[AMDGPU][True16][MC][CodeGen] true16 for v_alignbyte_b32 #119750
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
broxigarchen
force-pushed
the
main-merge-true16-vop3-mc-more-instructions-9
branch
from
63323d7 to
605578f
Compare
broxigarchen
changed the title
broxigarchen
force-pushed
the
main-merge-true16-vop3-mc-more-instructions-9
branch
7 times, most recently
from
03f1efb to
6752dca
Compare
llvmbot
added
clang
|
@llvm/pr-subscribers-clang @llvm/pr-subscribers-backend-amdgpu Author: Brox Chen (broxigarchen) ChangesSupport true16 format for v_alignbyte_b32 in MC The operand type of v_alignbyte_b32 is Patch is 46.11 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/119750.diff 17 Files Affected:
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 4d4b7428abd505..4ea8c5eea15769 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -20219,6 +20219,14 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID,
Function *F = CGM.getIntrinsic(Intrinsic::fshr, Src0->getType());
return Builder.CreateCall(F, { Src0, Src1, Src2 });
}
+ case AMDGPU::BI__builtin_amdgcn_alignbyte: {
+ llvm::Value *Src0 = EmitScalarExpr(E->getArg(0));
+ llvm::Value *Src1 = EmitScalarExpr(E->getArg(1));
+ llvm::Value *Src2 = EmitScalarExpr(E->getArg(2));
+ llvm::Function *F =
+ CGM.getIntrinsic(Intrinsic::amdgcn_alignbyte, Src2->getType());
+ return Builder.CreateCall(F, {Src0, Src1, Src2});
+ }
case AMDGPU::BI__builtin_amdgcn_fence: {
ProcessOrderScopeAMDGCN(EmitScalarExpr(E->getArg(0)),
EmitScalarExpr(E->getArg(1)), AO, SSID);
diff --git a/clang/test/CodeGenOpenCL/builtins-amdgcn.cl b/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
index ded5f6b5ac4fd3..db816da45b8b35 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
@@ -734,7 +734,7 @@ kernel void test_alignbit(global uint* out, uint src0, uint src1, uint src2) {
}
// CHECK-LABEL: @test_alignbyte(
-// CHECK: tail call{{.*}} i32 @llvm.amdgcn.alignbyte(i32 %src0, i32 %src1, i32 %src2)
+// CHECK: tail call{{.*}} i32 @llvm.amdgcn.alignbyte.i32(i32 %src0, i32 %src1, i32 %src2)
kernel void test_alignbyte(global uint* out, uint src0, uint src1, uint src2) {
*out = __builtin_amdgcn_alignbyte(src0, src1, src2);
}
diff --git a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
index 92418b9104ad14..b07e90a83e8613 100644
--- a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
+++ b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
@@ -2353,8 +2353,8 @@ def int_amdgcn_writelane :
[IntrNoMem, IntrConvergent, IntrWillReturn, IntrNoCallback, IntrNoFree]
>;
-def int_amdgcn_alignbyte : ClangBuiltin<"__builtin_amdgcn_alignbyte">,
- DefaultAttrsIntrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+def int_amdgcn_alignbyte : DefaultAttrsIntrinsic<[llvm_i32_ty],
+ [llvm_i32_ty, llvm_i32_ty, llvm_anyint_ty],
[IntrNoMem, IntrSpeculatable]
>;
diff --git a/llvm/lib/Target/AMDGPU/VOP3Instructions.td b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
index 34f90b33bc4ba4..ba5da9000879ae 100644
--- a/llvm/lib/Target/AMDGPU/VOP3Instructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
@@ -212,7 +212,11 @@ defm V_BFE_U32 : VOP3Inst <"v_bfe_u32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGP
defm V_BFE_I32 : VOP3Inst <"v_bfe_i32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUbfe_i32>;
defm V_BFI_B32 : VOP3Inst <"v_bfi_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUbfi>;
defm V_ALIGNBIT_B32 : VOP3Inst <"v_alignbit_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, fshr>;
-defm V_ALIGNBYTE_B32 : VOP3Inst <"v_alignbyte_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, int_amdgcn_alignbyte>;
+defm V_ALIGNBYTE_B32 : VOP3Inst_t16_with_profiles <"v_alignbyte_b32",
+ VOP3_Profile<VOP_I32_I32_I32_I32>,
+ VOP3_Profile_True16<VOP_I32_I32_I32_I16, VOP3_OPSEL>,
+ VOP3_Profile_Fake16<VOP_I32_I32_I32_I16, VOP3_OPSEL>,
+ int_amdgcn_alignbyte>;
// XXX - No FPException seems suspect but manual doesn't say it does
let mayRaiseFPException = 0 in {
@@ -1679,7 +1683,7 @@ defm V_FMA_F32 : VOP3_Realtriple_gfx11_gfx12<0x213>;
defm V_FMA_F64 : VOP3_Real_Base_gfx11_gfx12<0x214>;
defm V_LERP_U8 : VOP3_Realtriple_gfx11_gfx12<0x215>;
defm V_ALIGNBIT_B32 : VOP3_Realtriple_gfx11_gfx12<0x216>;
-defm V_ALIGNBYTE_B32 : VOP3_Realtriple_gfx11_gfx12<0x217>;
+defm V_ALIGNBYTE_B32 : VOP3_Realtriple_t16_and_fake16_gfx11_gfx12<0x217, "v_alignbyte_b32">;
defm V_MULLIT_F32 : VOP3_Realtriple_gfx11_gfx12<0x218>;
defm V_MIN3_F32 : VOP3_Realtriple_gfx11<0x219>;
defm V_MIN3_I32 : VOP3_Realtriple_gfx11_gfx12<0x21a>;
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
index d46f010a2dafbd..1dbdb9ed5b6fda 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
@@ -461,11 +461,11 @@ v_alignbyte_b32 v5, s1, v255, s3
v_alignbyte_b32 v5, s105, s105, s105
// GFX11: v_alignbyte_b32 v5, s105, s105, s105 ; encoding: [0x05,0x00,0x17,0xd6,0x69,0xd2,0xa4,0x01]
-v_alignbyte_b32 v5, vcc_lo, ttmp15, v3
-// GFX11: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l
+// GFX11: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
-v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255
-// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l
+// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
v_alignbyte_b32 v5, ttmp15, src_scc, ttmp15
// GFX11: v_alignbyte_b32 v5, ttmp15, src_scc, ttmp15 ; encoding: [0x05,0x00,0x17,0xd6,0x7b,0xfa,0xed,0x01]
@@ -494,6 +494,9 @@ v_alignbyte_b32 v5, src_scc, vcc_lo, -1
v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null
// GFX11: v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null ; encoding: [0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h
+// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+
v_and_b16 v5.l, v1.l, v2.l
// GFX11: v_and_b16 v5.l, v1.l, v2.l ; encoding: [0x05,0x00,0x62,0xd7,0x01,0x05,0x02,0x00]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
index 36d959faa99840..64a244759870bd 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
@@ -363,22 +363,22 @@ v_alignbit_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bou
v_alignbit_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX11: v_alignbit_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x16,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[0,1,2,3]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_mirror
