[clang] [llvm] AMDGPU: Add v_mfma_f32_16x16x32_bf16 for gfx950 (PR #117053)

Matt Arsenault via llvm-commits llvm-commits at lists.llvm.org
Thu Nov 21 09:10:15 PST 2024


https://github.com/arsenm updated https://github.com/llvm/llvm-project/pull/117053

>From 34fb85ff3e70bce36ef7f641506f388d3242fe3b Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault at amd.com>
Date: Mon, 29 Jan 2024 18:16:52 +0530
Subject: [PATCH] AMDGPU: Add v_mfma_f32_16x16x32_bf16 for gfx950

---
 .../CodeGenOpenCL/builtins-amdgcn-mfma.cl     |   7 +
 .../builtins-amdgcn-error-gfx950-param.cl     |   7 +
 .../builtins-amdgcn-error-gfx950.cl           |   1 +
 llvm/include/llvm/IR/IntrinsicsAMDGPU.td      |   2 +-
 .../Target/AMDGPU/AMDGPURegisterBankInfo.cpp  |   3 +-
 llvm/lib/Target/AMDGPU/SIInstrInfo.td         |   1 +
 llvm/lib/Target/AMDGPU/VOP3PInstructions.td   |   5 +
 .../UniformityAnalysis/AMDGPU/intrinsics.ll   |   9 +
 .../CodeGen/AMDGPU/llvm.amdgcn.mfma.gfx950.ll | 198 ++++++++++++++++++
 llvm/test/MC/AMDGPU/mai-gfx950.s              |  56 +++++
 .../MC/Disassembler/AMDGPU/gfx950_mai.txt     |  34 +++
 llvm/test/tools/llvm-mca/AMDGPU/gfx950.s      |  10 +-
 12 files changed, 328 insertions(+), 5 deletions(-)

diff --git a/clang/test/CodeGenOpenCL/builtins-amdgcn-mfma.cl b/clang/test/CodeGenOpenCL/builtins-amdgcn-mfma.cl
index 1fcd6597e2da2f..345f05f463bf44 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn-mfma.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn-mfma.cl
@@ -460,4 +460,11 @@ v16i test_mfma_i32_32x32x32_i8(v4i a, v4i b, v16i c) {
   return __builtin_amdgcn_mfma_i32_32x32x32_i8(a, b, c, 1, 2, 3);
 }
 
