[llvm] [AArch64] Set predicates for FP/SIMD InstAliases (PR #79033)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Jan 22 10:46:49 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-mc
@llvm/pr-subscribers-backend-aarch64
Author: None (ostannard)
<details>
<summary>Changes</summary>
These are aliases for instructions which are are only available when the fp-armv8 or neon features are enabled, so their predicates should be set appropriately.
---
Full diff: https://github.com/llvm/llvm-project/pull/79033.diff
2 Files Affected:
- (modified) llvm/lib/Target/AArch64/AArch64InstrInfo.td (+23-1)
- (modified) llvm/test/MC/AArch64/no-fp-errors.s (+170)
``````````diff
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.td b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
index c63f23bda6805a5..cdd9ad5f7e442e8 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -3520,6 +3520,7 @@ def : InstAlias<"ldr $Rt, [$Rn, $offset]",
(LDURXi GPR64:$Rt, GPR64sp:$Rn, simm9_offset_fb64:$offset), 0>;
def : InstAlias<"ldr $Rt, [$Rn, $offset]",
(LDURWi GPR32:$Rt, GPR64sp:$Rn, simm9_offset_fb32:$offset), 0>;
+let Predicates = [HasFPARMv8] in {
def : InstAlias<"ldr $Rt, [$Rn, $offset]",
(LDURBi FPR8Op:$Rt, GPR64sp:$Rn, simm9_offset_fb8:$offset), 0>;
def : InstAlias<"ldr $Rt, [$Rn, $offset]",
@@ -3530,6 +3531,7 @@ def : InstAlias<"ldr $Rt, [$Rn, $offset]",
(LDURDi FPR64Op:$Rt, GPR64sp:$Rn, simm9_offset_fb64:$offset), 0>;
def : InstAlias<"ldr $Rt, [$Rn, $offset]",
(LDURQi FPR128Op:$Rt, GPR64sp:$Rn, simm9_offset_fb128:$offset), 0>;
+}
// zextload -> i64
def : Pat<(i64 (zextloadi8 (am_unscaled8 GPR64sp:$Rn, simm9:$offset))),
@@ -4163,6 +4165,7 @@ def : InstAlias<"str $Rt, [$Rn, $offset]",
(STURXi GPR64:$Rt, GPR64sp:$Rn, simm9_offset_fb64:$offset), 0>;
def : InstAlias<"str $Rt, [$Rn, $offset]",
(STURWi GPR32:$Rt, GPR64sp:$Rn, simm9_offset_fb32:$offset), 0>;
+let Predicates = [HasFPARMv8] in {
def : InstAlias<"str $Rt, [$Rn, $offset]",
(STURBi FPR8Op:$Rt, GPR64sp:$Rn, simm9_offset_fb8:$offset), 0>;
def : InstAlias<"str $Rt, [$Rn, $offset]",
@@ -4173,6 +4176,7 @@ def : InstAlias<"str $Rt, [$Rn, $offset]",
(STURDi FPR64Op:$Rt, GPR64sp:$Rn, simm9_offset_fb64:$offset), 0>;
def : InstAlias<"str $Rt, [$Rn, $offset]",
(STURQi FPR128Op:$Rt, GPR64sp:$Rn, simm9_offset_fb128:$offset), 0>;
+}
def : InstAlias<"strb $Rt, [$Rn, $offset]",
(STURBBi GPR32:$Rt, GPR64sp:$Rn, simm9_offset_fb8:$offset), 0>;
@@ -4583,8 +4587,10 @@ def FMOVD0 : Pseudo<(outs FPR64:$Rd), (ins), [(set f64:$Rd, (fpimm0))]>,
// Similarly add aliases
def : InstAlias<"fmov $Rd, #0.0", (FMOVWHr FPR16:$Rd, WZR), 0>,
Requires<[HasFullFP16]>;
+let Predicates = [HasFPARMv8] in {
def : InstAlias<"fmov $Rd, #0.0", (FMOVWSr FPR32:$Rd, WZR), 0>;
def : InstAlias<"fmov $Rd, #0.0", (FMOVXDr FPR64:$Rd, XZR), 0>;
+}
def : Pat<(bf16 fpimm0),
(FMOVH0)>;
@@ -5026,10 +5032,12 @@ defm NEG : SIMDTwoVectorBHSD<1, 0b01011, "neg",
UnOpFrag<(sub immAllZerosV, node:$LHS)> >;
defm NOT : SIMDTwoVectorB<1, 0b00, 0b00101, "not", vnot>;
// Aliases for MVN -> NOT.
