[llvm] [AMDGPU][wmma] - Add tied wmma intrinsic (PR #69903)
Jessica Del via llvm-commits
llvm-commits at lists.llvm.org
Mon Oct 30 04:47:27 PDT 2023
https://github.com/OutOfCache updated https://github.com/llvm/llvm-project/pull/69903
>From 2a9d431ddb7bfca5a0a9416b058a2c898b1d52d6 Mon Sep 17 00:00:00 2001
From: Jessica Del <Jessica.Del at amd.com>
Date: Tue, 5 Sep 2023 16:26:41 +0200
Subject: [PATCH] [AMDGPU/VOP3P] - Add tied wmma_f16 pseudos
Add intrinsics for `wmma_f16` and `wmma_bf16`, which stay as two-address
instructions.
This is a requirement for a future optimization
regarding wmma instructions.
The new changes make use of the `op_sel` argument of `wmma` instructions
to read from the upper halves of the input
accumulator and write to the upper halves of the output matrix.
With two-address instructions, we can guarantee that the content
of the upper halves is the same as the input
accumulator.
With three-address instructions, the output
registers do not copy the content of the input
registers. Instead, the upper halves
remain unchanged from their previous values.
This can cause issues if there are unexpected
values remaining in these registers.
For example:
```
v_wmma_f16_16x16x16_f16 v[0:7], ..., v[24:31]
v_wmma_f16_16x16x16_f16 v[32:30], ..., v[24:31]
```
After these two instructions run, there is
no guarantee that the content of bits 16-31 of
`v[0:7]` are the same as the ones from `v[24:31]`.
If we have another instruction like the following:
```
v_wmma_f16_16x16x16_f16 v[0:7], v[24:31], v[32:49], v[0:7] op_sel:[0,0,1]
```
We read from the upper halves of `v[0:7]`, but
the content is not necessarily correct.
For our purpose, we create new pseudo instructions, while maintaining
the behavior of the original instructions.
---
llvm/include/llvm/IR/IntrinsicsAMDGPU.td | 8 ++
.../Target/AMDGPU/AMDGPURegisterBankInfo.cpp | 2 +
llvm/lib/Target/AMDGPU/VOP3PInstructions.td | 44 ++++----
.../AMDGPU/GlobalISel/llvm.amdgcn.wmma_32.ll | 100 ++++++++++++++++++
.../AMDGPU/GlobalISel/llvm.amdgcn.wmma_64.ll | 84 +++++++++++++++
.../CodeGen/AMDGPU/llvm.amdgcn.wmma_32.ll | 100 ++++++++++++++++++
.../CodeGen/AMDGPU/llvm.amdgcn.wmma_64.ll | 84 +++++++++++++++
7 files changed, 404 insertions(+), 18 deletions(-)
diff --git a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
index 5f1d1d932f74cbd..89c7b6ab9ee4333 100644
--- a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
+++ b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
@@ -2361,8 +2361,16 @@ class AMDGPUWmmaIntrinsicIU<LLVMType AB, LLVMType CD> :
def int_amdgcn_wmma_f32_16x16x16_f16 : AMDGPUWmmaIntrinsic<llvm_v16f16_ty, llvm_anyfloat_ty>;
def int_amdgcn_wmma_f32_16x16x16_bf16 : AMDGPUWmmaIntrinsic<llvm_v16i16_ty, llvm_anyfloat_ty>;
+// The regular, untied f16/bf16 wmma intrinsics only write to one half
+// of the registers (set via the op_sel bit).
+// The content of the other 16-bit of the registers is undefined.
def int_amdgcn_wmma_f16_16x16x16_f16 : AMDGPUWmmaIntrinsicOPSEL<llvm_v16f16_ty, llvm_anyfloat_ty>;
def int_amdgcn_wmma_bf16_16x16x16_bf16 : AMDGPUWmmaIntrinsicOPSEL<llvm_v16i16_ty, llvm_anyint_ty>;
+// The tied versions of the f16/bf16 wmma intrinsics tie the destination matrix
+// registers to the input accumulator registers.
+// Essentially, the content of the other 16-bit is preserved from the input.
+def int_amdgcn_wmma_f16_16x16x16_f16_tied : AMDGPUWmmaIntrinsicOPSEL<llvm_v16f16_ty, llvm_anyfloat_ty>;
+def int_amdgcn_wmma_bf16_16x16x16_bf16_tied : AMDGPUWmmaIntrinsicOPSEL<llvm_v16i16_ty, llvm_anyint_ty>;
def int_amdgcn_wmma_i32_16x16x16_iu8 : AMDGPUWmmaIntrinsicIU<llvm_v4i32_ty, llvm_anyint_ty>;
def int_amdgcn_wmma_i32_16x16x16_iu4 : AMDGPUWmmaIntrinsicIU<llvm_v2i32_ty, llvm_anyint_ty>;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
index 5b056bd9e5dba2c..e409a24007a6b22 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
@@ -4279,6 +4279,8 @@ AMDGPURegisterBankInfo::getInstrMapping(const MachineInstr &MI) const {
case Intrinsic::amdgcn_sudot8:
case Intrinsic::amdgcn_wmma_bf16_16x16x16_bf16:
case Intrinsic::amdgcn_wmma_f16_16x16x16_f16:
+ case Intrinsic::amdgcn_wmma_bf16_16x16x16_bf16_tied:
+ case Intrinsic::amdgcn_wmma_f16_16x16x16_f16_tied:
case Intrinsic::amdgcn_wmma_f32_16x16x16_bf16:
case Intrinsic::amdgcn_wmma_f32_16x16x16_f16:
case Intrinsic::amdgcn_wmma_i32_16x16x16_iu4:
diff --git a/llvm/lib/Target/AMDGPU/VOP3PInstructions.td b/llvm/lib/Target/AMDGPU/VOP3PInstructions.td
index 539b69651dfedf4..3b7aa9a9998e6c9 100644
--- a/llvm/lib/Target/AMDGPU/VOP3PInstructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP3PInstructions.td
@@ -865,22 +865,26 @@ def WMMAOpcode3AddrMappingTable : WMMAMappingTable {
// it converts the default pseudo to the pseudo where src2 is not the same as vdst.
// 3) @earlyclobber on the destination satisfies the constraint during RA.
