEXT: and w8, w8, w0
-; CHECK-NEXT: cmp w8, #1
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i8_signbit_eq_with_nonzero:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: mov w8, #128 // =0x80
+; CHECK-SD-NEXT: lsr w8, w8, w1
+; CHECK-SD-NEXT: and w8, w8, w0
+; CHECK-SD-NEXT: cmp w8, #1
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i8_signbit_eq_with_nonzero:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #128 // =0x80
+; CHECK-GI-NEXT: and w9, w1, #0xff
+; CHECK-GI-NEXT: lsr w8, w8, w9
+; CHECK-GI-NEXT: and w8, w8, w0
+; CHECK-GI-NEXT: cmp w8, #1
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = lshr i8 128, %y
%t1 = and i8 %t0, %x
%res = icmp eq i8 %t1, 1 ; should be comparing with 0
diff --git a/llvm/test/CodeGen/AArch64/hoist-and-by-const-from-shl-in-eqcmp-zero.ll b/llvm/test/CodeGen/AArch64/hoist-and-by-const-from-shl-in-eqcmp-zero.ll
index 4a73b10..cc1bf27 100644
--- a/llvm/test/CodeGen/AArch64/hoist-and-by-const-from-shl-in-eqcmp-zero.ll
+++ b/llvm/test/CodeGen/AArch64/hoist-and-by-const-from-shl-in-eqcmp-zero.ll
@@ -1,5 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=aarch64-unknown-unknown < %s | FileCheck %s --check-prefix=CHECK
+; RUN: llc -mtriple=aarch64-unknown-unknown < %s | FileCheck %s --check-prefixes=CHECK,CHECK-SD
+; RUN: llc -mtriple=aarch64-unknown-unknown -global-isel < %s | FileCheck %s --check-prefixes=CHECK,CHECK-GI
; We are looking for the following pattern here:
; (X & (C << Y)) ==/!= 0
@@ -13,13 +14,23 @@
; i8 scalar
define i1 @scalar_i8_signbit_eq(i8 %x, i8 %y) nounwind {
-; CHECK-LABEL: scalar_i8_signbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: and w8, w0, #0xff
-; CHECK-NEXT: lsr w8, w8, w1
-; CHECK-NEXT: tst w8, #0x80
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i8_signbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: and w8, w0, #0xff
+; CHECK-SD-NEXT: lsr w8, w8, w1
+; CHECK-SD-NEXT: tst w8, #0x80
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i8_signbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #-128 // =0xffffff80
+; CHECK-GI-NEXT: and w9, w1, #0xff
+; CHECK-GI-NEXT: lsl w8, w8, w9
+; CHECK-GI-NEXT: and w8, w8, w0
+; CHECK-GI-NEXT: tst w8, #0xff
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = shl i8 128, %y
%t1 = and i8 %t0, %x
%res = icmp eq i8 %t1, 0
@@ -27,13 +38,23 @@ define i1 @scalar_i8_signbit_eq(i8 %x, i8 %y) nounwind {
}
define i1 @scalar_i8_lowestbit_eq(i8 %x, i8 %y) nounwind {
-; CHECK-LABEL: scalar_i8_lowestbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: and w8, w0, #0xff
-; CHECK-NEXT: lsr w8, w8, w1
-; CHECK-NEXT: tst w8, #0x1
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i8_lowestbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: and w8, w0, #0xff
+; CHECK-SD-NEXT: lsr w8, w8, w1
+; CHECK-SD-NEXT: tst w8, #0x1
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i8_lowestbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #1 // =0x1
+; CHECK-GI-NEXT: and w9, w1, #0xff
+; CHECK-GI-NEXT: lsl w8, w8, w9
+; CHECK-GI-NEXT: and w8, w8, w0
+; CHECK-GI-NEXT: tst w8, #0xff
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = shl i8 1, %y
%t1 = and i8 %t0, %x
%res = icmp eq i8 %t1, 0
@@ -41,13 +62,23 @@ define i1 @scalar_i8_lowestbit_eq(i8 %x, i8 %y) nounwind {
}
define i1 @scalar_i8_bitsinmiddle_eq(i8 %x, i8 %y) nounwind {
-; CHECK-LABEL: scalar_i8_bitsinmiddle_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: and w8, w0, #0xff
-; CHECK-NEXT: lsr w8, w8, w1
-; CHECK-NEXT: tst w8, #0x18
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i8_bitsinmiddle_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: and w8, w0, #0xff
+; CHECK-SD-NEXT: lsr w8, w8, w1
+; CHECK-SD-NEXT: tst w8, #0x18
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i8_bitsinmiddle_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #24 // =0x18
+; CHECK-GI-NEXT: and w9, w1, #0xff
+; CHECK-GI-NEXT: lsl w8, w8, w9
+; CHECK-GI-NEXT: and w8, w8, w0
+; CHECK-GI-NEXT: tst w8, #0xff
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = shl i8 24, %y
%t1 = and i8 %t0, %x
%res = icmp eq i8 %t1, 0
@@ -57,13 +88,23 @@ define i1 @scalar_i8_bitsinmiddle_eq(i8 %x, i8 %y) nounwind {
; i16 scalar
define i1 @scalar_i16_signbit_eq(i16 %x, i16 %y) nounwind {
-; CHECK-LABEL: scalar_i16_signbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: and w8, w0, #0xffff
-; CHECK-NEXT: lsr w8, w8, w1
-; CHECK-NEXT: tst w8, #0x8000
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i16_signbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: and w8, w0, #0xffff
+; CHECK-SD-NEXT: lsr w8, w8, w1
+; CHECK-SD-NEXT: tst w8, #0x8000
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i16_signbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #-32768 // =0xffff8000
+; CHECK-GI-NEXT: and w9, w1, #0xffff
+; CHECK-GI-NEXT: lsl w8, w8, w9
+; CHECK-GI-NEXT: and w8, w8, w0
+; CHECK-GI-NEXT: tst w8, #0xffff
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = shl i16 32768, %y
%t1 = and i16 %t0, %x
%res = icmp eq i16 %t1, 0
@@ -71,13 +112,23 @@ define i1 @scalar_i16_signbit_eq(i16 %x, i16 %y) nounwind {
}
define i1 @scalar_i16_lowestbit_eq(i16 %x, i16 %y) nounwind {
-; CHECK-LABEL: scalar_i16_lowestbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: and w8, w0, #0xffff
-; CHECK-NEXT: lsr w8, w8, w1
-; CHECK-NEXT: tst w8, #0x1
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i16_lowestbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: and w8, w0, #0xffff
+; CHECK-SD-NEXT: lsr w8, w8, w1
+; CHECK-SD-NEXT: tst w8, #0x1
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i16_lowestbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #1 // =0x1
+; CHECK-GI-NEXT: and w9, w1, #0xffff
+; CHECK-GI-NEXT: lsl w8, w8, w9
+; CHECK-GI-NEXT: and w8, w8, w0
+; CHECK-GI-NEXT: tst w8, #0xffff
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = shl i16 1, %y