+let Predicates = [HasNEON] in {
def : InstAlias<"mvn{ $Vd.8b, $Vn.8b|.8b $Vd, $Vn}",
(NOTv8i8 V64:$Vd, V64:$Vn)>;
def : InstAlias<"mvn{ $Vd.16b, $Vn.16b|.16b $Vd, $Vn}",
(NOTv16i8 V128:$Vd, V128:$Vn)>;
+}
def : Pat<(vnot (v4i16 V64:$Rn)), (NOTv8i8 V64:$Rn)>;
def : Pat<(vnot (v8i16 V128:$Rn)), (NOTv16i8 V128:$Rn)>;
@@ -5292,6 +5300,7 @@ def : Pat<(AArch64bsp (v4i32 V128:$Rd), V128:$Rn, V128:$Rm),
def : Pat<(AArch64bsp (v2i64 V128:$Rd), V128:$Rn, V128:$Rm),
(BSPv16i8 V128:$Rd, V128:$Rn, V128:$Rm)>;
+let Predicates = [HasNEON] in {
def : InstAlias<"mov{\t$dst.16b, $src.16b|.16b\t$dst, $src}",
(ORRv16i8 V128:$dst, V128:$src, V128:$src), 1>;
def : InstAlias<"mov{\t$dst.8h, $src.8h|.8h\t$dst, $src}",
@@ -5469,6 +5478,7 @@ def : InstAlias<"{faclt\t$dst.4s, $src1.4s, $src2.4s" #
def : InstAlias<"{faclt\t$dst.2d, $src1.2d, $src2.2d" #
"|faclt.2d\t$dst, $src1, $src2}",
(FACGTv2f64 V128:$dst, V128:$src2, V128:$src1), 0>;
+}
//===----------------------------------------------------------------------===//
// Advanced SIMD three scalar instructions.
@@ -5531,6 +5541,7 @@ defm : FMULScalarFromIndexedLane0Patterns<"FMULX", "16", "32", "64",
int_aarch64_neon_fmulx,
[HasNEONorSME]>;
+let Predicates = [HasNEON] in {
def : InstAlias<"cmls $dst, $src1, $src2",
(CMHSv1i64 FPR64:$dst, FPR64:$src2, FPR64:$src1), 0>;
def : InstAlias<"cmle $dst, $src1, $src2",
@@ -5539,6 +5550,8 @@ def : InstAlias<"cmlo $dst, $src1, $src2",
(CMHIv1i64 FPR64:$dst, FPR64:$src2, FPR64:$src1), 0>;
def : InstAlias<"cmlt $dst, $src1, $src2",
(CMGTv1i64 FPR64:$dst, FPR64:$src2, FPR64:$src1), 0>;
+}
+let Predicates = [HasFPARMv8] in {
def : InstAlias<"fcmle $dst, $src1, $src2",
(FCMGE32 FPR32:$dst, FPR32:$src2, FPR32:$src1), 0>;
def : InstAlias<"fcmle $dst, $src1, $src2",
@@ -5555,6 +5568,7 @@ def : InstAlias<"faclt $dst, $src1, $src2",
(FACGT32 FPR32:$dst, FPR32:$src2, FPR32:$src1), 0>;
def : InstAlias<"faclt $dst, $src1, $src2",
(FACGT64 FPR64:$dst, FPR64:$src2, FPR64:$src1), 0>;
+}
//===----------------------------------------------------------------------===//
// Advanced SIMD three scalar instructions (mixed operands).