+// CHECK-GFX950-LABEL: @test_mfma_f32_16x16x32_bf16(
+// CHECK-GFX950: tail call <4 x float> @llvm.amdgcn.mfma.f32.16x16x32.bf16(<8 x bfloat> %a, <8 x bfloat> %b, <4 x float> %c, i32 1, i32 2, i32 3)
+v4f test_mfma_f32_16x16x32_bf16(v8bf16 a, v8bf16 b, v4f c)
+{
+  return __builtin_amdgcn_mfma_f32_16x16x32_bf16(a, b, c, 1, 2, 3);
+}
+
 #endif
diff --git a/clang/test/SemaOpenCL/builtins-amdgcn-error-gfx950-param.cl b/clang/test/SemaOpenCL/builtins-amdgcn-error-gfx950-param.cl
index 9c14c0541ff3b8..acaa20090dfcba 100644
--- a/clang/test/SemaOpenCL/builtins-amdgcn-error-gfx950-param.cl
+++ b/clang/test/SemaOpenCL/builtins-amdgcn-error-gfx950-param.cl
@@ -55,3 +55,10 @@ void test_mfma_i32_32x32x32_i8(__global int16* out, int4 a, int4 b, int16 c, int
   *out = __builtin_amdgcn_mfma_i32_32x32x32_i8(a, b, c, 0, X, 0);  // expected-error{{argument to '__builtin_amdgcn_mfma_i32_32x32x32_i8' must be a constant integer}}
   *out = __builtin_amdgcn_mfma_i32_32x32x32_i8(a, b, c, 0, 0, X);  // expected-error{{argument to '__builtin_amdgcn_mfma_i32_32x32x32_i8' must be a constant integer}}
 }
+
+void test_mfma_f32_16x16x32_bf16(__global float4* out, bfloat8 a, bfloat8 b, float4 c, int X) {
+
+  *out = __builtin_amdgcn_mfma_f32_16x16x32_bf16(a, b, c, X, 0, 0); // expected-error{{argument to '__builtin_amdgcn_mfma_f32_16x16x32_bf16' must be a constant integer}}
+  *out = __builtin_amdgcn_mfma_f32_16x16x32_bf16(a, b, c, 0, X, 0); // expected-error{{argument to '__builtin_amdgcn_mfma_f32_16x16x32_bf16' must be a constant integer}}
+  *out = __builtin_amdgcn_mfma_f32_16x16x32_bf16(a, b, c, 0, 0, X); // expected-error{{argument to '__builtin_amdgcn_mfma_f32_16x16x32_bf16' must be a constant integer}}
+}
diff --git a/clang/test/SemaOpenCL/builtins-amdgcn-error-gfx950.cl b/clang/test/SemaOpenCL/builtins-amdgcn-error-gfx950.cl
index 71a110066342cb..6bf76b3cba0f59 100644
--- a/clang/test/SemaOpenCL/builtins-amdgcn-error-gfx950.cl
+++ b/clang/test/SemaOpenCL/builtins-amdgcn-error-gfx950.cl
@@ -33,6 +33,7 @@ void test(__global float4* out0, half8 a0, half8 b0, float4 c0,
   *out2 = __builtin_amdgcn_mfma_f32_32x32x16_bf16(a2, b2, c2, 0, 0, 0); // expected-error{{'__builtin_amdgcn_mfma_f32_32x32x16_bf16' needs target feature gfx950-insts}}
   *out3 = __builtin_amdgcn_mfma_i32_16x16x64_i8(a3, b3, c3, 0, 0, 0); // expected-error{{'__builtin_amdgcn_mfma_i32_16x16x64_i8' needs target feature gfx950-insts}}
   *out4 = __builtin_amdgcn_mfma_i32_32x32x32_i8(a4, b4, c4, 0, 0, 0); // expected-error{{'__builtin_amdgcn_mfma_i32_32x32x32_i8' needs target feature gfx950-insts}}
+  *out5 = __builtin_amdgcn_mfma_f32_16x16x32_bf16(a5, b5, c5, 0, 0, 0); // expected-error{{'__builtin_amdgcn_mfma_f32_16x16x32_bf16' needs target feature gfx950-insts}}
   *out14 = __builtin_amdgcn_mfma_scale_f32_16x16x128_f8f6f4(a14, b14, c14, 0, 0, 0, d14, 0, e14); // expected-error{{'__builtin_amdgcn_mfma_scale_f32_16x16x128_f8f6f4' needs target feature gfx950-insts}}
   *out15 = __builtin_amdgcn_mfma_scale_f32_32x32x64_f8f6f4(a15, b15, c15, 0, 0, 0, d15, 0, e15); // expected-error{{'__builtin_amdgcn_mfma_scale_f32_32x32x64_f8f6f4' needs target feature gfx950-insts}}
 }
diff --git a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
index b5d5eae0c7cd7e..479120f9c202bf 100644
--- a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
+++ b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
@@ -3148,7 +3148,7 @@ def int_amdgcn_mfma_f32_16x16x32_f16 : AMDGPUMfmaIntrinsic<llvm_v4f32_ty, llvm_v
 def int_amdgcn_mfma_f32_32x32x16_f16 : AMDGPUMfmaIntrinsic<llvm_v16f32_ty, llvm_v8f16_ty>;
 def int_amdgcn_mfma_i32_16x16x64_i8 : AMDGPUMfmaIntrinsic<llvm_v4i32_ty, llvm_v4i32_ty>;
 def int_amdgcn_mfma_i32_32x32x32_i8 : AMDGPUMfmaIntrinsic<llvm_v16i32_ty, llvm_v4i32_ty>;
-
+def int_amdgcn_mfma_f32_16x16x32_bf16 : AMDGPUMfmaIntrinsic<llvm_v4f32_ty, llvm_v8bf16_ty>;
 def int_amdgcn_mfma_f32_32x32x16_bf16 : AMDGPUMfmaIntrinsic<llvm_v16f32_ty, llvm_v8bf16_ty>;
 def int_amdgcn_mfma_scale_f32_16x16x128_f8f6f4 : AMDGPUMfmaScaleIntrinsic<llvm_v4f32_ty>;
 def int_amdgcn_mfma_scale_f32_32x32x64_f8f6f4 : AMDGPUMfmaScaleIntrinsic<llvm_v16f32_ty>;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
index ea9c688c710418..4b7ba4effc6857 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
@@ -4751,7 +4751,8 @@ AMDGPURegisterBankInfo::getInstrMapping(const MachineInstr &MI) const {
     case Intrinsic::amdgcn_mfma_f32_16x16x32_f16:
     case Intrinsic::amdgcn_mfma_f32_32x32x16_f16:
     case Intrinsic::amdgcn_mfma_i32_16x16x64_i8:
-    case Intrinsic::amdgcn_mfma_i32_32x32x32_i8: {
+    case Intrinsic::amdgcn_mfma_i32_32x32x32_i8:
+    case Intrinsic::amdgcn_mfma_f32_16x16x32_bf16: {
       // Default for MAI intrinsics.
       // srcC can also be an immediate which can be folded later.
       // FIXME: Should we eventually add an alternative mapping with AGPR src
diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.td b/llvm/lib/Target/AMDGPU/SIInstrInfo.td
index 6b0c32b62176b6..05568b4f9ad1ec 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.td
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.td
@@ -2880,6 +2880,7 @@ def VOP_V16F32_V2I32_V4I32_I32    : VOPProfile <[v16f32, v2i32, v4i32, i32]>;
 def VOP_V4F32_V8F16_V8F16_V4F32   : VOPProfile <[v4f32,  v8f16, v8f16, v4f32]>;
 def VOP_V16F32_V8F16_V8F16_V16F32 : VOPProfile <[v16f32, v8f16, v8f16, v16f32]>;
 def VOP_V16F32_V8BF16_V8BF16_V16F32 : VOPProfile <[v16f32, v8bf16, v8bf16, v16f32]>;
+def VOP_V4F32_V8BF16_V8BF16_V4F32 : VOPProfile <[v4f32, v8bf16, v8bf16, v4f32]>;
 def VOP_V4F32_V8I32_V8I32_V4F32   : VOPProfile <[v4f32,  v8i32, v8i32, v4f32]>;
 