%t1 = and i16 %t0, %x
%res = icmp eq i16 %t1, 0
@@ -85,13 +136,23 @@ define i1 @scalar_i16_lowestbit_eq(i16 %x, i16 %y) nounwind {
}
define i1 @scalar_i16_bitsinmiddle_eq(i16 %x, i16 %y) nounwind {
-; CHECK-LABEL: scalar_i16_bitsinmiddle_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: and w8, w0, #0xffff
-; CHECK-NEXT: lsr w8, w8, w1
-; CHECK-NEXT: tst w8, #0xff0
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i16_bitsinmiddle_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: and w8, w0, #0xffff
+; CHECK-SD-NEXT: lsr w8, w8, w1
+; CHECK-SD-NEXT: tst w8, #0xff0
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i16_bitsinmiddle_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #4080 // =0xff0
+; CHECK-GI-NEXT: and w9, w1, #0xffff
+; CHECK-GI-NEXT: lsl w8, w8, w9
+; CHECK-GI-NEXT: and w8, w8, w0
+; CHECK-GI-NEXT: tst w8, #0xffff
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = shl i16 4080, %y
%t1 = and i16 %t0, %x
%res = icmp eq i16 %t1, 0
@@ -101,12 +162,20 @@ define i1 @scalar_i16_bitsinmiddle_eq(i16 %x, i16 %y) nounwind {
; i32 scalar
define i1 @scalar_i32_signbit_eq(i32 %x, i32 %y) nounwind {
-; CHECK-LABEL: scalar_i32_signbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsr w8, w0, w1
-; CHECK-NEXT: tst w8, #0x80000000
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i32_signbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsr w8, w0, w1
+; CHECK-SD-NEXT: tst w8, #0x80000000
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i32_signbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #-2147483648 // =0x80000000
+; CHECK-GI-NEXT: lsl w8, w8, w1
+; CHECK-GI-NEXT: tst w8, w0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = shl i32 2147483648, %y
%t1 = and i32 %t0, %x
%res = icmp eq i32 %t1, 0
@@ -114,12 +183,20 @@ define i1 @scalar_i32_signbit_eq(i32 %x, i32 %y) nounwind {
}
define i1 @scalar_i32_lowestbit_eq(i32 %x, i32 %y) nounwind {
-; CHECK-LABEL: scalar_i32_lowestbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsr w8, w0, w1
-; CHECK-NEXT: tst w8, #0x1
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i32_lowestbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsr w8, w0, w1
+; CHECK-SD-NEXT: tst w8, #0x1
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i32_lowestbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #1 // =0x1
+; CHECK-GI-NEXT: lsl w8, w8, w1
+; CHECK-GI-NEXT: tst w8, w0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = shl i32 1, %y
%t1 = and i32 %t0, %x
%res = icmp eq i32 %t1, 0
@@ -127,12 +204,20 @@ define i1 @scalar_i32_lowestbit_eq(i32 %x, i32 %y) nounwind {
}
define i1 @scalar_i32_bitsinmiddle_eq(i32 %x, i32 %y) nounwind {
-; CHECK-LABEL: scalar_i32_bitsinmiddle_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsr w8, w0, w1
-; CHECK-NEXT: tst w8, #0xffff00
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i32_bitsinmiddle_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsr w8, w0, w1
+; CHECK-SD-NEXT: tst w8, #0xffff00
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i32_bitsinmiddle_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #16776960 // =0xffff00
+; CHECK-GI-NEXT: lsl w8, w8, w1
+; CHECK-GI-NEXT: tst w8, w0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = shl i32 16776960, %y
%t1 = and i32 %t0, %x
%res = icmp eq i32 %t1, 0
@@ -142,12 +227,20 @@ define i1 @scalar_i32_bitsinmiddle_eq(i32 %x, i32 %y) nounwind {
; i64 scalar
define i1 @scalar_i64_signbit_eq(i64 %x, i64 %y) nounwind {
-; CHECK-LABEL: scalar_i64_signbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsr x8, x0, x1
-; CHECK-NEXT: tst x8, #0x8000000000000000
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i64_signbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsr x8, x0, x1
+; CHECK-SD-NEXT: tst x8, #0x8000000000000000
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i64_signbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov x8, #-9223372036854775808 // =0x8000000000000000
+; CHECK-GI-NEXT: lsl x8, x8, x1
+; CHECK-GI-NEXT: tst x8, x0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = shl i64 9223372036854775808, %y
%t1 = and i64 %t0, %x
%res = icmp eq i64 %t1, 0
@@ -155,12 +248,20 @@ define i1 @scalar_i64_signbit_eq(i64 %x, i64 %y) nounwind {
}
define i1 @scalar_i64_lowestbit_eq(i64 %x, i64 %y) nounwind {
-; CHECK-LABEL: scalar_i64_lowestbit_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsr x8, x0, x1
-; CHECK-NEXT: tst x8, #0x1
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i64_lowestbit_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsr x8, x0, x1
+; CHECK-SD-NEXT: tst x8, #0x1
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i64_lowestbit_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #1 // =0x1
+; CHECK-GI-NEXT: lsl x8, x8, x1
+; CHECK-GI-NEXT: tst x8, x0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = shl i64 1, %y
%t1 = and i64 %t0, %x
%res = icmp eq i64 %t1, 0
@@ -168,12 +269,20 @@ define i1 @scalar_i64_lowestbit_eq(i64 %x, i64 %y) nounwind {
}
define i1 @scalar_i64_bitsinmiddle_eq(i64 %x, i64 %y) nounwind {
-; CHECK-LABEL: scalar_i64_bitsinmiddle_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: lsr x8, x0, x1
-; CHECK-NEXT: tst x8, #0xffffffff0000
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i64_bitsinmiddle_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: lsr x8, x0, x1
+; CHECK-SD-NEXT: tst x8, #0xffffffff0000
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i64_bitsinmiddle_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov x8, #281474976645120 // =0xffffffff0000
+; CHECK-GI-NEXT: lsl x8, x8, x1
+; CHECK-GI-NEXT: tst x8, x0
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%t0 = shl i64 281474976645120, %y
%t1 = and i64 %t0, %x
%res = icmp eq i64 %t1, 0
@@ -216,42 +325,81 @@ define <4 x i1> @vec_4xi32_nonsplat_eq(<4 x i32> %x, <4 x i32> %y) nounwind {