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_mirror row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_half_mirror
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x41,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_half_mirror row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x41,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v255 row_shl:1
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x01,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_shl:1 row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x01,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15
+v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15 row_mask:0xf bank_mask:0xf
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x0f,0x01,0xff]
v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_hi row_shr:1
@@ -387,7 +387,7 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_hi row_shr:1
v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_lo row_shr:15
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_lo row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x1f,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1
+v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1 row_mask:0xf bank_mask:0xf
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xee,0x01,0x01,0x21,0x01,0xff]
v_alignbyte_b32_e64_dpp v5, v1, v2, exec_hi row_ror:15
@@ -405,6 +405,24 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bo
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX11: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x17,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, s3 row_half_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s3 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x41,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:1
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x01,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_shl:15
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xee,0x01,0x01,0x0f,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, m0 row_ror:1
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, m0 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xf6,0x01,0x01,0x21,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h row_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0]
// GFX11: v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x62,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s
index 479bd19eaac896..87e141fa217bd0 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s
@@ -187,11 +187,11 @@ v_alignbit_b32_e64_dpp v5, v1, v2, -1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_alignbit_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX11: v_alignbit_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x16,0xd6,0xe9,0xfe,0xf7,0x03,0xff,0x00,0x00,0x00]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
v_alignbyte_b32_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0]
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05]
@@ -220,6 +220,15 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX11: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x17,0xd6,0xe9,0xfe,0xf7,0x03,0xff,0x00,0x00,0x00]
+v_alignbyte_b32_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, m0 dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xf6,0x01,0x01,0x77,0x39,0x05]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0]
// GFX11: v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x62,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s
index 62bebd00ee51f8..e3e12a14a8d989 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s
@@ -452,6 +452,9 @@ v_alignbyte_b32 v5, src_scc, vcc_lo, -1
v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null
// GFX12: v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null ; encoding: [0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h
+// GFX12: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+
v_and_b16 v5.l, v1.l, v2.l
// GFX12: v_and_b16 v5.l, v1.l, v2.l ; encoding: [0x05,0x00,0x62,0xd7,0x01,0x05,0x02,0x00]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s
index e7b12ec2deff5d..e6b40965e83c38 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s
@@ -485,6 +485,9 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bo
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX12: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x17,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h row_mirror
+// GFX12: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0]
// GFX12: v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x62,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s
index b879e59b3608b4..143505ed81fceb 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s
@@ -288,6 +288,9 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX12: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x17,0xd6,0xe9,0xfe,0xf7,0x03,0xff,0x00,0x00,0x00]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0]
// GFX12: v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x62,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt
index 857da7cd58cfb6..a756c6f4e76279 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt
@@ -508,10 +508,16 @@
# GFX11: v_alignbyte_b32 v5, s105, s105, s105 ; encoding: [0x05,0x00,0x17,0xd6,0x69,0xd2,0xa4,0x01]
0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04
-# GFX11: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W32-REAL16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W32-FAKE16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W64-REAL16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W64-FAKE16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf
-# GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W32-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W32-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
0x05,0x00,0x17,0xd6,0x7b,0xfa,0xed,0x01
# GFX11: v_alignbyte_b32 v5, ttmp15, src_scc, ttmp15 ; encoding: [0x05,0x00,0x17,0xd6,0x7b,0xfa,0xed,0x01]
@@ -540,6 +546,12 @@
0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf
# GFX11: v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null ; encoding: [0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
+0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf
+# W32-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W32-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x3...