 def VOP_V4F32_V8I32_V6I32_V4F32   : VOPProfile <[v4f32,  v8i32, v6i32, v4f32]>;
diff --git a/llvm/lib/Target/AMDGPU/VOP3PInstructions.td b/llvm/lib/Target/AMDGPU/VOP3PInstructions.td
index 98d5e3f199cddd..9bd2b124f122dc 100644
--- a/llvm/lib/Target/AMDGPU/VOP3PInstructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP3PInstructions.td
@@ -645,6 +645,9 @@ def VOPProfileMAI_F32_V8F16_X16_VCD : VOPProfileMAI<VOP_V16F32_V8F16_V8F16_V16F3
 def VOPProfileMAI_F32_V8BF16_X16     : VOPProfileMAI<VOP_V16F32_V8BF16_V8BF16_V16F32,     AISrc_512_f32,  ADst_512, AVSrc_128>;
 def VOPProfileMAI_F32_V8BF16_X16_VCD : VOPProfileMAI<VOP_V16F32_V8BF16_V8BF16_V16F32,     VISrc_512_f32,  VDst_512, AVSrc_128>;
 
+def VOPProfileMAI_F32_V8BF16_X4     : VOPProfileMAI<VOP_V4F32_V8BF16_V8BF16_V4F32,     AISrc_128_f32,  ADst_128, AVSrc_128>;
+def VOPProfileMAI_F32_V8BF16_X4_VCD : VOPProfileMAI<VOP_V4F32_V8BF16_V8BF16_V4F32,     VISrc_128_f32,  VDst_128, AVSrc_128>;
+
 