}
define <4 x i1> @vec_4xi32_nonsplat_undef0_eq(<4 x i32> %x, <4 x i32> %y) nounwind {
-; CHECK-LABEL: vec_4xi32_nonsplat_undef0_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: movi v2.4s, #1
-; CHECK-NEXT: ushl v1.4s, v2.4s, v1.4s
-; CHECK-NEXT: and v0.16b, v1.16b, v0.16b
-; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
-; CHECK-NEXT: xtn v0.4h, v0.4s
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: vec_4xi32_nonsplat_undef0_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: movi v2.4s, #1
+; CHECK-SD-NEXT: ushl v1.4s, v2.4s, v1.4s
+; CHECK-SD-NEXT: and v0.16b, v1.16b, v0.16b
+; CHECK-SD-NEXT: cmeq v0.4s, v0.4s, #0
+; CHECK-SD-NEXT: xtn v0.4h, v0.4s
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: vec_4xi32_nonsplat_undef0_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #1 // =0x1
+; CHECK-GI-NEXT: fmov s2, w8
+; CHECK-GI-NEXT: mov v2.s[1], w8
+; CHECK-GI-NEXT: mov v2.s[3], w8
+; CHECK-GI-NEXT: ushl v1.4s, v2.4s, v1.4s
+; CHECK-GI-NEXT: and v0.16b, v1.16b, v0.16b
+; CHECK-GI-NEXT: cmeq v0.4s, v0.4s, #0
+; CHECK-GI-NEXT: xtn v0.4h, v0.4s
+; CHECK-GI-NEXT: ret
%t0 = shl <4 x i32> <i32 1, i32 1, i32 undef, i32 1>, %y
%t1 = and <4 x i32> %t0, %x
%res = icmp eq <4 x i32> %t1, <i32 0, i32 0, i32 0, i32 0>
ret <4 x i1> %res
}
define <4 x i1> @vec_4xi32_nonsplat_undef1_eq(<4 x i32> %x, <4 x i32> %y) nounwind {
-; CHECK-LABEL: vec_4xi32_nonsplat_undef1_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: movi v2.4s, #1
-; CHECK-NEXT: ushl v1.4s, v2.4s, v1.4s
-; CHECK-NEXT: and v0.16b, v1.16b, v0.16b
-; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
-; CHECK-NEXT: xtn v0.4h, v0.4s
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: vec_4xi32_nonsplat_undef1_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: movi v2.4s, #1
+; CHECK-SD-NEXT: ushl v1.4s, v2.4s, v1.4s
+; CHECK-SD-NEXT: and v0.16b, v1.16b, v0.16b
+; CHECK-SD-NEXT: cmeq v0.4s, v0.4s, #0
+; CHECK-SD-NEXT: xtn v0.4h, v0.4s
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: vec_4xi32_nonsplat_undef1_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: movi d3, #0000000000000000
+; CHECK-GI-NEXT: movi v2.4s, #1
+; CHECK-GI-NEXT: mov v3.s[1], wzr
+; CHECK-GI-NEXT: ushl v1.4s, v2.4s, v1.4s
+; CHECK-GI-NEXT: and v0.16b, v1.16b, v0.16b
+; CHECK-GI-NEXT: mov v3.s[3], wzr
+; CHECK-GI-NEXT: cmeq v0.4s, v0.4s, v3.4s
+; CHECK-GI-NEXT: xtn v0.4h, v0.4s
+; CHECK-GI-NEXT: ret
%t0 = shl <4 x i32> <i32 1, i32 1, i32 1, i32 1>, %y
%t1 = and <4 x i32> %t0, %x
%res = icmp eq <4 x i32> %t1, <i32 0, i32 0, i32 undef, i32 0>
ret <4 x i1> %res
}
define <4 x i1> @vec_4xi32_nonsplat_undef2_eq(<4 x i32> %x, <4 x i32> %y) nounwind {
-; CHECK-LABEL: vec_4xi32_nonsplat_undef2_eq:
-; CHECK: // %bb.0:
-; CHECK-NEXT: movi v2.4s, #1
-; CHECK-NEXT: ushl v1.4s, v2.4s, v1.4s
-; CHECK-NEXT: and v0.16b, v1.16b, v0.16b
-; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
-; CHECK-NEXT: xtn v0.4h, v0.4s
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: vec_4xi32_nonsplat_undef2_eq:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: movi v2.4s, #1
+; CHECK-SD-NEXT: ushl v1.4s, v2.4s, v1.4s
+; CHECK-SD-NEXT: and v0.16b, v1.16b, v0.16b
+; CHECK-SD-NEXT: cmeq v0.4s, v0.4s, #0
+; CHECK-SD-NEXT: xtn v0.4h, v0.4s
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: vec_4xi32_nonsplat_undef2_eq:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #1 // =0x1
+; CHECK-GI-NEXT: movi d3, #0000000000000000
+; CHECK-GI-NEXT: fmov s2, w8
+; CHECK-GI-NEXT: mov v2.s[1], w8
+; CHECK-GI-NEXT: mov v3.s[1], wzr
+; CHECK-GI-NEXT: mov v2.s[3], w8
+; CHECK-GI-NEXT: mov v3.s[3], wzr
+; CHECK-GI-NEXT: ushl v1.4s, v2.4s, v1.4s
+; CHECK-GI-NEXT: and v0.16b, v1.16b, v0.16b
+; CHECK-GI-NEXT: cmeq v0.4s, v0.4s, v3.4s
+; CHECK-GI-NEXT: xtn v0.4h, v0.4s
+; CHECK-GI-NEXT: ret
%t0 = shl <4 x i32> <i32 1, i32 1, i32 undef, i32 1>, %y
%t1 = and <4 x i32> %t0, %x
%res = icmp eq <4 x i32> %t1, <i32 0, i32 0, i32 undef, i32 0>
@@ -263,12 +411,22 @@ define <4 x i1> @vec_4xi32_nonsplat_undef2_eq(<4 x i32> %x, <4 x i32> %y) nounwi
;------------------------------------------------------------------------------;
define i1 @scalar_i8_signbit_ne(i8 %x, i8 %y) nounwind {
-; CHECK-LABEL: scalar_i8_signbit_ne:
-; CHECK: // %bb.0:
-; CHECK-NEXT: and w8, w0, #0xff
-; CHECK-NEXT: lsr w8, w8, w1
-; CHECK-NEXT: lsr w0, w8, #7
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i8_signbit_ne:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: and w8, w0, #0xff
+; CHECK-SD-NEXT: lsr w8, w8, w1
+; CHECK-SD-NEXT: lsr w0, w8, #7
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i8_signbit_ne:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #-128 // =0xffffff80
+; CHECK-GI-NEXT: and w9, w1, #0xff
+; CHECK-GI-NEXT: lsl w8, w8, w9
+; CHECK-GI-NEXT: and w8, w8, w0
+; CHECK-GI-NEXT: tst w8, #0xff
+; CHECK-GI-NEXT: cset w0, ne
+; CHECK-GI-NEXT: ret
%t0 = shl i8 128, %y
%t1 = and i8 %t0, %x
%res = icmp ne i8 %t1, 0 ; we are perfectly happy with 'ne' predicate
@@ -310,13 +468,24 @@ define i1 @scalar_i32_x_is_const2_eq(i32 %y) nounwind {
}
define i1 @scalar_i8_bitsinmiddle_slt(i8 %x, i8 %y) nounwind {
-; CHECK-LABEL: scalar_i8_bitsinmiddle_slt:
-; CHECK: // %bb.0:
-; CHECK-NEXT: mov w8, #24 // =0x18
-; CHECK-NEXT: lsl w8, w8, w1
-; CHECK-NEXT: and w8, w8, w0
-; CHECK-NEXT: ubfx w0, w8, #7, #1
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i8_bitsinmiddle_slt:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: mov w8, #24 // =0x18
+; CHECK-SD-NEXT: lsl w8, w8, w1
+; CHECK-SD-NEXT: and w8, w8, w0
+; CHECK-SD-NEXT: ubfx w0, w8, #7, #1
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i8_bitsinmiddle_slt:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #24 // =0x18
+; CHECK-GI-NEXT: and w9, w1, #0xff
+; CHECK-GI-NEXT: lsl w8, w8, w9
+; CHECK-GI-NEXT: and w8, w8, w0
+; CHECK-GI-NEXT: sxtb w8, w8