-multiclass WMMAInst<string Suffix, string Instr, VOPProfile P, SDPatternOperator node = null_frag, RegisterOperand _Src01RC64 = VRegSrc_256, WMMAType Type> {
+multiclass WMMAInst<string Suffix, string Instr, VOPProfile P, SDPatternOperator node = null_frag, RegisterOperand _Src01RC64 = VRegSrc_256, WMMAType Type, bit convertibleTo3Addr> {
defvar WMMAConstraints2Addr = "@earlyclobber $vdst,$vdst = $src2";
defvar WMMAConstraints3Addr = "@earlyclobber $vdst";
defvar WMMAProfile = VOPProfileWMMA<P, Suffix, _Src01RC64, Type.hasClamp, Type.hasOpsel>;
let Mnemonic = Instr, mayRaiseFPException = 0, ReadsModeReg = 0 in {
- let Constraints = WMMAConstraints2Addr, isConvertibleToThreeAddress = 1 in {
+ let Constraints = WMMAConstraints2Addr, isConvertibleToThreeAddress = convertibleTo3Addr in {
def _twoaddr # Suffix : VOP3P_Pseudo<Instr # Suffix, WMMAProfile>;
}
- let Constraints = WMMAConstraints3Addr, SchedRW = [Write32Bit, Write32Bit] in {
- def _threeaddr # Suffix : VOP3P_Pseudo<Instr # Suffix, WMMAProfile>;
- }
}
- def : WMMAOpcodeMapping<!cast<Instruction>(NAME # _twoaddr # Suffix),
+ if convertibleTo3Addr then {
+ let Mnemonic = Instr, mayRaiseFPException = 0, ReadsModeReg = 0 in {
+ let Constraints = WMMAConstraints3Addr, SchedRW = [Write32Bit, Write32Bit] in {
+ def _threeaddr # Suffix : VOP3P_Pseudo<Instr # Suffix, WMMAProfile>;
+ }
+ }
+ def : WMMAOpcodeMapping<!cast<Instruction>(NAME # _twoaddr # Suffix),
!cast<Instruction>(NAME # _threeaddr # Suffix)>;
+ }
if !eq(Type, WMMAOpSel) then {
def : WMMAOpSelPat<!cast<Instruction>(NAME # _twoaddr # Suffix), node, P>;
@@ -893,21 +897,25 @@ multiclass WMMAInst<string Suffix, string Instr, VOPProfile P, SDPatternOperator
let WaveSizePredicate = isWave32 in {
- defm V_WMMA_F32_16X16X16_F16 : WMMAInst<"_w32", "v_wmma_f32_16x16x16_f16", VOP_V8F32_V16F16_V16F16_V8F32, int_amdgcn_wmma_f32_16x16x16_f16, VRegSrc_256, WMMARegular>;
- defm V_WMMA_F32_16X16X16_BF16 : WMMAInst<"_w32", "v_wmma_f32_16x16x16_bf16", VOP_V8F32_V16I16_V16I16_V8F32, int_amdgcn_wmma_f32_16x16x16_bf16, VRegSrc_256, WMMARegular>;
- defm V_WMMA_F16_16X16X16_F16 : WMMAInst<"_w32", "v_wmma_f16_16x16x16_f16", VOP_V16F16_V16F16_V16F16_V16F16, int_amdgcn_wmma_f16_16x16x16_f16, VRegSrc_256, WMMAOpSel>;
- defm V_WMMA_BF16_16X16X16_BF16 : WMMAInst<"_w32", "v_wmma_bf16_16x16x16_bf16", VOP_V16I16_V16I16_V16I16_V16I16, int_amdgcn_wmma_bf16_16x16x16_bf16, VRegSrc_256, WMMAOpSel>;
- defm V_WMMA_I32_16X16X16_IU8 : WMMAInst<"_w32", "v_wmma_i32_16x16x16_iu8", VOP_V8I32_V4I32_V4I32_V8I32, int_amdgcn_wmma_i32_16x16x16_iu8, VRegSrc_128, WMMAUIClamp>;
- defm V_WMMA_I32_16X16X16_IU4 : WMMAInst<"_w32", "v_wmma_i32_16x16x16_iu4", VOP_V8I32_V2I32_V2I32_V8I32, int_amdgcn_wmma_i32_16x16x16_iu4, VRegSrc_64, WMMAUIClamp>;
+ defm V_WMMA_F32_16X16X16_F16 : WMMAInst<"_w32", "v_wmma_f32_16x16x16_f16", VOP_V8F32_V16F16_V16F16_V8F32, int_amdgcn_wmma_f32_16x16x16_f16, VRegSrc_256, WMMARegular, 1>;
+ defm V_WMMA_F32_16X16X16_BF16 : WMMAInst<"_w32", "v_wmma_f32_16x16x16_bf16", VOP_V8F32_V16I16_V16I16_V8F32, int_amdgcn_wmma_f32_16x16x16_bf16, VRegSrc_256, WMMARegular, 1>;
+ defm V_WMMA_F16_16X16X16_F16 : WMMAInst<"_w32", "v_wmma_f16_16x16x16_f16", VOP_V16F16_V16F16_V16F16_V16F16, int_amdgcn_wmma_f16_16x16x16_f16, VRegSrc_256, WMMAOpSel, 1>;
+ defm V_WMMA_BF16_16X16X16_BF16 : WMMAInst<"_w32", "v_wmma_bf16_16x16x16_bf16", VOP_V16I16_V16I16_V16I16_V16I16, int_amdgcn_wmma_bf16_16x16x16_bf16, VRegSrc_256, WMMAOpSel, 1>;
+ defm V_WMMA_F16_16X16X16_F16_TIED : WMMAInst<"_w32", "v_wmma_f16_16x16x16_f16", VOP_V16F16_V16F16_V16F16_V16F16, int_amdgcn_wmma_f16_16x16x16_f16_tied, VRegSrc_256, WMMAOpSel, 0>;
+ defm V_WMMA_BF16_16X16X16_BF16_TIED : WMMAInst<"_w32", "v_wmma_bf16_16x16x16_bf16", VOP_V16I16_V16I16_V16I16_V16I16, int_amdgcn_wmma_bf16_16x16x16_bf16_tied, VRegSrc_256, WMMAOpSel, 0>;
+ defm V_WMMA_I32_16X16X16_IU8 : WMMAInst<"_w32", "v_wmma_i32_16x16x16_iu8", VOP_V8I32_V4I32_V4I32_V8I32, int_amdgcn_wmma_i32_16x16x16_iu8, VRegSrc_128, WMMAUIClamp, 1>;
+ defm V_WMMA_I32_16X16X16_IU4 : WMMAInst<"_w32", "v_wmma_i32_16x16x16_iu4", VOP_V8I32_V2I32_V2I32_V8I32, int_amdgcn_wmma_i32_16x16x16_iu4, VRegSrc_64, WMMAUIClamp, 1>;
}
let WaveSizePredicate = isWave64 in {
- defm V_WMMA_F32_16X16X16_F16 : WMMAInst<"_w64", "v_wmma_f32_16x16x16_f16", VOP_V4F32_V16F16_V16F16_V4F32, int_amdgcn_wmma_f32_16x16x16_f16, VRegSrc_256, WMMARegular>;
- defm V_WMMA_F32_16X16X16_BF16 : WMMAInst<"_w64", "v_wmma_f32_16x16x16_bf16", VOP_V4F32_V16I16_V16I16_V4F32, int_amdgcn_wmma_f32_16x16x16_bf16, VRegSrc_256, WMMARegular>;
- defm V_WMMA_F16_16X16X16_F16 : WMMAInst<"_w64", "v_wmma_f16_16x16x16_f16", VOP_V8F16_V16F16_V16F16_V8F16, int_amdgcn_wmma_f16_16x16x16_f16, VRegSrc_256, WMMAOpSel>;