[truncated]
|
|
@llvm/pr-subscribers-llvm-ir Author: Brox Chen (broxigarchen) ChangesSupport true16 format for v_alignbyte_b32 in MC The operand type of v_alignbyte_b32 is Patch is 46.11 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/119750.diff 17 Files Affected:
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 4d4b7428abd505..4ea8c5eea15769 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -20219,6 +20219,14 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID,
Function *F = CGM.getIntrinsic(Intrinsic::fshr, Src0->getType());
return Builder.CreateCall(F, { Src0, Src1, Src2 });
}
+ case AMDGPU::BI__builtin_amdgcn_alignbyte: {
+ llvm::Value *Src0 = EmitScalarExpr(E->getArg(0));
+ llvm::Value *Src1 = EmitScalarExpr(E->getArg(1));
+ llvm::Value *Src2 = EmitScalarExpr(E->getArg(2));
+ llvm::Function *F =
+ CGM.getIntrinsic(Intrinsic::amdgcn_alignbyte, Src2->getType());
+ return Builder.CreateCall(F, {Src0, Src1, Src2});
+ }
case AMDGPU::BI__builtin_amdgcn_fence: {
ProcessOrderScopeAMDGCN(EmitScalarExpr(E->getArg(0)),
EmitScalarExpr(E->getArg(1)), AO, SSID);
diff --git a/clang/test/CodeGenOpenCL/builtins-amdgcn.cl b/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
index ded5f6b5ac4fd3..db816da45b8b35 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
@@ -734,7 +734,7 @@ kernel void test_alignbit(global uint* out, uint src0, uint src1, uint src2) {
}
// CHECK-LABEL: @test_alignbyte(
-// CHECK: tail call{{.*}} i32 @llvm.amdgcn.alignbyte(i32 %src0, i32 %src1, i32 %src2)
+// CHECK: tail call{{.*}} i32 @llvm.amdgcn.alignbyte.i32(i32 %src0, i32 %src1, i32 %src2)
kernel void test_alignbyte(global uint* out, uint src0, uint src1, uint src2) {
*out = __builtin_amdgcn_alignbyte(src0, src1, src2);
}
diff --git a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
index 92418b9104ad14..b07e90a83e8613 100644
--- a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
+++ b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
@@ -2353,8 +2353,8 @@ def int_amdgcn_writelane :
[IntrNoMem, IntrConvergent, IntrWillReturn, IntrNoCallback, IntrNoFree]
>;
-def int_amdgcn_alignbyte : ClangBuiltin<"__builtin_amdgcn_alignbyte">,
- DefaultAttrsIntrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+def int_amdgcn_alignbyte : DefaultAttrsIntrinsic<[llvm_i32_ty],
+ [llvm_i32_ty, llvm_i32_ty, llvm_anyint_ty],
[IntrNoMem, IntrSpeculatable]
>;
diff --git a/llvm/lib/Target/AMDGPU/VOP3Instructions.td b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
index 34f90b33bc4ba4..ba5da9000879ae 100644
--- a/llvm/lib/Target/AMDGPU/VOP3Instructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
@@ -212,7 +212,11 @@ defm V_BFE_U32 : VOP3Inst <"v_bfe_u32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGP
defm V_BFE_I32 : VOP3Inst <"v_bfe_i32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUbfe_i32>;
defm V_BFI_B32 : VOP3Inst <"v_bfi_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUbfi>;
defm V_ALIGNBIT_B32 : VOP3Inst <"v_alignbit_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, fshr>;
-defm V_ALIGNBYTE_B32 : VOP3Inst <"v_alignbyte_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, int_amdgcn_alignbyte>;
+defm V_ALIGNBYTE_B32 : VOP3Inst_t16_with_profiles <"v_alignbyte_b32",
+ VOP3_Profile<VOP_I32_I32_I32_I32>,
+ VOP3_Profile_True16<VOP_I32_I32_I32_I16, VOP3_OPSEL>,
+ VOP3_Profile_Fake16<VOP_I32_I32_I32_I16, VOP3_OPSEL>,
+ int_amdgcn_alignbyte>;
// XXX - No FPException seems suspect but manual doesn't say it does
let mayRaiseFPException = 0 in {
@@ -1679,7 +1683,7 @@ defm V_FMA_F32 : VOP3_Realtriple_gfx11_gfx12<0x213>;
defm V_FMA_F64 : VOP3_Real_Base_gfx11_gfx12<0x214>;
defm V_LERP_U8 : VOP3_Realtriple_gfx11_gfx12<0x215>;
defm V_ALIGNBIT_B32 : VOP3_Realtriple_gfx11_gfx12<0x216>;
-defm V_ALIGNBYTE_B32 : VOP3_Realtriple_gfx11_gfx12<0x217>;
+defm V_ALIGNBYTE_B32 : VOP3_Realtriple_t16_and_fake16_gfx11_gfx12<0x217, "v_alignbyte_b32">;
defm V_MULLIT_F32 : VOP3_Realtriple_gfx11_gfx12<0x218>;
defm V_MIN3_F32 : VOP3_Realtriple_gfx11<0x219>;
defm V_MIN3_I32 : VOP3_Realtriple_gfx11_gfx12<0x21a>;
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
index d46f010a2dafbd..1dbdb9ed5b6fda 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
@@ -461,11 +461,11 @@ v_alignbyte_b32 v5, s1, v255, s3
v_alignbyte_b32 v5, s105, s105, s105
// GFX11: v_alignbyte_b32 v5, s105, s105, s105 ; encoding: [0x05,0x00,0x17,0xd6,0x69,0xd2,0xa4,0x01]
-v_alignbyte_b32 v5, vcc_lo, ttmp15, v3
-// GFX11: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l
+// GFX11: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
-v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255
-// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l
+// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
v_alignbyte_b32 v5, ttmp15, src_scc, ttmp15
// GFX11: v_alignbyte_b32 v5, ttmp15, src_scc, ttmp15 ; encoding: [0x05,0x00,0x17,0xd6,0x7b,0xfa,0xed,0x01]
@@ -494,6 +494,9 @@ v_alignbyte_b32 v5, src_scc, vcc_lo, -1
v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null
// GFX11: v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null ; encoding: [0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h
+// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+
v_and_b16 v5.l, v1.l, v2.l
// GFX11: v_and_b16 v5.l, v1.l, v2.l ; encoding: [0x05,0x00,0x62,0xd7,0x01,0x05,0x02,0x00]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
index 36d959faa99840..64a244759870bd 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
@@ -363,22 +363,22 @@ v_alignbit_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bou
v_alignbit_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX11: v_alignbit_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x16,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[0,1,2,3]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_mirror
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_mirror row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_half_mirror
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x41,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_half_mirror row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x41,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v255 row_shl:1
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x01,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_shl:1 row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x01,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15
+v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15 row_mask:0xf bank_mask:0xf
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x0f,0x01,0xff]
v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_hi row_shr:1
@@ -387,7 +387,7 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_hi row_shr:1