 let HasAbid = false in {
 // For f32_16x16x128_f8f6f4 - f8 x f8 case
@@ -952,6 +955,7 @@ defm V_MFMA_F32_32X32X4BF16 : MAIInst<"v_mfma_f32_32x32x4bf16", "F32_V2I16_X16",
 let SubtargetPredicate = HasGFX950Insts, is_gfx940_xdl = 1 in {
 defm V_MFMA_F32_16X16X32_F16   : MAIInst<"v_mfma_f32_16x16x32f16",    "F32_V8F16_X32", int_amdgcn_mfma_f32_16x16x32_f16>;
 defm V_MFMA_F32_32X32X16_F16   : MAIInst<"v_mfma_f32_32x32x16f16",    "F32_V8F16_X16", int_amdgcn_mfma_f32_32x32x16_f16>;
+defm V_MFMA_F32_16X16X32_BF16  : MAIInst<"v_mfma_f32_16x16x32bf16",   "F32_V8BF16_X4", int_amdgcn_mfma_f32_16x16x32_bf16>;
 defm V_MFMA_I32_16X16X64_I8    : MAIInst<"v_mfma_i32_16x16x64i8",     "I32_V4I32_X128", int_amdgcn_mfma_i32_16x16x64_i8>;
 defm V_MFMA_F32_32X32X16_BF16  : MAIInst<"v_mfma_f32_32x32x16bf16",   "F32_V8BF16_X16", int_amdgcn_mfma_f32_32x32x16_bf16>;
 defm V_MFMA_I32_32X32X32_I8    : MAIInst<"v_mfma_i32_32x32x32i8",     "I32_V4I32_X16", int_amdgcn_mfma_i32_32x32x32_i8>;
@@ -2078,6 +2082,7 @@ defm V_MFMA_F64_4X4X4F64        : VOP3P_Real_MFMA_gfx90a <0x6f>;
 
 defm V_MFMA_F32_16X16X32_F16     : VOP3P_Real_MFMA_gfx950 <0x54, "v_mfma_f32_16x16x32_f16">;
 defm V_MFMA_F32_32X32X16_F16     : VOP3P_Real_MFMA_gfx950 <0x55, "v_mfma_f32_32x32x16_f16">;
+defm V_MFMA_F32_16X16X32_BF16    : VOP3P_Real_MFMA_gfx950 <0x35, "v_mfma_f32_16x16x32_bf16">;
 defm V_MFMA_I32_16X16X64_I8      : VOP3P_Real_MFMA_gfx950 <0x36, "v_mfma_i32_16x16x64_i8">;
 defm V_MFMA_F32_32X32X16_BF16    : VOP3P_Real_MFMA_gfx950 <0x37, "v_mfma_f32_32x32x16_bf16">;
 defm V_MFMA_I32_32X32X32_I8      : VOP3P_Real_MFMA_gfx950 <0x38, "v_mfma_i32_32x32x32_i8">;
diff --git a/llvm/test/Analysis/UniformityAnalysis/AMDGPU/intrinsics.ll b/llvm/test/Analysis/UniformityAnalysis/AMDGPU/intrinsics.ll
index 26021a56790aae..2d7983ebafd653 100644
--- a/llvm/test/Analysis/UniformityAnalysis/AMDGPU/intrinsics.ll
+++ b/llvm/test/Analysis/UniformityAnalysis/AMDGPU/intrinsics.ll
@@ -323,6 +323,15 @@ define amdgpu_kernel void @mfma_i32_32x32x32_i8(<4 x i32> %arg0, <4 x i32> %arg1
   ret void
 }
 
+declare <4 x float> @llvm.amdgcn.mfma.f32.16x16x32.bf16(<8 x bfloat>, <8 x bfloat>, <4 x float>, i32 immarg, i32 immarg, i32 immarg)
+
+; CHECK: DIVERGENT: %result = call <4 x float> @llvm.amdgcn.mfma.f32.16x16x32.bf16(<8 x bfloat> %arg0, <8 x bfloat> %arg1, <4 x float> %arg2, i32 immarg 0, i32 immarg 0, i32 immarg 0)
+define amdgpu_kernel void @mfma_f32_16x16x32_bf16(<8 x bfloat> %arg0, <8 x bfloat> %arg1, <4 x float> %arg2, ptr addrspace(1) %out) {
+  %result = call <4 x float> @llvm.amdgcn.mfma.f32.16x16x32.bf16(<8 x bfloat> %arg0, <8 x bfloat> %arg1, <4 x float> %arg2, i32 immarg 0, i32 immarg 0, i32 immarg 0)
+  store <4 x float> %result, ptr addrspace(1) %out
+  ret void
+}
+
 declare i32 @llvm.amdgcn.ds.swizzle(i32, i32) #1
 declare i32 @llvm.amdgcn.permlane16.i32(i32, i32, i32, i32, i1, i1) #1
 declare i32 @llvm.amdgcn.permlanex16.i32(i32, i32, i32, i32, i1, i1) #1
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.gfx950.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.gfx950.ll
index 29668b2c5bfdbf..d0ae669ffb3d68 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.gfx950.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.gfx950.ll
@@ -1315,5 +1315,203 @@ define amdgpu_kernel void @test_mfma_i32_32x32x32_i8__vgprcd_mac_flags(<4 x i32>
   ret void
 }
 