+; CHECK-GI-NEXT: cmp w8, #0
+; CHECK-GI-NEXT: cset w0, mi
+; CHECK-GI-NEXT: ret
%t0 = shl i8 24, %y
%t1 = and i8 %t0, %x
%res = icmp slt i8 %t1, 0
@@ -324,15 +493,20 @@ define i1 @scalar_i8_bitsinmiddle_slt(i8 %x, i8 %y) nounwind {
}
define i1 @scalar_i8_signbit_eq_with_nonzero(i8 %x, i8 %y) nounwind {
-; CHECK-LABEL: scalar_i8_signbit_eq_with_nonzero:
-; CHECK: // %bb.0:
-; CHECK-NEXT: mov w8, #-128 // =0xffffff80
-; CHECK-NEXT: lsl w8, w8, w1
-; CHECK-NEXT: and w8, w8, w0
-; CHECK-NEXT: and w8, w8, #0x80
-; CHECK-NEXT: cmp w8, #1
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: scalar_i8_signbit_eq_with_nonzero:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: mov w8, #-128 // =0xffffff80
+; CHECK-SD-NEXT: lsl w8, w8, w1
+; CHECK-SD-NEXT: and w8, w8, w0
+; CHECK-SD-NEXT: and w8, w8, #0x80
+; CHECK-SD-NEXT: cmp w8, #1
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: scalar_i8_signbit_eq_with_nonzero:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w0, wzr
+; CHECK-GI-NEXT: ret
%t0 = shl i8 128, %y
%t1 = and i8 %t0, %x
%res = icmp eq i8 %t1, 1 ; should be comparing with 0
diff --git a/llvm/test/CodeGen/AArch64/llvm.sincos.ll b/llvm/test/CodeGen/AArch64/llvm.sincos.ll
index f1dcb2a..21da864 100644
--- a/llvm/test/CodeGen/AArch64/llvm.sincos.ll
+++ b/llvm/test/CodeGen/AArch64/llvm.sincos.ll
@@ -215,6 +215,133 @@ define { <2 x half>, <2 x half> } @test_sincos_v2f16(<2 x half> %a) nounwind {
ret { <2 x half>, <2 x half> } %result
}
+define { <3 x half>, <3 x half> } @test_sincos_v3f16(<3 x half> %a) nounwind {
+; CHECK-LABEL: test_sincos_v3f16:
+; CHECK: // %bb.0:
+; CHECK-NEXT: sub sp, sp, #64
+; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT: mov h1, v0.h[1]
+; CHECK-NEXT: str q0, [sp] // 16-byte Folded Spill
+; CHECK-NEXT: add x0, sp, #36
+; CHECK-NEXT: add x1, sp, #32
+; CHECK-NEXT: str x30, [sp, #48] // 8-byte Folded Spill
+; CHECK-NEXT: fcvt s0, h1
+; CHECK-NEXT: bl sincosf
+; CHECK-NEXT: ldr q0, [sp] // 16-byte Folded Reload
+; CHECK-NEXT: add x0, sp, #28
+; CHECK-NEXT: add x1, sp, #24
+; CHECK-NEXT: fcvt s0, h0
+; CHECK-NEXT: bl sincosf
+; CHECK-NEXT: ldr q0, [sp] // 16-byte Folded Reload
+; CHECK-NEXT: add x0, sp, #44
+; CHECK-NEXT: add x1, sp, #40
+; CHECK-NEXT: mov h0, v0.h[2]
+; CHECK-NEXT: fcvt s0, h0
+; CHECK-NEXT: bl sincosf
+; CHECK-NEXT: ldr q0, [sp] // 16-byte Folded Reload
+; CHECK-NEXT: add x0, sp, #60
+; CHECK-NEXT: add x1, sp, #56
+; CHECK-NEXT: mov h0, v0.h[3]
+; CHECK-NEXT: fcvt s0, h0
+; CHECK-NEXT: bl sincosf
+; CHECK-NEXT: ldp s2, s0, [sp, #32]
+; CHECK-NEXT: ldr x30, [sp, #48] // 8-byte Folded Reload
+; CHECK-NEXT: ldp s3, s1, [sp, #24]
+; CHECK-NEXT: fcvt h4, s0
+; CHECK-NEXT: fcvt h2, s2
+; CHECK-NEXT: fcvt h0, s1
+; CHECK-NEXT: fcvt h1, s3
+; CHECK-NEXT: ldp s5, s3, [sp, #40]
+; CHECK-NEXT: fcvt h3, s3
+; CHECK-NEXT: mov v0.h[1], v4.h[0]
+; CHECK-NEXT: fcvt h4, s5
+; CHECK-NEXT: mov v1.h[1], v2.h[0]
+; CHECK-NEXT: ldp s5, s2, [sp, #56]
+; CHECK-NEXT: mov v0.h[2], v3.h[0]
+; CHECK-NEXT: fcvt h2, s2
+; CHECK-NEXT: fcvt h3, s5
+; CHECK-NEXT: mov v1.h[2], v4.h[0]
+; CHECK-NEXT: mov v0.h[3], v2.h[0]
+; CHECK-NEXT: mov v1.h[3], v3.h[0]
+; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
+; CHECK-NEXT: // kill: def $d1 killed $d1 killed $q1
+; CHECK-NEXT: add sp, sp, #64
+; CHECK-NEXT: ret
+;
+; NO-LIBCALL-LABEL: test_sincos_v3f16:
+; NO-LIBCALL: // %bb.0:
+; NO-LIBCALL-NEXT: sub sp, sp, #80
+; NO-LIBCALL-NEXT: // kill: def $d0 killed $d0 def $q0
+; NO-LIBCALL-NEXT: mov h1, v0.h[1]
+; NO-LIBCALL-NEXT: stp d9, d8, [sp, #48] // 16-byte Folded Spill
+; NO-LIBCALL-NEXT: str q0, [sp] // 16-byte Folded Spill
+; NO-LIBCALL-NEXT: stp d11, d10, [sp, #32] // 16-byte Folded Spill
+; NO-LIBCALL-NEXT: str x30, [sp, #64] // 8-byte Folded Spill
+; NO-LIBCALL-NEXT: fcvt s8, h1
+; NO-LIBCALL-NEXT: fmov s0, s8
+; NO-LIBCALL-NEXT: bl sinf
+; NO-LIBCALL-NEXT: ldr q1, [sp] // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: fcvt h0, s0
+; NO-LIBCALL-NEXT: fcvt s9, h1
+; NO-LIBCALL-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
+; NO-LIBCALL-NEXT: fmov s0, s9
+; NO-LIBCALL-NEXT: bl sinf
+; NO-LIBCALL-NEXT: ldr q1, [sp] // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: fcvt h0, s0
+; NO-LIBCALL-NEXT: mov h1, v1.h[2]
+; NO-LIBCALL-NEXT: fcvt s10, h1
+; NO-LIBCALL-NEXT: ldr q1, [sp, #16] // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: mov v0.h[1], v1.h[0]
+; NO-LIBCALL-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
+; NO-LIBCALL-NEXT: fmov s0, s10
+; NO-LIBCALL-NEXT: bl sinf
+; NO-LIBCALL-NEXT: ldr q1, [sp] // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: fcvt h0, s0
+; NO-LIBCALL-NEXT: mov h1, v1.h[3]
+; NO-LIBCALL-NEXT: fcvt s11, h1
+; NO-LIBCALL-NEXT: ldr q1, [sp, #16] // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: mov v1.h[2], v0.h[0]
+; NO-LIBCALL-NEXT: fmov s0, s11
+; NO-LIBCALL-NEXT: str q1, [sp, #16] // 16-byte Folded Spill
+; NO-LIBCALL-NEXT: bl sinf
+; NO-LIBCALL-NEXT: fcvt h0, s0
+; NO-LIBCALL-NEXT: ldr q1, [sp, #16] // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: mov v1.h[3], v0.h[0]
+; NO-LIBCALL-NEXT: fmov s0, s8
+; NO-LIBCALL-NEXT: str q1, [sp, #16] // 16-byte Folded Spill
+; NO-LIBCALL-NEXT: bl cosf
+; NO-LIBCALL-NEXT: fcvt h0, s0
+; NO-LIBCALL-NEXT: str q0, [sp] // 16-byte Folded Spill
+; NO-LIBCALL-NEXT: fmov s0, s9
+; NO-LIBCALL-NEXT: bl cosf
+; NO-LIBCALL-NEXT: fcvt h0, s0
+; NO-LIBCALL-NEXT: ldr q1, [sp] // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: mov v0.h[1], v1.h[0]
+; NO-LIBCALL-NEXT: str q0, [sp] // 16-byte Folded Spill
+; NO-LIBCALL-NEXT: fmov s0, s10
+; NO-LIBCALL-NEXT: bl cosf
+; NO-LIBCALL-NEXT: fcvt h0, s0
+; NO-LIBCALL-NEXT: ldr q1, [sp] // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: mov v1.h[2], v0.h[0]
+; NO-LIBCALL-NEXT: fmov s0, s11
+; NO-LIBCALL-NEXT: str q1, [sp] // 16-byte Folded Spill