v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_lo row_shr:15
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_lo row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x1f,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1
+v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1 row_mask:0xf bank_mask:0xf
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xee,0x01,0x01,0x21,0x01,0xff]
v_alignbyte_b32_e64_dpp v5, v1, v2, exec_hi row_ror:15
@@ -405,6 +405,24 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bo
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX11: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x17,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, s3 row_half_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s3 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x41,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:1
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x01,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_shl:15
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xee,0x01,0x01,0x0f,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, m0 row_ror:1
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, m0 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xf6,0x01,0x01,0x21,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h row_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0]
// GFX11: v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x62,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s
index 479bd19eaac896..87e141fa217bd0 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s
@@ -187,11 +187,11 @@ v_alignbit_b32_e64_dpp v5, v1, v2, -1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_alignbit_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX11: v_alignbit_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x16,0xd6,0xe9,0xfe,0xf7,0x03,0xff,0x00,0x00,0x00]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
v_alignbyte_b32_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0]
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05]
@@ -220,6 +220,15 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX11: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x17,0xd6,0xe9,0xfe,0xf7,0x03,0xff,0x00,0x00,0x00]
+v_alignbyte_b32_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, m0 dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xf6,0x01,0x01,0x77,0x39,0x05]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0]
// GFX11: v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x62,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s
index 62bebd00ee51f8..e3e12a14a8d989 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s
@@ -452,6 +452,9 @@ v_alignbyte_b32 v5, src_scc, vcc_lo, -1
v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null
// GFX12: v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null ; encoding: [0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h
+// GFX12: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+
v_and_b16 v5.l, v1.l, v2.l
// GFX12: v_and_b16 v5.l, v1.l, v2.l ; encoding: [0x05,0x00,0x62,0xd7,0x01,0x05,0x02,0x00]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s
index e7b12ec2deff5d..e6b40965e83c38 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s
@@ -485,6 +485,9 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bo
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX12: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x17,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h row_mirror
+// GFX12: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0]
// GFX12: v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x62,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s
index b879e59b3608b4..143505ed81fceb 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s
@@ -288,6 +288,9 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX12: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x17,0xd6,0xe9,0xfe,0xf7,0x03,0xff,0x00,0x00,0x00]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0]
// GFX12: v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x62,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt
index 857da7cd58cfb6..a756c6f4e76279 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt
@@ -508,10 +508,16 @@
# GFX11: v_alignbyte_b32 v5, s105, s105, s105 ; encoding: [0x05,0x00,0x17,0xd6,0x69,0xd2,0xa4,0x01]
0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04
-# GFX11: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W32-REAL16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W32-FAKE16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W64-REAL16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W64-FAKE16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf
-# GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W32-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W32-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
0x05,0x00,0x17,0xd6,0x7b,0xfa,0xed,0x01
# GFX11: v_alignbyte_b32 v5, ttmp15, src_scc, ttmp15 ; encoding: [0x05,0x00,0x17,0xd6,0x7b,0xfa,0xed,0x01]
@@ -540,6 +546,12 @@
0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf
# GFX11: v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null ; encoding: [0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
+0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf
+# W32-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W32-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x3...
[truncated]
|
|
@llvm/pr-subscribers-mc Author: Brox Chen (broxigarchen) ChangesSupport true16 format for v_alignbyte_b32 in MC The operand type of v_alignbyte_b32 is Patch is 46.11 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/119750.diff 17 Files Affected:
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 4d4b7428abd505..4ea8c5eea15769 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -20219,6 +20219,14 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID,
Function *F = CGM.getIntrinsic(Intrinsic::fshr, Src0->getType());
return Builder.CreateCall(F, { Src0, Src1, Src2 });
}
+ case AMDGPU::BI__builtin_amdgcn_alignbyte: {
+ llvm::Value *Src0 = EmitScalarExpr(E->getArg(0));
+ llvm::Value *Src1 = EmitScalarExpr(E->getArg(1));
+ llvm::Value *Src2 = EmitScalarExpr(E->getArg(2));
+ llvm::Function *F =
+ CGM.getIntrinsic(Intrinsic::amdgcn_alignbyte, Src2->getType());
+ return Builder.CreateCall(F, {Src0, Src1, Src2});
+ }
case AMDGPU::BI__builtin_amdgcn_fence: {
ProcessOrderScopeAMDGCN(EmitScalarExpr(E->getArg(0)),
EmitScalarExpr(E->getArg(1)), AO, SSID);
diff --git a/clang/test/CodeGenOpenCL/builtins-amdgcn.cl b/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
index ded5f6b5ac4fd3..db816da45b8b35 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