- defm V_WMMA_BF16_16X16X16_BF16 : WMMAInst<"_w64", "v_wmma_bf16_16x16x16_bf16", VOP_V8I16_V16I16_V16I16_V8I16, int_amdgcn_wmma_bf16_16x16x16_bf16, VRegSrc_256, WMMAOpSel>;
- defm V_WMMA_I32_16X16X16_IU8 : WMMAInst<"_w64", "v_wmma_i32_16x16x16_iu8", VOP_V4I32_V4I32_V4I32_V4I32, int_amdgcn_wmma_i32_16x16x16_iu8, VRegSrc_128, WMMAUIClamp>;
- defm V_WMMA_I32_16X16X16_IU4 : WMMAInst<"_w64", "v_wmma_i32_16x16x16_iu4", VOP_V4I32_V2I32_V2I32_V4I32, int_amdgcn_wmma_i32_16x16x16_iu4, VRegSrc_64, WMMAUIClamp>;
+ defm V_WMMA_F32_16X16X16_F16 : WMMAInst<"_w64", "v_wmma_f32_16x16x16_f16", VOP_V4F32_V16F16_V16F16_V4F32, int_amdgcn_wmma_f32_16x16x16_f16, VRegSrc_256, WMMARegular, 1>;
+ defm V_WMMA_F32_16X16X16_BF16 : WMMAInst<"_w64", "v_wmma_f32_16x16x16_bf16", VOP_V4F32_V16I16_V16I16_V4F32, int_amdgcn_wmma_f32_16x16x16_bf16, VRegSrc_256, WMMARegular, 1>;
+ defm V_WMMA_F16_16X16X16_F16 : WMMAInst<"_w64", "v_wmma_f16_16x16x16_f16", VOP_V8F16_V16F16_V16F16_V8F16, int_amdgcn_wmma_f16_16x16x16_f16, VRegSrc_256, WMMAOpSel, 1>;
+ defm V_WMMA_BF16_16X16X16_BF16 : WMMAInst<"_w64", "v_wmma_bf16_16x16x16_bf16", VOP_V8I16_V16I16_V16I16_V8I16, int_amdgcn_wmma_bf16_16x16x16_bf16, VRegSrc_256, WMMAOpSel, 1>;
+ defm V_WMMA_F16_16X16X16_F16_TIED : WMMAInst<"_w64", "v_wmma_f16_16x16x16_f16", VOP_V8F16_V16F16_V16F16_V8F16, int_amdgcn_wmma_f16_16x16x16_f16_tied, VRegSrc_256, WMMAOpSel, 0>;
+ defm V_WMMA_BF16_16X16X16_BF16_TIED : WMMAInst<"_w64", "v_wmma_bf16_16x16x16_bf16", VOP_V8I16_V16I16_V16I16_V8I16, int_amdgcn_wmma_bf16_16x16x16_bf16_tied, VRegSrc_256, WMMAOpSel, 0>;
+ defm V_WMMA_I32_16X16X16_IU8 : WMMAInst<"_w64", "v_wmma_i32_16x16x16_iu8", VOP_V4I32_V4I32_V4I32_V4I32, int_amdgcn_wmma_i32_16x16x16_iu8, VRegSrc_128, WMMAUIClamp, 1>;
+ defm V_WMMA_I32_16X16X16_IU4 : WMMAInst<"_w64", "v_wmma_i32_16x16x16_iu4", VOP_V4I32_V2I32_V2I32_V4I32, int_amdgcn_wmma_i32_16x16x16_iu4, VRegSrc_64, WMMAUIClamp, 1>;
}
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wmma_32.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wmma_32.ll
index 6ca2dd838d37ac9..2ddf367f0aafc20 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wmma_32.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wmma_32.ll
@@ -4,7 +4,9 @@
declare <8 x float> @llvm.amdgcn.wmma.f32.16x16x16.f16(<16 x half>, <16 x half> , <8 x float>)
declare <8 x float> @llvm.amdgcn.wmma.f32.16x16x16.bf16(<16 x i16>, <16 x i16> , <8 x float>)
declare <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16(<16 x half>, <16 x half> , <16 x half>, i1 immarg)
+declare <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.tied(<16 x half>, <16 x half> , <16 x half>, i1 immarg)
declare <16 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16(<16 x i16>, <16 x i16> , <16 x i16>, i1 immarg)
+declare <16 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16.tied(<16 x i16>, <16 x i16> , <16 x i16>, i1 immarg)
declare <8 x i32> @llvm.amdgcn.wmma.i32.16x16x16.iu8(i1 immarg, <4 x i32>, i1 immarg, <4 x i32> , <8 x i32>, i1 immarg)
declare <8 x i32> @llvm.amdgcn.wmma.i32.16x16x16.iu4(i1 immarg, <2 x i32>, i1 immarg, <2 x i32> , <8 x i32>, i1 immarg)
@@ -78,6 +80,55 @@ bb:
ret void
}
+define amdgpu_ps void @test_wmma_f16_16x16x16_f16_untied(<16 x half> %A.0, <16 x half> %B.0, <16 x half> %A.1, <16 x half> %B.1, <16 x half> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W32-LABEL: test_wmma_f16_16x16x16_f16_untied:
+; W32: ; %bb.0: ; %bb
+; W32-NEXT: v_wmma_f16_16x16x16_f16 v[44:51], v[0:7], v[8:15], v[32:39]
+; W32-NEXT: v_wmma_f16_16x16x16_f16 v[32:39], v[16:23], v[24:31], v[32:39]
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[40:41], v[44:47], off
+; W32-NEXT: global_store_b128 v[40:41], v[48:51], off offset:16
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[42:43], v[32:35], off
+; W32-NEXT: global_store_b128 v[42:43], v[36:39], off offset:16
+; W32-NEXT: s_nop 0
+; W32-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W32-NEXT: s_endpgm
+bb:
+ %res.0 = call <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16(<16 x half> %A.0, <16 x half> %B.0, <16 x half> %C, i1 0)
+ %res.1 = call <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16(<16 x half> %A.1, <16 x half> %B.1, <16 x half> %C, i1 0)
+ store <16 x half> %res.0, ptr addrspace(1) %out.0, align 32
+ store <16 x half> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
+define amdgpu_ps void @test_wmma_f16_16x16x16_f16_tied(<16 x half> %A.0, <16 x half> %B.0, <16 x half> %A.1, <16 x half> %B.1, <16 x half> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W32-LABEL: test_wmma_f16_16x16x16_f16_tied:
+; W32: ; %bb.0: ; %bb
+; W32-NEXT: v_dual_mov_b32 v51, v39 :: v_dual_mov_b32 v50, v38