+; NO-LIBCALL-NEXT: bl cosf
+; NO-LIBCALL-NEXT: fmov s1, s0
+; NO-LIBCALL-NEXT: ldp d9, d8, [sp, #48] // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: ldp d11, d10, [sp, #32] // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: ldr q0, [sp, #16] // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: ldr x30, [sp, #64] // 8-byte Folded Reload
+; NO-LIBCALL-NEXT: // kill: def $d0 killed $d0 killed $q0
+; NO-LIBCALL-NEXT: fcvt h2, s1
+; NO-LIBCALL-NEXT: ldr q1, [sp] // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: mov v1.h[3], v2.h[0]
+; NO-LIBCALL-NEXT: // kill: def $d1 killed $d1 killed $q1
+; NO-LIBCALL-NEXT: add sp, sp, #80
+; NO-LIBCALL-NEXT: ret
+ %result = call { <3 x half>, <3 x half> } @llvm.sincos.v3f16(<3 x half> %a)
+ ret { <3 x half>, <3 x half> } %result
+}
+
define { float, float } @test_sincos_f32(float %a) nounwind {
; CHECK-LABEL: test_sincos_f32:
; CHECK: // %bb.0:
@@ -493,3 +620,71 @@ define { <2 x double>, <2 x double> } @test_sincos_v2f64(<2 x double> %a) nounwi
%result = call { <2 x double>, <2 x double> } @llvm.sincos.v2f64(<2 x double> %a)
ret { <2 x double>, <2 x double> } %result
}
+
+define { <3 x double>, <3 x double> } @test_sincos_v3f64(<3 x double> %a) nounwind {
+; CHECK-LABEL: test_sincos_v3f64:
+; CHECK: // %bb.0:
+; CHECK-NEXT: sub sp, sp, #80
+; CHECK-NEXT: add x0, sp, #16
+; CHECK-NEXT: add x1, sp, #8
+; CHECK-NEXT: stp d9, d8, [sp, #48] // 16-byte Folded Spill
+; CHECK-NEXT: str x30, [sp, #64] // 8-byte Folded Spill
+; CHECK-NEXT: fmov d8, d2
+; CHECK-NEXT: fmov d9, d1
+; CHECK-NEXT: bl sincos
+; CHECK-NEXT: fmov d0, d9
+; CHECK-NEXT: add x0, sp, #32
+; CHECK-NEXT: add x1, sp, #24
+; CHECK-NEXT: bl sincos
+; CHECK-NEXT: fmov d0, d8
+; CHECK-NEXT: add x0, sp, #72
+; CHECK-NEXT: add x1, sp, #40
+; CHECK-NEXT: bl sincos
+; CHECK-NEXT: ldp d3, d0, [sp, #8]
+; CHECK-NEXT: ldr d2, [sp, #72]
+; CHECK-NEXT: ldp d4, d1, [sp, #24]
+; CHECK-NEXT: ldr d5, [sp, #40]
+; CHECK-NEXT: ldr x30, [sp, #64] // 8-byte Folded Reload
+; CHECK-NEXT: ldp d9, d8, [sp, #48] // 16-byte Folded Reload
+; CHECK-NEXT: add sp, sp, #80
+; CHECK-NEXT: ret
+;
+; NO-LIBCALL-LABEL: test_sincos_v3f64:
+; NO-LIBCALL: // %bb.0:
+; NO-LIBCALL-NEXT: stp d13, d12, [sp, #-64]! // 16-byte Folded Spill
+; NO-LIBCALL-NEXT: stp d11, d10, [sp, #16] // 16-byte Folded Spill
+; NO-LIBCALL-NEXT: fmov d10, d0
+; NO-LIBCALL-NEXT: stp d9, d8, [sp, #32] // 16-byte Folded Spill
+; NO-LIBCALL-NEXT: fmov d8, d2
+; NO-LIBCALL-NEXT: fmov d9, d1
+; NO-LIBCALL-NEXT: str x30, [sp, #48] // 8-byte Folded Spill
+; NO-LIBCALL-NEXT: bl sin
+; NO-LIBCALL-NEXT: fmov d11, d0
+; NO-LIBCALL-NEXT: fmov d0, d9
+; NO-LIBCALL-NEXT: bl sin
+; NO-LIBCALL-NEXT: fmov d12, d0
+; NO-LIBCALL-NEXT: fmov d0, d8
+; NO-LIBCALL-NEXT: bl sin
+; NO-LIBCALL-NEXT: fmov d13, d0
+; NO-LIBCALL-NEXT: fmov d0, d10
+; NO-LIBCALL-NEXT: bl cos
+; NO-LIBCALL-NEXT: fmov d10, d0
+; NO-LIBCALL-NEXT: fmov d0, d9
+; NO-LIBCALL-NEXT: bl cos
+; NO-LIBCALL-NEXT: fmov d9, d0
+; NO-LIBCALL-NEXT: fmov d0, d8
+; NO-LIBCALL-NEXT: bl cos
+; NO-LIBCALL-NEXT: fmov d5, d0
+; NO-LIBCALL-NEXT: fmov d0, d11
+; NO-LIBCALL-NEXT: ldr x30, [sp, #48] // 8-byte Folded Reload
+; NO-LIBCALL-NEXT: fmov d3, d10
+; NO-LIBCALL-NEXT: fmov d4, d9
+; NO-LIBCALL-NEXT: fmov d1, d12
+; NO-LIBCALL-NEXT: ldp d9, d8, [sp, #32] // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: fmov d2, d13
+; NO-LIBCALL-NEXT: ldp d11, d10, [sp, #16] // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: ldp d13, d12, [sp], #64 // 16-byte Folded Reload
+; NO-LIBCALL-NEXT: ret
+ %result = call { <3 x double>, <3 x double> } @llvm.sincos.v3f64(<3 x double> %a)
+ ret { <3 x double>, <3 x double> } %result
+}
diff --git a/llvm/test/CodeGen/AArch64/signbit-test.ll b/llvm/test/CodeGen/AArch64/signbit-test.ll
index c74a934..298495b 100644
--- a/llvm/test/CodeGen/AArch64/signbit-test.ll
+++ b/llvm/test/CodeGen/AArch64/signbit-test.ll
@@ -1,13 +1,21 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=aarch64-- | FileCheck %s
+; RUN: llc -mtriple=aarch64-- < %s | FileCheck %s --check-prefixes=CHECK,CHECK-SD
+; RUN: llc -mtriple=aarch64-- -global-isel < %s | FileCheck %s --check-prefixes=CHECK,CHECK-GI
define i64 @test_clear_mask_i64_i32(i64 %x) nounwind {
-; CHECK-LABEL: test_clear_mask_i64_i32:
-; CHECK: // %bb.0: // %entry
-; CHECK-NEXT: mov w8, #42 // =0x2a
-; CHECK-NEXT: cmn w0, #1
-; CHECK-NEXT: csel x0, x8, x0, gt
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: test_clear_mask_i64_i32:
+; CHECK-SD: // %bb.0: // %entry
+; CHECK-SD-NEXT: mov w8, #42 // =0x2a
+; CHECK-SD-NEXT: cmn w0, #1
+; CHECK-SD-NEXT: csel x0, x8, x0, gt
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: test_clear_mask_i64_i32:
+; CHECK-GI: // %bb.0: // %entry
+; CHECK-GI-NEXT: mov w8, #42 // =0x2a
+; CHECK-GI-NEXT: tst x0, #0x80000000
+; CHECK-GI-NEXT: csel x0, x8, x0, eq
+; CHECK-GI-NEXT: ret
entry:
%a = and i64 %x, 2147483648
%r = icmp eq i64 %a, 0
diff --git a/llvm/test/CodeGen/AArch64/signed-truncation-check.ll b/llvm/test/CodeGen/AArch64/signed-truncation-check.ll
index 7c80f93..fc01c6b 100644
--- a/llvm/test/CodeGen/AArch64/signed-truncation-check.ll
+++ b/llvm/test/CodeGen/AArch64/signed-truncation-check.ll
@@ -1,5 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=aarch64-unknown-linux-gnu < %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-unknown-linux-gnu < %s | FileCheck %s --check-prefixes=CHECK,CHECK-SD
+; RUN: llc -mtriple=aarch64-unknown-linux-gnu -global-isel < %s | FileCheck %s --check-prefixes=CHECK,CHECK-GI
; https://bugs.llvm.org/show_bug.cgi?id=38149
@@ -19,13 +20,22 @@
; ---------------------------------------------------------------------------- ;
define i1 @shifts_eqcmp_i16_i8(i16 %x) nounwind {
-; CHECK-LABEL: shifts_eqcmp_i16_i8:
-; CHECK: // %bb.0:
-; CHECK-NEXT: sxtb w8, w0
-; CHECK-NEXT: and w8, w8, #0xffff