@@ -7001,6 +7015,7 @@ defm BIC : SIMDModifiedImmVectorShiftTied<1, 0b11, 0b01, "bic", AArch64bici>;
// AdvSIMD ORR
defm ORR : SIMDModifiedImmVectorShiftTied<0, 0b11, 0b01, "orr", AArch64orri>;
+let Predicates = [HasNEON] in {
def : InstAlias<"bic $Vd.4h, $imm", (BICv4i16 V64:$Vd, imm0_255:$imm, 0)>;
def : InstAlias<"bic $Vd.8h, $imm", (BICv8i16 V128:$Vd, imm0_255:$imm, 0)>;
def : InstAlias<"bic $Vd.2s, $imm", (BICv2i32 V64:$Vd, imm0_255:$imm, 0)>;
@@ -7020,6 +7035,7 @@ def : InstAlias<"orr.4h $Vd, $imm", (ORRv4i16 V64:$Vd, imm0_255:$imm, 0)>;
def : InstAlias<"orr.8h $Vd, $imm", (ORRv8i16 V128:$Vd, imm0_255:$imm, 0)>;
def : InstAlias<"orr.2s $Vd, $imm", (ORRv2i32 V64:$Vd, imm0_255:$imm, 0)>;
def : InstAlias<"orr.4s $Vd, $imm", (ORRv4i32 V128:$Vd, imm0_255:$imm, 0)>;
+}
// AdvSIMD FMOV
def FMOVv2f64_ns : SIMDModifiedImmVectorNoShift<1, 1, 0, 0b1111, V128, fpimm8,
@@ -7103,6 +7119,7 @@ let Predicates = [HasNEON] in {
ssub)>;
}
+let Predicates = [HasNEON] in {
def : InstAlias<"movi $Vd.4h, $imm", (MOVIv4i16 V64:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"movi $Vd.8h, $imm", (MOVIv8i16 V128:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"movi $Vd.2s, $imm", (MOVIv2i32 V64:$Vd, imm0_255:$imm, 0), 0>;
@@ -7112,6 +7129,7 @@ def : InstAlias<"movi.4h $Vd, $imm", (MOVIv4i16 V64:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"movi.8h $Vd, $imm", (MOVIv8i16 V128:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"movi.2s $Vd, $imm", (MOVIv2i32 V64:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"movi.4s $Vd, $imm", (MOVIv4i32 V128:$Vd, imm0_255:$imm, 0), 0>;
+}
def : Pat<(v2i32 (AArch64movi_shift imm0_255:$imm8, (i32 imm:$shift))),
(MOVIv2i32 imm0_255:$imm8, imm:$shift)>;
@@ -7147,6 +7165,7 @@ def MOVIv16b_ns : SIMDModifiedImmVectorNoShift<1, 0, 0, 0b1110, V128, imm0_255,
let isReMaterializable = 1, isAsCheapAsAMove = 1 in
defm MVNI : SIMDModifiedImmVectorShift<1, 0b10, 0b00, "mvni">;
+let Predicates = [HasNEON] in {
def : InstAlias<"mvni $Vd.4h, $imm", (MVNIv4i16 V64:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"mvni $Vd.8h, $imm", (MVNIv8i16 V128:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"mvni $Vd.2s, $imm", (MVNIv2i32 V64:$Vd, imm0_255:$imm, 0), 0>;
@@ -7156,6 +7175,7 @@ def : InstAlias<"mvni.4h $Vd, $imm", (MVNIv4i16 V64:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"mvni.8h $Vd, $imm", (MVNIv8i16 V128:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"mvni.2s $Vd, $imm", (MVNIv2i32 V64:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"mvni.4s $Vd, $imm", (MVNIv4i32 V128:$Vd, imm0_255:$imm, 0), 0>;
+}
def : Pat<(v2i32 (AArch64mvni_shift imm0_255:$imm8, (i32 imm:$shift))),
(MVNIv2i32 imm0_255:$imm8, imm:$shift)>;
@@ -7643,6 +7663,7 @@ def : Pat<(v2i64 (zext (v2i32 (extract_high_v4i32 (v4i32 V128:$Rn)) ))),
def : Pat<(v2i64 (sext (v2i32 (extract_high_v4i32 (v4i32 V128:$Rn)) ))),
(SSHLLv4i32_shift V128:$Rn, (i32 0))>;
+let Predicates = [HasNEON] in {
// Vector shift sxtl aliases
def : InstAlias<"sxtl.8h $dst, $src1",
(SSHLLv8i8_shift V128:$dst, V64:$src1, 0)>;
@@ -7698,6 +7719,7 @@ def : InstAlias<"uxtl2.2d $dst, $src1",
(USHLLv4i32_shift V128:$dst, V128:$src1, 0)>;
def : InstAlias<"uxtl2 $dst.2d, $src1.4s",
(USHLLv4i32_shift V128:$dst, V128:$src1, 0)>;
+}
// If an integer is about to be converted to a floating point value,
// just load it on the floating point unit.
@@ -8146,7 +8168,7 @@ def AESIMCrr : AESInst< 0b0111, "aesimc", int_aarch64_crypto_aesimc>;
// Pseudo instructions for AESMCrr/AESIMCrr with a register constraint required
// for AES fusion on some CPUs.