+; W32-NEXT: v_dual_mov_b32 v49, v37 :: v_dual_mov_b32 v48, v36
+; W32-NEXT: v_dual_mov_b32 v47, v35 :: v_dual_mov_b32 v46, v34
+; W32-NEXT: v_dual_mov_b32 v45, v33 :: v_dual_mov_b32 v44, v32
+; W32-NEXT: v_wmma_f16_16x16x16_f16 v[32:39], v[16:23], v[24:31], v[32:39]
+; W32-NEXT: s_delay_alu instid0(VALU_DEP_2)
+; W32-NEXT: v_wmma_f16_16x16x16_f16 v[44:51], v[0:7], v[8:15], v[44:51]
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[40:41], v[44:47], off
+; W32-NEXT: global_store_b128 v[40:41], v[48:51], off offset:16
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[42:43], v[32:35], off
+; W32-NEXT: global_store_b128 v[42:43], v[36:39], off offset:16
+; W32-NEXT: s_nop 0
+; W32-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W32-NEXT: s_endpgm
+bb:
+ %res.0 = call <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.tied(<16 x half> %A.0, <16 x half> %B.0, <16 x half> %C, i1 0)
+ %res.1 = call <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.tied(<16 x half> %A.1, <16 x half> %B.1, <16 x half> %C, i1 0)
+ store <16 x half> %res.0, ptr addrspace(1) %out.0, align 32
+ store <16 x half> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
; @llvm.amdgcn.wmma.bf16.16x16x16.bf16
define amdgpu_ps void @test_wmma_bf16_16x16x16_bf16_lo(<16 x i16> %A, <16 x i16> %B, <16 x i16> %C, ptr addrspace(1) %out) {
@@ -112,6 +163,55 @@ bb:
ret void
}
+define amdgpu_ps void @test_wmma_bf16_16x16x16_bf16_untied(<16 x i16> %A.0, <16 x i16> %B.0, <16 x i16> %A.1, <16 x i16> %B.1, <16 x i16> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W32-LABEL: test_wmma_bf16_16x16x16_bf16_untied:
+; W32: ; %bb.0: ; %bb
+; W32-NEXT: v_wmma_bf16_16x16x16_bf16 v[44:51], v[0:7], v[8:15], v[32:39]
+; W32-NEXT: v_wmma_bf16_16x16x16_bf16 v[32:39], v[16:23], v[24:31], v[32:39]
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[40:41], v[44:47], off
+; W32-NEXT: global_store_b128 v[40:41], v[48:51], off offset:16
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[42:43], v[32:35], off
+; W32-NEXT: global_store_b128 v[42:43], v[36:39], off offset:16
+; W32-NEXT: s_nop 0
+; W32-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W32-NEXT: s_endpgm
+bb:
+ %res.0 = call <16 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16(<16 x i16> %A.0, <16 x i16> %B.0, <16 x i16> %C, i1 0)
+ %res.1 = call <16 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16(<16 x i16> %A.1, <16 x i16> %B.1, <16 x i16> %C, i1 0)
+ store <16 x i16> %res.0, ptr addrspace(1) %out.0, align 32
+ store <16 x i16> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
+define amdgpu_ps void @test_wmma_bf16_16x16x16_bf16_tied(<16 x i16> %A.0, <16 x i16> %B.0, <16 x i16> %A.1, <16 x i16> %B.1, <16 x i16> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W32-LABEL: test_wmma_bf16_16x16x16_bf16_tied:
+; W32: ; %bb.0: ; %bb
+; W32-NEXT: v_dual_mov_b32 v51, v39 :: v_dual_mov_b32 v50, v38
+; W32-NEXT: v_dual_mov_b32 v49, v37 :: v_dual_mov_b32 v48, v36
+; W32-NEXT: v_dual_mov_b32 v47, v35 :: v_dual_mov_b32 v46, v34
+; W32-NEXT: v_dual_mov_b32 v45, v33 :: v_dual_mov_b32 v44, v32
+; W32-NEXT: v_wmma_bf16_16x16x16_bf16 v[32:39], v[16:23], v[24:31], v[32:39]
+; W32-NEXT: s_delay_alu instid0(VALU_DEP_2)
+; W32-NEXT: v_wmma_bf16_16x16x16_bf16 v[44:51], v[0:7], v[8:15], v[44:51]
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[40:41], v[44:47], off
+; W32-NEXT: global_store_b128 v[40:41], v[48:51], off offset:16
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[42:43], v[32:35], off
+; W32-NEXT: global_store_b128 v[42:43], v[36:39], off offset:16
+; W32-NEXT: s_nop 0
+; W32-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W32-NEXT: s_endpgm
+bb:
+ %res.0 = call <16 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16.tied(<16 x i16> %A.0, <16 x i16> %B.0, <16 x i16> %C, i1 0)
+ %res.1 = call <16 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16.tied(<16 x i16> %A.1, <16 x i16> %B.1, <16 x i16> %C, i1 0)
+ store <16 x i16> %res.0, ptr addrspace(1) %out.0, align 32
+ store <16 x i16> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
; @llvm.amdgcn.wmma.i32.16x16x16.iu8
define amdgpu_ps void @test_wmma_i32_16x16x16_ui8_unsigned_unsigned(<4 x i32> %A, <4 x i32> %B, <8 x i32> %C, ptr addrspace(1) %out) {
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wmma_64.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wmma_64.ll
index a18d0a569bfb6ef..09702ae5cb608fc 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wmma_64.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wmma_64.ll
@@ -4,7 +4,9 @@
declare <4 x float> @llvm.amdgcn.wmma.f32.16x16x16.f16(<16 x half>, <16 x half>, <4 x float>)
declare <4 x float> @llvm.amdgcn.wmma.f32.16x16x16.bf16(<16 x i16>, <16 x i16>, <4 x float>)