-; CHECK-NEXT: cmp w8, w0, uxth
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: shifts_eqcmp_i16_i8:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: sxtb w8, w0
+; CHECK-SD-NEXT: and w8, w8, #0xffff
+; CHECK-SD-NEXT: cmp w8, w0, uxth
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: shifts_eqcmp_i16_i8:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: lsl w8, w0, #8
+; CHECK-GI-NEXT: sbfx w8, w8, #8, #8
+; CHECK-GI-NEXT: and w8, w8, #0xffff
+; CHECK-GI-NEXT: cmp w8, w0, uxth
+; CHECK-GI-NEXT: cset w0, eq
+; CHECK-GI-NEXT: ret
%tmp0 = shl i16 %x, 8 ; 16-8
%tmp1 = ashr exact i16 %tmp0, 8 ; 16-8
%tmp2 = icmp eq i16 %tmp1, %x
@@ -97,26 +107,43 @@ define i1 @shifts_eqcmp_i64_i8(i64 %x) nounwind {
; ---------------------------------------------------------------------------- ;
define i1 @add_ugecmp_i16_i8(i16 %x) nounwind {
-; CHECK-LABEL: add_ugecmp_i16_i8:
-; CHECK: // %bb.0:
-; CHECK-NEXT: and w8, w0, #0xffff
-; CHECK-NEXT: sub w8, w8, #128
-; CHECK-NEXT: lsr w8, w8, #8
-; CHECK-NEXT: cmp w8, #254
-; CHECK-NEXT: cset w0, hi
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ugecmp_i16_i8:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: and w8, w0, #0xffff
+; CHECK-SD-NEXT: sub w8, w8, #128
+; CHECK-SD-NEXT: lsr w8, w8, #8
+; CHECK-SD-NEXT: cmp w8, #254
+; CHECK-SD-NEXT: cset w0, hi
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ugecmp_i16_i8:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #-128 // =0xffffff80
+; CHECK-GI-NEXT: mov w9, #65280 // =0xff00
+; CHECK-GI-NEXT: add w8, w8, w0, uxth
+; CHECK-GI-NEXT: cmp w8, w9
+; CHECK-GI-NEXT: cset w0, hs
+; CHECK-GI-NEXT: ret
%tmp0 = add i16 %x, -128 ; ~0U << (8-1)
%tmp1 = icmp uge i16 %tmp0, -256 ; ~0U << 8
ret i1 %tmp1
}
define i1 @add_ugecmp_i32_i16_i8(i16 %xx) nounwind {
-; CHECK-LABEL: add_ugecmp_i32_i16_i8:
-; CHECK: // %bb.0:
-; CHECK-NEXT: and w8, w0, #0xffff
-; CHECK-NEXT: cmp w8, w8, sxtb
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ugecmp_i32_i16_i8:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: and w8, w0, #0xffff
+; CHECK-SD-NEXT: cmp w8, w8, sxtb
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ugecmp_i32_i16_i8:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #-128 // =0xffffff80
+; CHECK-GI-NEXT: add w8, w8, w0, uxth
+; CHECK-GI-NEXT: cmn w8, #256
+; CHECK-GI-NEXT: cset w0, hs
+; CHECK-GI-NEXT: ret
%x = zext i16 %xx to i32
%tmp0 = add i32 %x, -128 ; ~0U << (8-1)
%tmp1 = icmp uge i32 %tmp0, -256 ; ~0U << 8
@@ -124,55 +151,92 @@ define i1 @add_ugecmp_i32_i16_i8(i16 %xx) nounwind {
}
define i1 @add_ugecmp_i32_i16(i32 %x) nounwind {
-; CHECK-LABEL: add_ugecmp_i32_i16:
-; CHECK: // %bb.0:
-; CHECK-NEXT: cmp w0, w0, sxth
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ugecmp_i32_i16:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: cmp w0, w0, sxth
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ugecmp_i32_i16:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: sub w8, w0, #8, lsl #12 // =32768
+; CHECK-GI-NEXT: cmn w8, #16, lsl #12 // =65536
+; CHECK-GI-NEXT: cset w0, hs
+; CHECK-GI-NEXT: ret
%tmp0 = add i32 %x, -32768 ; ~0U << (16-1)
%tmp1 = icmp uge i32 %tmp0, -65536 ; ~0U << 16
ret i1 %tmp1
}
define i1 @add_ugecmp_i32_i8(i32 %x) nounwind {
-; CHECK-LABEL: add_ugecmp_i32_i8:
-; CHECK: // %bb.0:
-; CHECK-NEXT: cmp w0, w0, sxtb
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ugecmp_i32_i8:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: cmp w0, w0, sxtb
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ugecmp_i32_i8:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: sub w8, w0, #128
+; CHECK-GI-NEXT: cmn w8, #256
+; CHECK-GI-NEXT: cset w0, hs
+; CHECK-GI-NEXT: ret
%tmp0 = add i32 %x, -128 ; ~0U << (8-1)
%tmp1 = icmp uge i32 %tmp0, -256 ; ~0U << 8
ret i1 %tmp1
}
define i1 @add_ugecmp_i64_i32(i64 %x) nounwind {
-; CHECK-LABEL: add_ugecmp_i64_i32:
-; CHECK: // %bb.0:
-; CHECK-NEXT: cmp x0, w0, sxtw
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ugecmp_i64_i32:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: cmp x0, w0, sxtw
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ugecmp_i64_i32:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov x8, #-2147483648 // =0xffffffff80000000
+; CHECK-GI-NEXT: mov x9, #-4294967296 // =0xffffffff00000000
+; CHECK-GI-NEXT: add x8, x0, x8
+; CHECK-GI-NEXT: cmp x8, x9
+; CHECK-GI-NEXT: cset w0, hs
+; CHECK-GI-NEXT: ret
%tmp0 = add i64 %x, -2147483648 ; ~0U << (32-1)
%tmp1 = icmp uge i64 %tmp0, -4294967296 ; ~0U << 32
ret i1 %tmp1
}
define i1 @add_ugecmp_i64_i16(i64 %x) nounwind {
-; CHECK-LABEL: add_ugecmp_i64_i16:
-; CHECK: // %bb.0:
-; CHECK-NEXT: cmp x0, w0, sxth
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ugecmp_i64_i16:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: cmp x0, w0, sxth
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ugecmp_i64_i16:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: sub x8, x0, #8, lsl #12 // =32768
+; CHECK-GI-NEXT: cmn x8, #16, lsl #12 // =65536
+; CHECK-GI-NEXT: cset w0, hs
+; CHECK-GI-NEXT: ret
%tmp0 = add i64 %x, -32768 ; ~0U << (16-1)
%tmp1 = icmp uge i64 %tmp0, -65536 ; ~0U << 16
ret i1 %tmp1
}
define i1 @add_ugecmp_i64_i8(i64 %x) nounwind {
-; CHECK-LABEL: add_ugecmp_i64_i8:
-; CHECK: // %bb.0:
-; CHECK-NEXT: cmp x0, w0, sxtb
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ugecmp_i64_i8:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: cmp x0, w0, sxtb
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ugecmp_i64_i8:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: sub x8, x0, #128
+; CHECK-GI-NEXT: cmn x8, #256
+; CHECK-GI-NEXT: cset w0, hs
+; CHECK-GI-NEXT: ret
%tmp0 = add i64 %x, -128 ; ~0U << (8-1)
%tmp1 = icmp uge i64 %tmp0, -256 ; ~0U << 8
ret i1 %tmp1
@@ -180,14 +244,23 @@ define i1 @add_ugecmp_i64_i8(i64 %x) nounwind {
; Slightly more canonical variant