@@ -734,7 +734,7 @@ kernel void test_alignbit(global uint* out, uint src0, uint src1, uint src2) {
}
// CHECK-LABEL: @test_alignbyte(
-// CHECK: tail call{{.*}} i32 @llvm.amdgcn.alignbyte(i32 %src0, i32 %src1, i32 %src2)
+// CHECK: tail call{{.*}} i32 @llvm.amdgcn.alignbyte.i32(i32 %src0, i32 %src1, i32 %src2)
kernel void test_alignbyte(global uint* out, uint src0, uint src1, uint src2) {
*out = __builtin_amdgcn_alignbyte(src0, src1, src2);
}
diff --git a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
index 92418b9104ad14..b07e90a83e8613 100644
--- a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
+++ b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
@@ -2353,8 +2353,8 @@ def int_amdgcn_writelane :
[IntrNoMem, IntrConvergent, IntrWillReturn, IntrNoCallback, IntrNoFree]
>;
-def int_amdgcn_alignbyte : ClangBuiltin<"__builtin_amdgcn_alignbyte">,
- DefaultAttrsIntrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+def int_amdgcn_alignbyte : DefaultAttrsIntrinsic<[llvm_i32_ty],
+ [llvm_i32_ty, llvm_i32_ty, llvm_anyint_ty],
[IntrNoMem, IntrSpeculatable]
>;
diff --git a/llvm/lib/Target/AMDGPU/VOP3Instructions.td b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
index 34f90b33bc4ba4..ba5da9000879ae 100644
--- a/llvm/lib/Target/AMDGPU/VOP3Instructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
@@ -212,7 +212,11 @@ defm V_BFE_U32 : VOP3Inst <"v_bfe_u32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGP
defm V_BFE_I32 : VOP3Inst <"v_bfe_i32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUbfe_i32>;
defm V_BFI_B32 : VOP3Inst <"v_bfi_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUbfi>;
defm V_ALIGNBIT_B32 : VOP3Inst <"v_alignbit_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, fshr>;
-defm V_ALIGNBYTE_B32 : VOP3Inst <"v_alignbyte_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, int_amdgcn_alignbyte>;
+defm V_ALIGNBYTE_B32 : VOP3Inst_t16_with_profiles <"v_alignbyte_b32",
+ VOP3_Profile<VOP_I32_I32_I32_I32>,
+ VOP3_Profile_True16<VOP_I32_I32_I32_I16, VOP3_OPSEL>,
+ VOP3_Profile_Fake16<VOP_I32_I32_I32_I16, VOP3_OPSEL>,
+ int_amdgcn_alignbyte>;
// XXX - No FPException seems suspect but manual doesn't say it does
let mayRaiseFPException = 0 in {
@@ -1679,7 +1683,7 @@ defm V_FMA_F32 : VOP3_Realtriple_gfx11_gfx12<0x213>;
defm V_FMA_F64 : VOP3_Real_Base_gfx11_gfx12<0x214>;
defm V_LERP_U8 : VOP3_Realtriple_gfx11_gfx12<0x215>;
defm V_ALIGNBIT_B32 : VOP3_Realtriple_gfx11_gfx12<0x216>;
-defm V_ALIGNBYTE_B32 : VOP3_Realtriple_gfx11_gfx12<0x217>;
+defm V_ALIGNBYTE_B32 : VOP3_Realtriple_t16_and_fake16_gfx11_gfx12<0x217, "v_alignbyte_b32">;
defm V_MULLIT_F32 : VOP3_Realtriple_gfx11_gfx12<0x218>;
defm V_MIN3_F32 : VOP3_Realtriple_gfx11<0x219>;
defm V_MIN3_I32 : VOP3_Realtriple_gfx11_gfx12<0x21a>;
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
index d46f010a2dafbd..1dbdb9ed5b6fda 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
@@ -461,11 +461,11 @@ v_alignbyte_b32 v5, s1, v255, s3
v_alignbyte_b32 v5, s105, s105, s105
// GFX11: v_alignbyte_b32 v5, s105, s105, s105 ; encoding: [0x05,0x00,0x17,0xd6,0x69,0xd2,0xa4,0x01]
-v_alignbyte_b32 v5, vcc_lo, ttmp15, v3
-// GFX11: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l
+// GFX11: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
-v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255
-// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l
+// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
v_alignbyte_b32 v5, ttmp15, src_scc, ttmp15
// GFX11: v_alignbyte_b32 v5, ttmp15, src_scc, ttmp15 ; encoding: [0x05,0x00,0x17,0xd6,0x7b,0xfa,0xed,0x01]
@@ -494,6 +494,9 @@ v_alignbyte_b32 v5, src_scc, vcc_lo, -1
v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null
// GFX11: v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null ; encoding: [0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h
+// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+
v_and_b16 v5.l, v1.l, v2.l
// GFX11: v_and_b16 v5.l, v1.l, v2.l ; encoding: [0x05,0x00,0x62,0xd7,0x01,0x05,0x02,0x00]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
index 36d959faa99840..64a244759870bd 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
@@ -363,22 +363,22 @@ v_alignbit_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bou
v_alignbit_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX11: v_alignbit_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x16,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[0,1,2,3]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_mirror
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_mirror row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_half_mirror
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x41,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_half_mirror row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x41,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v255 row_shl:1
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x01,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_shl:1 row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x01,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15
+v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15 row_mask:0xf bank_mask:0xf
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x0f,0x01,0xff]
v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_hi row_shr:1
@@ -387,7 +387,7 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_hi row_shr:1
v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_lo row_shr:15
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_lo row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x1f,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1
+v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1 row_mask:0xf bank_mask:0xf
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xee,0x01,0x01,0x21,0x01,0xff]
v_alignbyte_b32_e64_dpp v5, v1, v2, exec_hi row_ror:15
@@ -405,6 +405,24 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bo
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX11: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x17,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, s3 row_half_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s3 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x41,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:1
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x01,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_shl:15
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xee,0x01,0x01,0x0f,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, m0 row_ror:1