declare <8 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16(<16 x half>, <16 x half>, <8 x half>, i1 immarg)
+declare <8 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.tied(<16 x half>, <16 x half>, <8 x half>, i1 immarg)
declare <8 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16(<16 x i16>, <16 x i16>, <8 x i16>, i1 immarg)
+declare <8 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16.tied(<16 x i16>, <16 x i16>, <8 x i16>, i1 immarg)
declare <4 x i32> @llvm.amdgcn.wmma.i32.16x16x16.iu8(i1 immarg, <4 x i32>, i1 immarg, <4 x i32>, <4 x i32>, i1 immarg)
declare <4 x i32> @llvm.amdgcn.wmma.i32.16x16x16.iu4(i1 immarg, <2 x i32>, i1 immarg, <2 x i32>, <4 x i32>, i1 immarg)
@@ -70,6 +72,47 @@ bb:
ret void
}
+define amdgpu_ps void @test_wmma_f16_16x16x16_f16_untied(<16 x half> %A.0, <16 x half> %B.0, <16 x half> %A.1, <16 x half> %B.1, <8 x half> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W64-LABEL: test_wmma_f16_16x16x16_f16_untied:
+; W64: ; %bb.0: ; %bb
+; W64-NEXT: v_wmma_f16_16x16x16_f16 v[40:43], v[0:7], v[8:15], v[32:35]
+; W64-NEXT: v_wmma_f16_16x16x16_f16 v[32:35], v[16:23], v[24:31], v[32:35]
+; W64-NEXT: global_store_b128 v[36:37], v[40:43], off
+; W64-NEXT: global_store_b128 v[38:39], v[32:35], off
+; W64-NEXT: s_nop 0
+; W64-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W64-NEXT: s_endpgm
+bb:
+ %res.0 = call <8 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16(<16 x half> %A.0, <16 x half> %B.0, <8 x half> %C, i1 0)
+ %res.1 = call <8 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16(<16 x half> %A.1, <16 x half> %B.1, <8 x half> %C, i1 0)
+ store <8 x half> %res.0, ptr addrspace(1) %out.0, align 32
+ store <8 x half> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
+define amdgpu_ps void @test_wmma_f16_16x16x16_f16_tied(<16 x half> %A.0, <16 x half> %B.0, <16 x half> %A.1, <16 x half> %B.1, <8 x half> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W64-LABEL: test_wmma_f16_16x16x16_f16_tied:
+; W64: ; %bb.0: ; %bb
+; W64-NEXT: v_mov_b32_e32 v43, v35
+; W64-NEXT: v_mov_b32_e32 v42, v34
+; W64-NEXT: v_mov_b32_e32 v41, v33
+; W64-NEXT: v_mov_b32_e32 v40, v32
+; W64-NEXT: v_wmma_f16_16x16x16_f16 v[32:35], v[16:23], v[24:31], v[32:35]
+; W64-NEXT: s_delay_alu instid0(VALU_DEP_2)
+; W64-NEXT: v_wmma_f16_16x16x16_f16 v[40:43], v[0:7], v[8:15], v[40:43]
+; W64-NEXT: global_store_b128 v[36:37], v[40:43], off
+; W64-NEXT: global_store_b128 v[38:39], v[32:35], off
+; W64-NEXT: s_nop 0
+; W64-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W64-NEXT: s_endpgm
+bb:
+ %res.0 = call <8 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.tied(<16 x half> %A.0, <16 x half> %B.0, <8 x half> %C, i1 0)
+ %res.1 = call <8 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.tied(<16 x half> %A.1, <16 x half> %B.1, <8 x half> %C, i1 0)
+ store <8 x half> %res.0, ptr addrspace(1) %out.0, align 32
+ store <8 x half> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
; @llvm.amdgcn.wmma.bf16.16x16x16.bf16
define amdgpu_ps void @test_wmma_bf16_16x16x16_bf16_lo(<16 x i16> %A, <16 x i16> %B, <8 x i16> %C, ptr addrspace(1) %out) {
@@ -100,6 +143,47 @@ bb:
ret void
}
+define amdgpu_ps void @test_wmma_bf16_16x16x16_bf16_untied(<16 x i16> %A.0, <16 x i16> %B.0, <16 x i16> %A.1, <16 x i16> %B.1, <8 x i16> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W64-LABEL: test_wmma_bf16_16x16x16_bf16_untied:
+; W64: ; %bb.0: ; %bb
+; W64-NEXT: v_wmma_bf16_16x16x16_bf16 v[40:43], v[0:7], v[8:15], v[32:35]
+; W64-NEXT: v_wmma_bf16_16x16x16_bf16 v[32:35], v[16:23], v[24:31], v[32:35]
+; W64-NEXT: global_store_b128 v[36:37], v[40:43], off
+; W64-NEXT: global_store_b128 v[38:39], v[32:35], off
+; W64-NEXT: s_nop 0
+; W64-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W64-NEXT: s_endpgm
+bb:
+ %res.0 = call <8 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16(<16 x i16> %A.0, <16 x i16> %B.0, <8 x i16> %C, i1 0)
+ %res.1 = call <8 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16(<16 x i16> %A.1, <16 x i16> %B.1, <8 x i16> %C, i1 0)
+ store <8 x i16> %res.0, ptr addrspace(1) %out.0, align 32
+ store <8 x i16> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
+define amdgpu_ps void @test_wmma_bf16_16x16x16_bf16_tied(<16 x i16> %A.0, <16 x i16> %B.0, <16 x i16> %A.1, <16 x i16> %B.1, <8 x i16> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W64-LABEL: test_wmma_bf16_16x16x16_bf16_tied:
+; W64: ; %bb.0: ; %bb
+; W64-NEXT: v_mov_b32_e32 v43, v35
+; W64-NEXT: v_mov_b32_e32 v42, v34
+; W64-NEXT: v_mov_b32_e32 v41, v33
+; W64-NEXT: v_mov_b32_e32 v40, v32
+; W64-NEXT: v_wmma_bf16_16x16x16_bf16 v[32:35], v[16:23], v[24:31], v[32:35]