define i1 @add_ugtcmp_i16_i8(i16 %x) nounwind {
-; CHECK-LABEL: add_ugtcmp_i16_i8:
-; CHECK: // %bb.0:
-; CHECK-NEXT: and w8, w0, #0xffff
-; CHECK-NEXT: sub w8, w8, #128
-; CHECK-NEXT: lsr w8, w8, #8
-; CHECK-NEXT: cmp w8, #254
-; CHECK-NEXT: cset w0, hi
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ugtcmp_i16_i8:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: and w8, w0, #0xffff
+; CHECK-SD-NEXT: sub w8, w8, #128
+; CHECK-SD-NEXT: lsr w8, w8, #8
+; CHECK-SD-NEXT: cmp w8, #254
+; CHECK-SD-NEXT: cset w0, hi
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ugtcmp_i16_i8:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #-128 // =0xffffff80
+; CHECK-GI-NEXT: mov w9, #65279 // =0xfeff
+; CHECK-GI-NEXT: add w8, w8, w0, uxth
+; CHECK-GI-NEXT: cmp w8, w9
+; CHECK-GI-NEXT: cset w0, hi
+; CHECK-GI-NEXT: ret
%tmp0 = add i16 %x, -128 ; ~0U << (8-1)
%tmp1 = icmp ugt i16 %tmp0, -257 ; ~0U << 8 - 1
ret i1 %tmp1
@@ -198,68 +271,113 @@ define i1 @add_ugtcmp_i16_i8(i16 %x) nounwind {
; ---------------------------------------------------------------------------- ;
define i1 @add_ultcmp_i16_i8(i16 %x) nounwind {
-; CHECK-LABEL: add_ultcmp_i16_i8:
-; CHECK: // %bb.0:
-; CHECK-NEXT: sxtb w8, w0
-; CHECK-NEXT: and w8, w8, #0xffff
-; CHECK-NEXT: cmp w8, w0, uxth
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ultcmp_i16_i8:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: sxtb w8, w0
+; CHECK-SD-NEXT: and w8, w8, #0xffff
+; CHECK-SD-NEXT: cmp w8, w0, uxth
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ultcmp_i16_i8:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: add w8, w0, #128
+; CHECK-GI-NEXT: and w8, w8, #0xffff
+; CHECK-GI-NEXT: cmp w8, #256
+; CHECK-GI-NEXT: cset w0, lo
+; CHECK-GI-NEXT: ret
%tmp0 = add i16 %x, 128 ; 1U << (8-1)
%tmp1 = icmp ult i16 %tmp0, 256 ; 1U << 8
ret i1 %tmp1
}
define i1 @add_ultcmp_i32_i16(i32 %x) nounwind {
-; CHECK-LABEL: add_ultcmp_i32_i16:
-; CHECK: // %bb.0:
-; CHECK-NEXT: cmp w0, w0, sxth
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ultcmp_i32_i16:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: cmp w0, w0, sxth
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ultcmp_i32_i16:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: add w8, w0, #8, lsl #12 // =32768
+; CHECK-GI-NEXT: cmp w8, #16, lsl #12 // =65536
+; CHECK-GI-NEXT: cset w0, lo
+; CHECK-GI-NEXT: ret
%tmp0 = add i32 %x, 32768 ; 1U << (16-1)
%tmp1 = icmp ult i32 %tmp0, 65536 ; 1U << 16
ret i1 %tmp1
}
define i1 @add_ultcmp_i32_i8(i32 %x) nounwind {
-; CHECK-LABEL: add_ultcmp_i32_i8:
-; CHECK: // %bb.0:
-; CHECK-NEXT: cmp w0, w0, sxtb
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ultcmp_i32_i8:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: cmp w0, w0, sxtb
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ultcmp_i32_i8:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: add w8, w0, #128
+; CHECK-GI-NEXT: cmp w8, #256
+; CHECK-GI-NEXT: cset w0, lo
+; CHECK-GI-NEXT: ret
%tmp0 = add i32 %x, 128 ; 1U << (8-1)
%tmp1 = icmp ult i32 %tmp0, 256 ; 1U << 8
ret i1 %tmp1
}
define i1 @add_ultcmp_i64_i32(i64 %x) nounwind {
-; CHECK-LABEL: add_ultcmp_i64_i32:
-; CHECK: // %bb.0:
-; CHECK-NEXT: cmp x0, w0, sxtw
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ultcmp_i64_i32:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: cmp x0, w0, sxtw
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ultcmp_i64_i32:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: mov w8, #-2147483648 // =0x80000000
+; CHECK-GI-NEXT: mov x9, #4294967296 // =0x100000000
+; CHECK-GI-NEXT: add x8, x0, x8
+; CHECK-GI-NEXT: cmp x8, x9
+; CHECK-GI-NEXT: cset w0, lo
+; CHECK-GI-NEXT: ret
%tmp0 = add i64 %x, 2147483648 ; 1U << (32-1)
%tmp1 = icmp ult i64 %tmp0, 4294967296 ; 1U << 32
ret i1 %tmp1
}
define i1 @add_ultcmp_i64_i16(i64 %x) nounwind {
-; CHECK-LABEL: add_ultcmp_i64_i16:
-; CHECK: // %bb.0:
-; CHECK-NEXT: cmp x0, w0, sxth
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ultcmp_i64_i16:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: cmp x0, w0, sxth
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ultcmp_i64_i16:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: add x8, x0, #8, lsl #12 // =32768
+; CHECK-GI-NEXT: cmp x8, #16, lsl #12 // =65536
+; CHECK-GI-NEXT: cset w0, lo
+; CHECK-GI-NEXT: ret
%tmp0 = add i64 %x, 32768 ; 1U << (16-1)
%tmp1 = icmp ult i64 %tmp0, 65536 ; 1U << 16
ret i1 %tmp1
}
define i1 @add_ultcmp_i64_i8(i64 %x) nounwind {
-; CHECK-LABEL: add_ultcmp_i64_i8:
-; CHECK: // %bb.0:
-; CHECK-NEXT: cmp x0, w0, sxtb
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ultcmp_i64_i8:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: cmp x0, w0, sxtb
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ultcmp_i64_i8:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: add x8, x0, #128
+; CHECK-GI-NEXT: cmp x8, #256
+; CHECK-GI-NEXT: cset w0, lo
+; CHECK-GI-NEXT: ret
%tmp0 = add i64 %x, 128 ; 1U << (8-1)
%tmp1 = icmp ult i64 %tmp0, 256 ; 1U << 8
ret i1 %tmp1
@@ -267,13 +385,21 @@ define i1 @add_ultcmp_i64_i8(i64 %x) nounwind {
; Slightly more canonical variant
define i1 @add_ulecmp_i16_i8(i16 %x) nounwind {
-; CHECK-LABEL: add_ulecmp_i16_i8:
-; CHECK: // %bb.0:
-; CHECK-NEXT: sxtb w8, w0
-; CHECK-NEXT: and w8, w8, #0xffff
-; CHECK-NEXT: cmp w8, w0, uxth
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ulecmp_i16_i8:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: sxtb w8, w0
+; CHECK-SD-NEXT: and w8, w8, #0xffff
+; CHECK-SD-NEXT: cmp w8, w0, uxth
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ulecmp_i16_i8:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: add w8, w0, #128
+; CHECK-GI-NEXT: and w8, w8, #0xffff
+; CHECK-GI-NEXT: cmp w8, #255
+; CHECK-GI-NEXT: cset w0, ls
+; CHECK-GI-NEXT: ret
%tmp0 = add i16 %x, 128 ; 1U << (8-1)
%tmp1 = icmp ule i16 %tmp0, 255 ; (1U << 8) - 1