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, m0 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xf6,0x01,0x01,0x21,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h row_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0]
// GFX11: v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x62,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s
index 479bd19eaac896..87e141fa217bd0 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s
@@ -187,11 +187,11 @@ v_alignbit_b32_e64_dpp v5, v1, v2, -1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_alignbit_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX11: v_alignbit_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x16,0xd6,0xe9,0xfe,0xf7,0x03,0xff,0x00,0x00,0x00]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
v_alignbyte_b32_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0]
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05]
@@ -220,6 +220,15 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX11: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x17,0xd6,0xe9,0xfe,0xf7,0x03,0xff,0x00,0x00,0x00]
+v_alignbyte_b32_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, m0 dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xf6,0x01,0x01,0x77,0x39,0x05]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0]
// GFX11: v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x62,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s
index 62bebd00ee51f8..e3e12a14a8d989 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s
@@ -452,6 +452,9 @@ v_alignbyte_b32 v5, src_scc, vcc_lo, -1
v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null
// GFX12: v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null ; encoding: [0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h
+// GFX12: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+
v_and_b16 v5.l, v1.l, v2.l
// GFX12: v_and_b16 v5.l, v1.l, v2.l ; encoding: [0x05,0x00,0x62,0xd7,0x01,0x05,0x02,0x00]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s
index e7b12ec2deff5d..e6b40965e83c38 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s
@@ -485,6 +485,9 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bo
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX12: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x17,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h row_mirror
+// GFX12: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0]
// GFX12: v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x62,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s
index b879e59b3608b4..143505ed81fceb 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s
@@ -288,6 +288,9 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX12: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x17,0xd6,0xe9,0xfe,0xf7,0x03,0xff,0x00,0x00,0x00]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0]
// GFX12: v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x62,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt
index 857da7cd58cfb6..a756c6f4e76279 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt
@@ -508,10 +508,16 @@
# GFX11: v_alignbyte_b32 v5, s105, s105, s105 ; encoding: [0x05,0x00,0x17,0xd6,0x69,0xd2,0xa4,0x01]
0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04
-# GFX11: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W32-REAL16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W32-FAKE16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W64-REAL16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W64-FAKE16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf
-# GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W32-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W32-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
0x05,0x00,0x17,0xd6,0x7b,0xfa,0xed,0x01
# GFX11: v_alignbyte_b32 v5, ttmp15, src_scc, ttmp15 ; encoding: [0x05,0x00,0x17,0xd6,0x7b,0xfa,0xed,0x01]
@@ -540,6 +546,12 @@
0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf
# GFX11: v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null ; encoding: [0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
+0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf
+# W32-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W32-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x3...
[truncated]
|
|
@llvm/pr-subscribers-clang-codegen Author: Brox Chen (broxigarchen) ChangesSupport true16 format for v_alignbyte_b32 in MC The operand type of v_alignbyte_b32 is Patch is 46.11 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/119750.diff 17 Files Affected:
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 4d4b7428abd505..4ea8c5eea15769 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -20219,6 +20219,14 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID,
Function *F = CGM.getIntrinsic(Intrinsic::fshr, Src0->getType());
return Builder.CreateCall(F, { Src0, Src1, Src2 });
}
+ case AMDGPU::BI__builtin_amdgcn_alignbyte: {
+ llvm::Value *Src0 = EmitScalarExpr(E->getArg(0));
+ llvm::Value *Src1 = EmitScalarExpr(E->getArg(1));
+ llvm::Value *Src2 = EmitScalarExpr(E->getArg(2));
+ llvm::Function *F =
+ CGM.getIntrinsic(Intrinsic::amdgcn_alignbyte, Src2->getType());
+ return Builder.CreateCall(F, {Src0, Src1, Src2});
+ }
case AMDGPU::BI__builtin_amdgcn_fence: {
ProcessOrderScopeAMDGCN(EmitScalarExpr(E->getArg(0)),
EmitScalarExpr(E->getArg(1)), AO, SSID);
diff --git a/clang/test/CodeGenOpenCL/builtins-amdgcn.cl b/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
index ded5f6b5ac4fd3..db816da45b8b35 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
@@ -734,7 +734,7 @@ kernel void test_alignbit(global uint* out, uint src0, uint src1, uint src2) {
}
// CHECK-LABEL: @test_alignbyte(
-// CHECK: tail call{{.*}} i32 @llvm.amdgcn.alignbyte(i32 %src0, i32 %src1, i32 %src2)
+// CHECK: tail call{{.*}} i32 @llvm.amdgcn.alignbyte.i32(i32 %src0, i32 %src1, i32 %src2)
kernel void test_alignbyte(global uint* out, uint src0, uint src1, uint src2) {
*out = __builtin_amdgcn_alignbyte(src0, src1, src2);
}
diff --git a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
index 92418b9104ad14..b07e90a83e8613 100644
--- a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
+++ b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
@@ -2353,8 +2353,8 @@ def int_amdgcn_writelane :
[IntrNoMem, IntrConvergent, IntrWillReturn, IntrNoCallback, IntrNoFree]
>;
-def int_amdgcn_alignbyte : ClangBuiltin<"__builtin_amdgcn_alignbyte">,
- DefaultAttrsIntrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
+def int_amdgcn_alignbyte : DefaultAttrsIntrinsic<[llvm_i32_ty],
+ [llvm_i32_ty, llvm_i32_ty, llvm_anyint_ty],
[IntrNoMem, IntrSpeculatable]
>;
diff --git a/llvm/lib/Target/AMDGPU/VOP3Instructions.td b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