+; W64-NEXT: s_delay_alu instid0(VALU_DEP_2)
+; W64-NEXT: v_wmma_bf16_16x16x16_bf16 v[40:43], v[0:7], v[8:15], v[40:43]
+; W64-NEXT: global_store_b128 v[36:37], v[40:43], off
+; W64-NEXT: global_store_b128 v[38:39], v[32:35], off
+; W64-NEXT: s_nop 0
+; W64-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W64-NEXT: s_endpgm
+bb:
+ %res.0 = call <8 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16.tied(<16 x i16> %A.0, <16 x i16> %B.0, <8 x i16> %C, i1 0)
+ %res.1 = call <8 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16.tied(<16 x i16> %A.1, <16 x i16> %B.1, <8 x i16> %C, i1 0)
+ store <8 x i16> %res.0, ptr addrspace(1) %out.0, align 32
+ store <8 x i16> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
; @llvm.amdgcn.wmma.i32.16x16x16.iu8
define amdgpu_ps void @test_wmma_i32_16x16x16_ui8_unsigned_unsigned(<4 x i32> %A, <4 x i32> %B, <4 x i32> %C, ptr addrspace(1) %out) {
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wmma_32.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wmma_32.ll
index 464c374f638c270..5076fda60a4749b 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wmma_32.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wmma_32.ll
@@ -4,7 +4,9 @@
declare <8 x float> @llvm.amdgcn.wmma.f32.16x16x16.f16(<16 x half>, <16 x half> , <8 x float>)
declare <8 x float> @llvm.amdgcn.wmma.f32.16x16x16.bf16(<16 x i16>, <16 x i16> , <8 x float>)
declare <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16(<16 x half>, <16 x half> , <16 x half>, i1 immarg)
+declare <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.tied(<16 x half>, <16 x half> , <16 x half>, i1 immarg)
declare <16 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16(<16 x i16>, <16 x i16> , <16 x i16>, i1 immarg)
+declare <16 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16.tied(<16 x i16>, <16 x i16> , <16 x i16>, i1 immarg)
declare <8 x i32> @llvm.amdgcn.wmma.i32.16x16x16.iu8(i1 immarg, <4 x i32>, i1 immarg, <4 x i32> , <8 x i32>, i1 immarg)
declare <8 x i32> @llvm.amdgcn.wmma.i32.16x16x16.iu4(i1 immarg, <2 x i32>, i1 immarg, <2 x i32> , <8 x i32>, i1 immarg)
@@ -78,6 +80,55 @@ bb:
ret void
}
+define amdgpu_ps void @test_wmma_f16_16x16x16_f16_untied(<16 x half> %A.0, <16 x half> %B.0, <16 x half> %A.1, <16 x half> %B.1, <16 x half> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W32-LABEL: test_wmma_f16_16x16x16_f16_untied:
+; W32: ; %bb.0: ; %bb
+; W32-NEXT: v_wmma_f16_16x16x16_f16 v[44:51], v[0:7], v[8:15], v[32:39]
+; W32-NEXT: v_wmma_f16_16x16x16_f16 v[32:39], v[16:23], v[24:31], v[32:39]
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[40:41], v[48:51], off offset:16
+; W32-NEXT: global_store_b128 v[40:41], v[44:47], off
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[42:43], v[36:39], off offset:16
+; W32-NEXT: global_store_b128 v[42:43], v[32:35], off
+; W32-NEXT: s_nop 0
+; W32-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W32-NEXT: s_endpgm
+bb:
+ %res.0 = call <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16(<16 x half> %A.0, <16 x half> %B.0, <16 x half> %C, i1 0)
+ %res.1 = call <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16(<16 x half> %A.1, <16 x half> %B.1, <16 x half> %C, i1 0)
+ store <16 x half> %res.0, ptr addrspace(1) %out.0, align 32
+ store <16 x half> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
+define amdgpu_ps void @test_wmma_f16_16x16x16_f16_tied(<16 x half> %A.0, <16 x half> %B.0, <16 x half> %A.1, <16 x half> %B.1, <16 x half> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W32-LABEL: test_wmma_f16_16x16x16_f16_tied:
+; W32: ; %bb.0: ; %bb
+; W32-NEXT: v_dual_mov_b32 v51, v39 :: v_dual_mov_b32 v50, v38
+; W32-NEXT: v_dual_mov_b32 v49, v37 :: v_dual_mov_b32 v48, v36
+; W32-NEXT: v_dual_mov_b32 v47, v35 :: v_dual_mov_b32 v46, v34
+; W32-NEXT: v_dual_mov_b32 v45, v33 :: v_dual_mov_b32 v44, v32
+; W32-NEXT: v_wmma_f16_16x16x16_f16 v[32:39], v[16:23], v[24:31], v[32:39]
+; W32-NEXT: s_delay_alu instid0(VALU_DEP_2)
+; W32-NEXT: v_wmma_f16_16x16x16_f16 v[44:51], v[0:7], v[8:15], v[44:51]
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[40:41], v[48:51], off offset:16
+; W32-NEXT: global_store_b128 v[40:41], v[44:47], off
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[42:43], v[36:39], off offset:16
+; W32-NEXT: global_store_b128 v[42:43], v[32:35], off
+; W32-NEXT: s_nop 0
+; W32-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W32-NEXT: s_endpgm
+bb:
+ %res.0 = call <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.tied(<16 x half> %A.0, <16 x half> %B.0, <16 x half> %C, i1 0)
+ %res.1 = call <16 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.tied(<16 x half> %A.1, <16 x half> %B.1, <16 x half> %C, i1 0)