-let hasSideEffects = 0, mayStore = 0, mayLoad = 0 in {
+let hasSideEffects = 0, mayStore = 0, mayLoad = 0, Predicates = [HasAES] in {
def AESMCrrTied: Pseudo<(outs V128:$Rd), (ins V128:$Rn), [], "$Rn = $Rd">,
Sched<[WriteVq]>;
def AESIMCrrTied: Pseudo<(outs V128:$Rd), (ins V128:$Rn), [], "$Rn = $Rd">,
diff --git a/llvm/test/MC/AArch64/no-fp-errors.s b/llvm/test/MC/AArch64/no-fp-errors.s
index 1595ba4798b082d..9fe3cba83e25513 100644
--- a/llvm/test/MC/AArch64/no-fp-errors.s
+++ b/llvm/test/MC/AArch64/no-fp-errors.s
@@ -191,3 +191,173 @@ label:
// CHECK: [[@LINE-1]]:7: error: expected writable system register or pstate
msr FPSR, x0
// CHECK: [[@LINE-1]]:7: error: expected writable system register or pstate
+
+ ldr s0, [x0, #1]
+// CHECK: [[@LINE-1]]:3: error: instruction requires: fp-armv8
+ str q0, [x0, #1]
+// CHECK: [[@LINE-1]]:3: error: instruction requires: fp-armv8
+
+ fmov s0, #0.0
+// CHECK: [[@LINE-1]]:3: error: instruction requires: fp-armv8
+ fmov d0, #0.0
+// CHECK: [[@LINE-1]]:3: error: instruction requires: fp-armv8
+
+ mvn v0.8b, v1.8b
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ mvn v0.16b, v1.16b
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ mov v0.16b, v1.16b
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ mov v0.8h, v1.8h
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ mov v0.4s, v1.4s
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ mov v0.2d, v1.2d
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ mov v0.8b, v1.8b
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ mov v0.4h, v1.4h
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ mov v0.2s, v1.2s
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ mov v0.1d, v1.1d
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ faclt v0.4h, v1.4h, v2.4h
+// CHECK: [[@LINE-1]]:3: error: instruction requires: fullfp16 neon
+ faclt v0.8h, v1.8h, v2.8h
+// CHECK: [[@LINE-1]]:3: error: instruction requires: fullfp16 neon
+ faclt v0.2s, v1.2s, v2.2s
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ faclt v0.4s, v1.4s, v2.4s
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ faclt v0.2d, v1.2d, v2.2d
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ cmls d0, d1, d2
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ cmle d0, d1, d2
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ cmlo d0, d1, d2
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ cmlt d0, d1, d2
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ fcmle s0, s1, s2
+// CHECK: [[@LINE-1]]:3: error: instruction requires: fp-armv8
+ fcmle d0, d1, d2
+// CHECK: [[@LINE-1]]:3: error: instruction requires: fp-armv8
+ fcmlt s0, s1, s2
+// CHECK: [[@LINE-1]]:3: error: instruction requires: fp-armv8
+ fcmlt d0, d1, d2
+// CHECK: [[@LINE-1]]:3: error: instruction requires: fp-armv8
+ facle s0, s1, s2
+// CHECK: [[@LINE-1]]:3: error: instruction requires: fp-armv8
+ facle d0, d1, d2
+// CHECK: [[@LINE-1]]:3: error: instruction requires: fp-armv8
+ faclt s0, s1, s2
+// CHECK: [[@LINE-1]]:3: error: instruction requires: fp-armv8
+ faclt d0, d1, d2
+// CHECK: [[@LINE-1]]:3: error: instruction requires: fp-armv8
+
+ bic v0.4h, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ bic v0.8h, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ bic v0.2s, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ bic v0.4s, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ bic.4h v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ bic.8h v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ bic.2s v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ bic.4s v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ orr v0.4h, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ orr v0.8h, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ orr v0.2s, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ orr v0.4s, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ orr.4h v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ orr.8h v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ orr.2s v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ orr.4s v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ movi v0.4h, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ movi v0.8h, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ movi v0.2s, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ movi v0.4s, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ movi.4h v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ movi.8h v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ movi.2s v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ movi.4s v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ mvni v0.4h, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ mvni v0.8h, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ mvni v0.2s, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ mvni v0.4s, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ mvni.4h v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ mvni.8h v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ mvni.2s v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ mvni.4s v0, #42
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ sxtl.8h v0, v1
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ sxtl.4s v0, v1
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ sxtl.2d v0, v1
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ sxtl2.8h v0, v1
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ sxtl2.4s v0, v1
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ sxtl2.2d v0, v1
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ uxtl.8h v0, v1
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ uxtl.4s v0, v1
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ uxtl.2d v0, v1
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+
+ uxtl2.8h v0, v1
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ uxtl2.4s v0, v1
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
+ uxtl2.2d v0, v1
+// CHECK: [[@LINE-1]]:3: error: instruction requires: neon
``````````
</details>
https://github.com/llvm/llvm-project/pull/79033
More information about the llvm-commits
mailing list