ret i1 %tmp1
@@ -284,12 +410,20 @@ define i1 @add_ulecmp_i16_i8(i16 %x) nounwind {
; Adding not a constant
define i1 @add_ultcmp_bad_i16_i8_add(i16 %x, i16 %y) nounwind {
-; CHECK-LABEL: add_ultcmp_bad_i16_i8_add:
-; CHECK: // %bb.0:
-; CHECK-NEXT: add w8, w0, w1
-; CHECK-NEXT: tst w8, #0xff00
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ultcmp_bad_i16_i8_add:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: add w8, w0, w1
+; CHECK-SD-NEXT: tst w8, #0xff00
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ultcmp_bad_i16_i8_add:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: add w8, w0, w1
+; CHECK-GI-NEXT: and w8, w8, #0xffff
+; CHECK-GI-NEXT: cmp w8, #256
+; CHECK-GI-NEXT: cset w0, lo
+; CHECK-GI-NEXT: ret
%tmp0 = add i16 %x, %y
%tmp1 = icmp ult i16 %tmp0, 256 ; 1U << 8
ret i1 %tmp1
@@ -311,12 +445,20 @@ define i1 @add_ultcmp_bad_i16_i8_cmp(i16 %x, i16 %y) nounwind {
; Second constant is not larger than the first one
define i1 @add_ultcmp_bad_i8_i16(i16 %x) nounwind {
-; CHECK-LABEL: add_ultcmp_bad_i8_i16:
-; CHECK: // %bb.0:
-; CHECK-NEXT: and w8, w0, #0xffff
-; CHECK-NEXT: add w8, w8, #128
-; CHECK-NEXT: lsr w0, w8, #16
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ultcmp_bad_i8_i16:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: and w8, w0, #0xffff
+; CHECK-SD-NEXT: add w8, w8, #128
+; CHECK-SD-NEXT: lsr w0, w8, #16
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ultcmp_bad_i8_i16:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: and w8, w0, #0xffff
+; CHECK-GI-NEXT: add w8, w8, #128
+; CHECK-GI-NEXT: cmp w8, w8, uxth
+; CHECK-GI-NEXT: cset w0, ne
+; CHECK-GI-NEXT: ret
%tmp0 = add i16 %x, 128 ; 1U << (8-1)
%tmp1 = icmp ult i16 %tmp0, 128 ; 1U << (8-1)
ret i1 %tmp1
@@ -324,12 +466,20 @@ define i1 @add_ultcmp_bad_i8_i16(i16 %x) nounwind {
; First constant is not power of two
define i1 @add_ultcmp_bad_i16_i8_c0notpoweroftwo(i16 %x) nounwind {
-; CHECK-LABEL: add_ultcmp_bad_i16_i8_c0notpoweroftwo:
-; CHECK: // %bb.0:
-; CHECK-NEXT: add w8, w0, #192
-; CHECK-NEXT: tst w8, #0xff00
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ultcmp_bad_i16_i8_c0notpoweroftwo:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: add w8, w0, #192
+; CHECK-SD-NEXT: tst w8, #0xff00
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ultcmp_bad_i16_i8_c0notpoweroftwo:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: add w8, w0, #192
+; CHECK-GI-NEXT: and w8, w8, #0xffff
+; CHECK-GI-NEXT: cmp w8, #256
+; CHECK-GI-NEXT: cset w0, lo
+; CHECK-GI-NEXT: ret
%tmp0 = add i16 %x, 192 ; (1U << (8-1)) + (1U << (8-1-1))
%tmp1 = icmp ult i16 %tmp0, 256 ; 1U << 8
ret i1 %tmp1
@@ -351,12 +501,20 @@ define i1 @add_ultcmp_bad_i16_i8_c1notpoweroftwo(i16 %x) nounwind {
; Magic check fails, 64 << 1 != 256
define i1 @add_ultcmp_bad_i16_i8_magic(i16 %x) nounwind {
-; CHECK-LABEL: add_ultcmp_bad_i16_i8_magic:
-; CHECK: // %bb.0:
-; CHECK-NEXT: add w8, w0, #64
-; CHECK-NEXT: tst w8, #0xff00
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ultcmp_bad_i16_i8_magic:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: add w8, w0, #64
+; CHECK-SD-NEXT: tst w8, #0xff00
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ultcmp_bad_i16_i8_magic:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: add w8, w0, #64
+; CHECK-GI-NEXT: and w8, w8, #0xffff
+; CHECK-GI-NEXT: cmp w8, #256
+; CHECK-GI-NEXT: cset w0, lo
+; CHECK-GI-NEXT: ret
%tmp0 = add i16 %x, 64 ; 1U << (8-1-1)
%tmp1 = icmp ult i16 %tmp0, 256 ; 1U << 8
ret i1 %tmp1
@@ -364,12 +522,20 @@ define i1 @add_ultcmp_bad_i16_i8_magic(i16 %x) nounwind {
; Bad 'destination type'
define i1 @add_ultcmp_bad_i16_i4(i16 %x) nounwind {
-; CHECK-LABEL: add_ultcmp_bad_i16_i4:
-; CHECK: // %bb.0:
-; CHECK-NEXT: add w8, w0, #8
-; CHECK-NEXT: tst w8, #0xfff0
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ultcmp_bad_i16_i4:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: add w8, w0, #8
+; CHECK-SD-NEXT: tst w8, #0xfff0
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ultcmp_bad_i16_i4:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: add w8, w0, #8
+; CHECK-GI-NEXT: and w8, w8, #0xffff
+; CHECK-GI-NEXT: cmp w8, #16
+; CHECK-GI-NEXT: cset w0, lo
+; CHECK-GI-NEXT: ret
%tmp0 = add i16 %x, 8 ; 1U << (4-1)
%tmp1 = icmp ult i16 %tmp0, 16 ; 1U << 4
ret i1 %tmp1
@@ -377,12 +543,20 @@ define i1 @add_ultcmp_bad_i16_i4(i16 %x) nounwind {
; Bad storage type
define i1 @add_ultcmp_bad_i24_i8(i24 %x) nounwind {
-; CHECK-LABEL: add_ultcmp_bad_i24_i8:
-; CHECK: // %bb.0:
-; CHECK-NEXT: add w8, w0, #128
-; CHECK-NEXT: tst w8, #0xffff00
-; CHECK-NEXT: cset w0, eq
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: add_ultcmp_bad_i24_i8:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: add w8, w0, #128
+; CHECK-SD-NEXT: tst w8, #0xffff00
+; CHECK-SD-NEXT: cset w0, eq
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: add_ultcmp_bad_i24_i8:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: add w8, w0, #128
+; CHECK-GI-NEXT: and w8, w8, #0xffffff
+; CHECK-GI-NEXT: cmp w8, #256
+; CHECK-GI-NEXT: cset w0, lo
+; CHECK-GI-NEXT: ret
%tmp0 = add i24 %x, 128 ; 1U << (8-1)
%tmp1 = icmp ult i24 %tmp0, 256 ; 1U << 8
ret i1 %tmp1
diff --git a/llvm/test/CodeGen/AArch64/stackmap.ll b/llvm/test/CodeGen/AArch64/stackmap.ll
index 995d254..26221d0 100644
--- a/llvm/test/CodeGen/AArch64/stackmap.ll
+++ b/llvm/test/CodeGen/AArch64/stackmap.ll
@@ -81,14 +81,14 @@
; CHECK-NEXT: .hword 8
; CHECK-NEXT: .hword 0
; CHECK-NEXT: .hword 0
-; CHECK-NEXT: .word 65535
+; CHECK-NEXT: .word -1
; SmallConstant
; CHECK-NEXT: .byte 4
; CHECK-NEXT: .byte 0
; CHECK-NEXT: .hword 8
; CHECK-NEXT: .hword 0
; CHECK-NEXT: .hword 0
-; CHECK-NEXT: .word 65535
+; CHECK-NEXT: .word -1
; SmallConstant
; CHECK-NEXT: .byte 4
; CHECK-NEXT: .byte 0
generated by cgit v1.1 at 2025-11-02 17:35:02 +0000