+ store <16 x half> %res.0, ptr addrspace(1) %out.0, align 32
+ store <16 x half> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
; @llvm.amdgcn.wmma.bf16.16x16x16.bf16
define amdgpu_ps void @test_wmma_bf16_16x16x16_bf16_lo(<16 x i16> %A, <16 x i16> %B, <16 x i16> %C, ptr addrspace(1) %out) {
@@ -112,6 +163,55 @@ bb:
ret void
}
+define amdgpu_ps void @test_wmma_bf16_16x16x16_bf16_untied(<16 x i16> %A.0, <16 x i16> %B.0, <16 x i16> %A.1, <16 x i16> %B.1, <16 x i16> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W32-LABEL: test_wmma_bf16_16x16x16_bf16_untied:
+; W32: ; %bb.0: ; %bb
+; W32-NEXT: v_wmma_bf16_16x16x16_bf16 v[44:51], v[0:7], v[8:15], v[32:39]
+; W32-NEXT: v_wmma_bf16_16x16x16_bf16 v[32:39], v[16:23], v[24:31], v[32:39]
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[40:41], v[48:51], off offset:16
+; W32-NEXT: global_store_b128 v[40:41], v[44:47], off
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[42:43], v[36:39], off offset:16
+; W32-NEXT: global_store_b128 v[42:43], v[32:35], off
+; W32-NEXT: s_nop 0
+; W32-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W32-NEXT: s_endpgm
+bb:
+ %res.0 = call <16 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16(<16 x i16> %A.0, <16 x i16> %B.0, <16 x i16> %C, i1 0)
+ %res.1 = call <16 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16(<16 x i16> %A.1, <16 x i16> %B.1, <16 x i16> %C, i1 0)
+ store <16 x i16> %res.0, ptr addrspace(1) %out.0, align 32
+ store <16 x i16> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
+define amdgpu_ps void @test_wmma_bf16_16x16x16_bf16_tied(<16 x i16> %A.0, <16 x i16> %B.0, <16 x i16> %A.1, <16 x i16> %B.1, <16 x i16> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W32-LABEL: test_wmma_bf16_16x16x16_bf16_tied:
+; W32: ; %bb.0: ; %bb
+; W32-NEXT: v_dual_mov_b32 v51, v39 :: v_dual_mov_b32 v50, v38
+; W32-NEXT: v_dual_mov_b32 v49, v37 :: v_dual_mov_b32 v48, v36
+; W32-NEXT: v_dual_mov_b32 v47, v35 :: v_dual_mov_b32 v46, v34
+; W32-NEXT: v_dual_mov_b32 v45, v33 :: v_dual_mov_b32 v44, v32
+; W32-NEXT: v_wmma_bf16_16x16x16_bf16 v[32:39], v[16:23], v[24:31], v[32:39]
+; W32-NEXT: s_delay_alu instid0(VALU_DEP_2)
+; W32-NEXT: v_wmma_bf16_16x16x16_bf16 v[44:51], v[0:7], v[8:15], v[44:51]
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[40:41], v[48:51], off offset:16
+; W32-NEXT: global_store_b128 v[40:41], v[44:47], off
+; W32-NEXT: s_clause 0x1
+; W32-NEXT: global_store_b128 v[42:43], v[36:39], off offset:16
+; W32-NEXT: global_store_b128 v[42:43], v[32:35], off
+; W32-NEXT: s_nop 0
+; W32-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W32-NEXT: s_endpgm
+bb:
+ %res.0 = call <16 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16.tied(<16 x i16> %A.0, <16 x i16> %B.0, <16 x i16> %C, i1 0)
+ %res.1 = call <16 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16.tied(<16 x i16> %A.1, <16 x i16> %B.1, <16 x i16> %C, i1 0)
+ store <16 x i16> %res.0, ptr addrspace(1) %out.0, align 32
+ store <16 x i16> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
; @llvm.amdgcn.wmma.i32.16x16x16.iu8
define amdgpu_ps void @test_wmma_i32_16x16x16_ui8_unsigned_unsigned(<4 x i32> %A, <4 x i32> %B, <8 x i32> %C, ptr addrspace(1) %out) {
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wmma_64.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wmma_64.ll
index 7b1e29c18c723f0..e47a91b4fc0bac1 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wmma_64.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wmma_64.ll
@@ -4,7 +4,9 @@
declare <4 x float> @llvm.amdgcn.wmma.f32.16x16x16.f16(<16 x half>, <16 x half>, <4 x float>)
declare <4 x float> @llvm.amdgcn.wmma.f32.16x16x16.bf16(<16 x i16>, <16 x i16>, <4 x float>)
declare <8 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16(<16 x half>, <16 x half>, <8 x half>, i1 immarg)
+declare <8 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.tied(<16 x half>, <16 x half>, <8 x half>, i1 immarg)
declare <8 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16(<16 x i16>, <16 x i16>, <8 x i16>, i1 immarg)
+declare <8 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16.tied(<16 x i16>, <16 x i16>, <8 x i16>, i1 immarg)
declare <4 x i32> @llvm.amdgcn.wmma.i32.16x16x16.iu8(i1 immarg, <4 x i32>, i1 immarg, <4 x i32>, <4 x i32>, i1 immarg)
declare <4 x i32> @llvm.amdgcn.wmma.i32.16x16x16.iu4(i1 immarg, <2 x i32>, i1 immarg, <2 x i32>, <4 x i32>, i1 immarg)
@@ -70,6 +72,47 @@ bb:
ret void
}
+define amdgpu_ps void @test_wmma_f16_16x16x16_f16_untied(<16 x half> %A.0, <16 x half> %B.0, <16 x half> %A.1, <16 x half> %B.1, <8 x half> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W64-LABEL: test_wmma_f16_16x16x16_f16_untied:
+; W64: ; %bb.0: ; %bb
+; W64-NEXT: v_wmma_f16_16x16x16_f16 v[40:43], v[0:7], v[8:15], v[32:35]
+; W64-NEXT: v_wmma_f16_16x16x16_f16 v[32:35], v[16:23], v[24:31], v[32:35]
+; W64-NEXT: global_store_b128 v[36:37], v[40:43], off
+; W64-NEXT: global_store_b128 v[38:39], v[32:35], off
+; W64-NEXT: s_nop 0
+; W64-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W64-NEXT: s_endpgm
+bb:
+ %res.0 = call <8 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16(<16 x half> %A.0, <16 x half> %B.0, <8 x half> %C, i1 0)
+ %res.1 = call <8 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16(<16 x half> %A.1, <16 x half> %B.1, <8 x half> %C, i1 0)
+ store <8 x half> %res.0, ptr addrspace(1) %out.0, align 32
+ store <8 x half> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
+define amdgpu_ps void @test_wmma_f16_16x16x16_f16_tied(<16 x half> %A.0, <16 x half> %B.0, <16 x half> %A.1, <16 x half> %B.1, <8 x half> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W64-LABEL: test_wmma_f16_16x16x16_f16_tied:
+; W64: ; %bb.0: ; %bb
+; W64-NEXT: v_mov_b32_e32 v43, v35
+; W64-NEXT: v_mov_b32_e32 v42, v34
+; W64-NEXT: v_mov_b32_e32 v41, v33
+; W64-NEXT: v_mov_b32_e32 v40, v32
+; W64-NEXT: v_wmma_f16_16x16x16_f16 v[32:35], v[16:23], v[24:31], v[32:35]
+; W64-NEXT: s_delay_alu instid0(VALU_DEP_2)
+; W64-NEXT: v_wmma_f16_16x16x16_f16 v[40:43], v[0:7], v[8:15], v[40:43]
+; W64-NEXT: global_store_b128 v[36:37], v[40:43], off
+; W64-NEXT: global_store_b128 v[38:39], v[32:35], off
+; W64-NEXT: s_nop 0
+; W64-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W64-NEXT: s_endpgm
+bb:
+ %res.0 = call <8 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.tied(<16 x half> %A.0, <16 x half> %B.0, <8 x half> %C, i1 0)
+ %res.1 = call <8 x half> @llvm.amdgcn.wmma.f16.16x16x16.f16.tied(<16 x half> %A.1, <16 x half> %B.1, <8 x half> %C, i1 0)
+ store <8 x half> %res.0, ptr addrspace(1) %out.0, align 32
+ store <8 x half> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
; @llvm.amdgcn.wmma.bf16.16x16x16.bf16
define amdgpu_ps void @test_wmma_bf16_16x16x16_bf16_lo(<16 x i16> %A, <16 x i16> %B, <8 x i16> %C, ptr addrspace(1) %out) {
@@ -100,6 +143,47 @@ bb:
ret void
}
+define amdgpu_ps void @test_wmma_bf16_16x16x16_bf16_untied(<16 x i16> %A.0, <16 x i16> %B.0, <16 x i16> %A.1, <16 x i16> %B.1, <8 x i16> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W64-LABEL: test_wmma_bf16_16x16x16_bf16_untied:
+; W64: ; %bb.0: ; %bb
+; W64-NEXT: v_wmma_bf16_16x16x16_bf16 v[40:43], v[0:7], v[8:15], v[32:35]
+; W64-NEXT: v_wmma_bf16_16x16x16_bf16 v[32:35], v[16:23], v[24:31], v[32:35]
+; W64-NEXT: global_store_b128 v[36:37], v[40:43], off
+; W64-NEXT: global_store_b128 v[38:39], v[32:35], off
+; W64-NEXT: s_nop 0
+; W64-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W64-NEXT: s_endpgm
+bb:
+ %res.0 = call <8 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16(<16 x i16> %A.0, <16 x i16> %B.0, <8 x i16> %C, i1 0)
+ %res.1 = call <8 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16(<16 x i16> %A.1, <16 x i16> %B.1, <8 x i16> %C, i1 0)
+ store <8 x i16> %res.0, ptr addrspace(1) %out.0, align 32
+ store <8 x i16> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
+define amdgpu_ps void @test_wmma_bf16_16x16x16_bf16_tied(<16 x i16> %A.0, <16 x i16> %B.0, <16 x i16> %A.1, <16 x i16> %B.1, <8 x i16> %C, ptr addrspace(1) %out.0, ptr addrspace(1) %out.1) {
+; W64-LABEL: test_wmma_bf16_16x16x16_bf16_tied:
+; W64: ; %bb.0: ; %bb
+; W64-NEXT: v_mov_b32_e32 v43, v35
+; W64-NEXT: v_mov_b32_e32 v42, v34
+; W64-NEXT: v_mov_b32_e32 v41, v33
+; W64-NEXT: v_mov_b32_e32 v40, v32
+; W64-NEXT: v_wmma_bf16_16x16x16_bf16 v[32:35], v[16:23], v[24:31], v[32:35]
+; W64-NEXT: s_delay_alu instid0(VALU_DEP_2)
+; W64-NEXT: v_wmma_bf16_16x16x16_bf16 v[40:43], v[0:7], v[8:15], v[40:43]
+; W64-NEXT: global_store_b128 v[36:37], v[40:43], off
+; W64-NEXT: global_store_b128 v[38:39], v[32:35], off
+; W64-NEXT: s_nop 0
+; W64-NEXT: s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; W64-NEXT: s_endpgm
+bb:
+ %res.0 = call <8 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16.tied(<16 x i16> %A.0, <16 x i16> %B.0, <8 x i16> %C, i1 0)
+ %res.1 = call <8 x i16> @llvm.amdgcn.wmma.bf16.16x16x16.bf16.tied(<16 x i16> %A.1, <16 x i16> %B.1, <8 x i16> %C, i1 0)
+ store <8 x i16> %res.0, ptr addrspace(1) %out.0, align 32
+ store <8 x i16> %res.1, ptr addrspace(1) %out.1, align 32
+ ret void
+}
+
; @llvm.amdgcn.wmma.i32.16x16x16.iu8
define amdgpu_ps void @test_wmma_i32_16x16x16_ui8_unsigned_unsigned(<4 x i32> %A, <4 x i32> %B, <4 x i32> %C, ptr addrspace(1) %out) {
More information about the llvm-commits
mailing list