index 34f90b33bc4ba4..ba5da9000879ae 100644
--- a/llvm/lib/Target/AMDGPU/VOP3Instructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
@@ -212,7 +212,11 @@ defm V_BFE_U32 : VOP3Inst <"v_bfe_u32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGP
defm V_BFE_I32 : VOP3Inst <"v_bfe_i32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUbfe_i32>;
defm V_BFI_B32 : VOP3Inst <"v_bfi_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, AMDGPUbfi>;
defm V_ALIGNBIT_B32 : VOP3Inst <"v_alignbit_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, fshr>;
-defm V_ALIGNBYTE_B32 : VOP3Inst <"v_alignbyte_b32", VOP3_Profile<VOP_I32_I32_I32_I32>, int_amdgcn_alignbyte>;
+defm V_ALIGNBYTE_B32 : VOP3Inst_t16_with_profiles <"v_alignbyte_b32",
+ VOP3_Profile<VOP_I32_I32_I32_I32>,
+ VOP3_Profile_True16<VOP_I32_I32_I32_I16, VOP3_OPSEL>,
+ VOP3_Profile_Fake16<VOP_I32_I32_I32_I16, VOP3_OPSEL>,
+ int_amdgcn_alignbyte>;
// XXX - No FPException seems suspect but manual doesn't say it does
let mayRaiseFPException = 0 in {
@@ -1679,7 +1683,7 @@ defm V_FMA_F32 : VOP3_Realtriple_gfx11_gfx12<0x213>;
defm V_FMA_F64 : VOP3_Real_Base_gfx11_gfx12<0x214>;
defm V_LERP_U8 : VOP3_Realtriple_gfx11_gfx12<0x215>;
defm V_ALIGNBIT_B32 : VOP3_Realtriple_gfx11_gfx12<0x216>;
-defm V_ALIGNBYTE_B32 : VOP3_Realtriple_gfx11_gfx12<0x217>;
+defm V_ALIGNBYTE_B32 : VOP3_Realtriple_t16_and_fake16_gfx11_gfx12<0x217, "v_alignbyte_b32">;
defm V_MULLIT_F32 : VOP3_Realtriple_gfx11_gfx12<0x218>;
defm V_MIN3_F32 : VOP3_Realtriple_gfx11<0x219>;
defm V_MIN3_I32 : VOP3_Realtriple_gfx11_gfx12<0x21a>;
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
index d46f010a2dafbd..1dbdb9ed5b6fda 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
@@ -461,11 +461,11 @@ v_alignbyte_b32 v5, s1, v255, s3
v_alignbyte_b32 v5, s105, s105, s105
// GFX11: v_alignbyte_b32 v5, s105, s105, s105 ; encoding: [0x05,0x00,0x17,0xd6,0x69,0xd2,0xa4,0x01]
-v_alignbyte_b32 v5, vcc_lo, ttmp15, v3
-// GFX11: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l
+// GFX11: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
-v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255
-// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l
+// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
v_alignbyte_b32 v5, ttmp15, src_scc, ttmp15
// GFX11: v_alignbyte_b32 v5, ttmp15, src_scc, ttmp15 ; encoding: [0x05,0x00,0x17,0xd6,0x7b,0xfa,0xed,0x01]
@@ -494,6 +494,9 @@ v_alignbyte_b32 v5, src_scc, vcc_lo, -1
v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null
// GFX11: v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null ; encoding: [0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h
+// GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+
v_and_b16 v5.l, v1.l, v2.l
// GFX11: v_and_b16 v5.l, v1.l, v2.l ; encoding: [0x05,0x00,0x62,0xd7,0x01,0x05,0x02,0x00]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
index 36d959faa99840..64a244759870bd 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
@@ -363,22 +363,22 @@ v_alignbit_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bou
v_alignbit_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX11: v_alignbit_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x16,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[0,1,2,3]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_mirror
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_mirror row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_half_mirror
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x41,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_half_mirror row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x41,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v255 row_shl:1
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x01,0x01,0xff]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_shl:1 row_mask:0xf bank_mask:0xf
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x01,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15
+v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15 row_mask:0xf bank_mask:0xf
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x0f,0x01,0xff]
v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_hi row_shr:1
@@ -387,7 +387,7 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_hi row_shr:1
v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_lo row_shr:15
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, vcc_lo row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x1f,0x01,0xff]
-v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1
+v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1 row_mask:0xf bank_mask:0xf
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xee,0x01,0x01,0x21,0x01,0xff]
v_alignbyte_b32_e64_dpp v5, v1, v2, exec_hi row_ror:15
@@ -405,6 +405,24 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bo
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX11: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x17,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, s3 row_half_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s3 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0x0e,0x00,0x01,0x41,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:1
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x01,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_shl:15
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, ttmp15 row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xee,0x01,0x01,0x0f,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, m0 row_ror:1
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, m0 row_ror:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x17,0xd6,0xfa,0x04,0xf6,0x01,0x01,0x21,0x01,0xff]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h row_mirror
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0]
// GFX11: v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x62,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s
index 479bd19eaac896..87e141fa217bd0 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s
@@ -187,11 +187,11 @@ v_alignbit_b32_e64_dpp v5, v1, v2, -1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_alignbit_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX11: v_alignbit_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x16,0xd6,0xe9,0xfe,0xf7,0x03,0xff,0x00,0x00,0x00]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v3.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x04,0x01,0x77,0x39,0x05]
-v_alignbyte_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0]
-// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
v_alignbyte_b32_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0]
// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s105 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xa6,0x01,0x01,0x77,0x39,0x05]
@@ -220,6 +220,15 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX11: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x17,0xd6,0xe9,0xfe,0xf7,0x03,0xff,0x00,0x00,0x00]
+v_alignbyte_b32_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0x0e,0x00,0x01,0x77,0x39,0x05]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, m0 dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, m0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x17,0xd6,0xe9,0x04,0xf6,0x01,0x01,0x77,0x39,0x05]
+
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX11: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0]
// GFX11: v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x62,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s
index 62bebd00ee51f8..e3e12a14a8d989 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3.s
@@ -452,6 +452,9 @@ v_alignbyte_b32 v5, src_scc, vcc_lo, -1
v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null
// GFX12: v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null ; encoding: [0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
+v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h
+// GFX12: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+
v_and_b16 v5.l, v1.l, v2.l
// GFX12: v_and_b16 v5.l, v1.l, v2.l ; encoding: [0x05,0x00,0x62,0xd7,0x01,0x05,0x02,0x00]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s
index e7b12ec2deff5d..e6b40965e83c38 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s
@@ -485,6 +485,9 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 row_xmask:0 row_mask:0x1 bank_mask:0x3 bo
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX12: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x00,0x17,0xd6,0xfa,0xfe,0xf7,0x03,0xff,0x6f,0x05,0x30]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h row_mirror
+// GFX12: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x20,0x17,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x40,0x01,0xff]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0]
// GFX12: v_and_b16_e64_dpp v5.l, v1.l, v2.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x62,0xd7,0xfa,0x04,0x02,0x00,0x01,0x1b,0x00,0xff]
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s
index b879e59b3608b4..143505ed81fceb 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s
@@ -288,6 +288,9 @@ v_alignbyte_b32_e64_dpp v5, v1, v2, -1 dpp8:[7,6,5,4,3,2,1,0] fi:1
v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] fi:0
// GFX12: v_alignbyte_b32_e64_dpp v255, v255, v255, src_scc dpp8:[0,0,0,0,0,0,0,0] ; encoding: [0xff,0x00,0x17,0xd6,0xe9,0xfe,0xf7,0x03,0xff,0x00,0x00,0x00]
+v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h dpp8:[7,6,5,4,3,2,1,0]
+// GFX12: v_alignbyte_b32_e64_dpp v5, v1, v2, v255.h op_sel:[0,0,1,0] dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0xe9,0x04,0xfe,0x07,0x01,0x77,0x39,0x05]
+
v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0]
// GFX12: v_and_b16_e64_dpp v5.l, v1.l, v2.l dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x62,0xd7,0xe9,0x04,0x02,0x00,0x01,0x77,0x39,0x05]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt
index 857da7cd58cfb6..a756c6f4e76279 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt
@@ -508,10 +508,16 @@
# GFX11: v_alignbyte_b32 v5, s105, s105, s105 ; encoding: [0x05,0x00,0x17,0xd6,0x69,0xd2,0xa4,0x01]
0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04
-# GFX11: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W32-REAL16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W32-FAKE16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W64-REAL16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
+# W64-FAKE16: v_alignbyte_b32 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x17,0xd6,0x6a,0xf6,0x0c,0x04]
0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf
-# GFX11: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W32-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W32-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.l ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 ; encoding: [0x05,0x00,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
0x05,0x00,0x17,0xd6,0x7b,0xfa,0xed,0x01
# GFX11: v_alignbyte_b32 v5, ttmp15, src_scc, ttmp15 ; encoding: [0x05,0x00,0x17,0xd6,0x7b,0xfa,0xed,0x01]
@@ -540,6 +546,12 @@
0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf
# GFX11: v_alignbyte_b32 v255, 0xaf123456, vcc_hi, null ; encoding: [0xff,0x00,0x17,0xd6,0xff,0xd6,0xf0,0x01,0x56,0x34,0x12,0xaf]
+0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf
+# W32-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W32-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-REAL16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x34,0x12,0xaf]
+# W64-FAKE16: v_alignbyte_b32 v5, vcc_hi, 0xaf123456, v255 op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x17,0xd6,0x6b,0xfe,0xfd,0x07,0x56,0x3...
[truncated]
|
arsenm
reviewed
Dec 20, 2024
broxigarchen
force-pushed
the
main-merge-true16-vop3-mc-more-instructions-9
branch
from
6752dca to
da05b27
Compare
broxigarchen
force-pushed
the
main-merge-true16-vop3-mc-more-instructions-9
branch
from
da05b27 to
3681a8c
Compare
broxigarchen
changed the title
Sisyph
reviewed
Jan 30, 2025
broxigarchen
force-pushed
the
main-merge-true16-vop3-mc-more-instructions-9
branch
from
3681a8c to
f33b00d
Compare
Sisyph
reviewed
Jan 30, 2025
| ; GFX11-TRUE16-NEXT: s_waitcnt lgkmcnt(0) | ||
| ; GFX11-TRUE16-NEXT: v_mov_b16_e32 v0.l, s2 | ||
| ; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | ||
| ; GFX11-TRUE16-NEXT: v_alignbyte_b32 v0, s0, s1, v0.l |
There was a problem hiding this comment.
Nit: Can you add another test in this file where s0 and s1 are vgpr arguments instead, so we can see if s2 can be folded into src2 of alignbyte?
There was a problem hiding this comment.
Added the test. It seems still there is additional mov being generated and the s2 is not folded into src2.
I guess we might need to address the RA first?
kosarev
approved these changes
Feb 4, 2025
| @@ -1690,7 +1715,7 @@ defm V_FMA_F32 : VOP3_Realtriple_gfx11_gfx12<0x213>; | |||
| defm V_FMA_F64 : VOP3_Real_Base_gfx11_gfx12<0x214>; | |||
| defm V_LERP_U8 : VOP3_Realtriple_gfx11_gfx12<0x215>; | |||
| defm V_ALIGNBIT_B32 : VOP3_Realtriple_gfx11_gfx12<0x216>; | |||
| defm V_ALIGNBYTE_B32 : VOP3_Realtriple_gfx11_gfx12<0x217>; | |||
| defm V_ALIGNBYTE_B32 : VOP3_Realtriple_t16_and_fake16_gfx11_gfx12<0x217, "v_alignbyte_b32">; | |||
There was a problem hiding this comment.
Nit: you can do string asmName = !tolower(NAME) in the multiclass.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Support true16 format for v_alignbyte_b32 in MC and CodeGen