+; --------------------------------------------------------------------
+; llvm.amdgcn.mfma.f32.16x16x32.bf16
+; --------------------------------------------------------------------
+
+declare <4 x float> @llvm.amdgcn.mfma.f32.16x16x32.bf16(<8 x bfloat>, <8 x bfloat>, <4 x float>, i32 immarg, i32 immarg, i32 immarg)
+
+define <4 x float> @test_mfma_f32_16x16x32_bf16(<8 x bfloat> %arg0, <8 x bfloat> %arg1, <4 x float> %arg2) {
+; SDAG-LABEL: test_mfma_f32_16x16x32_bf16:
+; SDAG:       ; %bb.0:
+; SDAG-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; SDAG-NEXT:    v_accvgpr_write_b32 a0, v8
+; SDAG-NEXT:    v_accvgpr_write_b32 a1, v9
+; SDAG-NEXT:    v_accvgpr_write_b32 a2, v10
+; SDAG-NEXT:    v_accvgpr_write_b32 a3, v11
+; SDAG-NEXT:    s_nop 1
+; SDAG-NEXT:    v_mfma_f32_16x16x32_bf16 a[0:3], v[0:3], v[4:7], a[0:3]
+; SDAG-NEXT:    s_nop 6
+; SDAG-NEXT:    v_accvgpr_read_b32 v0, a0
+; SDAG-NEXT:    v_accvgpr_read_b32 v1, a1
+; SDAG-NEXT:    v_accvgpr_read_b32 v2, a2
+; SDAG-NEXT:    v_accvgpr_read_b32 v3, a3
+; SDAG-NEXT:    s_setpc_b64 s[30:31]
+;
+; GISEL-LABEL: test_mfma_f32_16x16x32_bf16:
+; GISEL:       ; %bb.0:
+; GISEL-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-NEXT:    v_lshrrev_b32_e32 v12, 16, v0
+; GISEL-NEXT:    v_lshrrev_b32_e32 v13, 16, v1
+; GISEL-NEXT:    v_lshrrev_b32_e32 v14, 16, v2
+; GISEL-NEXT:    v_lshrrev_b32_e32 v15, 16, v3
+; GISEL-NEXT:    v_mov_b32_sdwa v0, v12 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_mov_b32_sdwa v1, v13 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_mov_b32_sdwa v2, v14 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_mov_b32_sdwa v3, v15 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_lshrrev_b32_e32 v12, 16, v4
+; GISEL-NEXT:    v_lshrrev_b32_e32 v13, 16, v5
+; GISEL-NEXT:    v_lshrrev_b32_e32 v14, 16, v6
+; GISEL-NEXT:    v_lshrrev_b32_e32 v15, 16, v7
+; GISEL-NEXT:    v_accvgpr_write_b32 a0, v8
+; GISEL-NEXT:    v_mov_b32_sdwa v4, v12 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_mov_b32_sdwa v5, v13 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_mov_b32_sdwa v6, v14 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_mov_b32_sdwa v7, v15 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_accvgpr_write_b32 a1, v9
+; GISEL-NEXT:    v_accvgpr_write_b32 a2, v10
+; GISEL-NEXT:    v_accvgpr_write_b32 a3, v11
+; GISEL-NEXT:    s_nop 1
+; GISEL-NEXT:    v_mfma_f32_16x16x32_bf16 a[0:3], v[0:3], v[4:7], a[0:3]
+; GISEL-NEXT:    s_nop 6
+; GISEL-NEXT:    v_accvgpr_read_b32 v0, a0
+; GISEL-NEXT:    v_accvgpr_read_b32 v1, a1
+; GISEL-NEXT:    v_accvgpr_read_b32 v2, a2
+; GISEL-NEXT:    v_accvgpr_read_b32 v3, a3
+; GISEL-NEXT:    s_setpc_b64 s[30:31]
+  %result = call <4 x float> @llvm.amdgcn.mfma.f32.16x16x32.bf16(<8 x bfloat> %arg0, <8 x bfloat> %arg1, <4 x float> %arg2, i32 0, i32 0, i32 0)
+  ret <4 x float> %result
+}
+
+define <4 x float> @test_mfma_f32_16x16x32_bf16__flags(<8 x bfloat> %arg0, <8 x bfloat> %arg1, <4 x float> %arg2) {
+; SDAG-LABEL: test_mfma_f32_16x16x32_bf16__flags:
+; SDAG:       ; %bb.0:
+; SDAG-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; SDAG-NEXT:    v_accvgpr_write_b32 a0, v8
+; SDAG-NEXT:    v_accvgpr_write_b32 a1, v9
+; SDAG-NEXT:    v_accvgpr_write_b32 a2, v10
+; SDAG-NEXT:    v_accvgpr_write_b32 a3, v11
+; SDAG-NEXT:    s_nop 1
+; SDAG-NEXT:    v_mfma_f32_16x16x32_bf16 a[0:3], v[0:3], v[4:7], a[0:3] cbsz:1 abid:1 blgp:1
+; SDAG-NEXT:    s_nop 6
+; SDAG-NEXT:    v_accvgpr_read_b32 v0, a0
+; SDAG-NEXT:    v_accvgpr_read_b32 v1, a1
+; SDAG-NEXT:    v_accvgpr_read_b32 v2, a2
+; SDAG-NEXT:    v_accvgpr_read_b32 v3, a3
+; SDAG-NEXT:    s_setpc_b64 s[30:31]
+;
+; GISEL-LABEL: test_mfma_f32_16x16x32_bf16__flags:
+; GISEL:       ; %bb.0:
+; GISEL-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-NEXT:    v_lshrrev_b32_e32 v12, 16, v0
+; GISEL-NEXT:    v_lshrrev_b32_e32 v13, 16, v1
+; GISEL-NEXT:    v_lshrrev_b32_e32 v14, 16, v2
+; GISEL-NEXT:    v_lshrrev_b32_e32 v15, 16, v3
+; GISEL-NEXT:    v_mov_b32_sdwa v0, v12 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_mov_b32_sdwa v1, v13 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_mov_b32_sdwa v2, v14 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_mov_b32_sdwa v3, v15 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_lshrrev_b32_e32 v12, 16, v4
+; GISEL-NEXT:    v_lshrrev_b32_e32 v13, 16, v5
+; GISEL-NEXT:    v_lshrrev_b32_e32 v14, 16, v6
+; GISEL-NEXT:    v_lshrrev_b32_e32 v15, 16, v7
+; GISEL-NEXT:    v_accvgpr_write_b32 a0, v8
+; GISEL-NEXT:    v_mov_b32_sdwa v4, v12 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_mov_b32_sdwa v5, v13 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_mov_b32_sdwa v6, v14 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_mov_b32_sdwa v7, v15 dst_sel:WORD_1 dst_unused:UNUSED_PRESERVE src0_sel:WORD_0
+; GISEL-NEXT:    v_accvgpr_write_b32 a1, v9
+; GISEL-NEXT:    v_accvgpr_write_b32 a2, v10
+; GISEL-NEXT:    v_accvgpr_write_b32 a3, v11
+; GISEL-NEXT:    s_nop 1
+; GISEL-NEXT:    v_mfma_f32_16x16x32_bf16 a[0:3], v[0:3], v[4:7], a[0:3] cbsz:1 abid:1 blgp:1
+; GISEL-NEXT:    s_nop 6
+; GISEL-NEXT:    v_accvgpr_read_b32 v0, a0
+; GISEL-NEXT:    v_accvgpr_read_b32 v1, a1
+; GISEL-NEXT:    v_accvgpr_read_b32 v2, a2
+; GISEL-NEXT:    v_accvgpr_read_b32 v3, a3
+; GISEL-NEXT:    s_setpc_b64 s[30:31]
+  %result = call <4 x float> @llvm.amdgcn.mfma.f32.16x16x32.bf16(<8 x bfloat> %arg0, <8 x bfloat> %arg1, <4 x float> %arg2, i32 1, i32 1, i32 1)
+  ret <4 x float> %result
+}
+
+define amdgpu_kernel void @test_mfma_f32_16x16x32_bf16_no_agpr__vgprcd(ptr addrspace(1) %out, <8 x bfloat> %arg0, <8 x bfloat> %arg1, <4 x float> %arg2) #0 {
+; SDAG-LABEL: test_mfma_f32_16x16x32_bf16_no_agpr__vgprcd:
+; SDAG:       ; %bb.0:
+; SDAG-NEXT:    s_load_dwordx8 s[4:11], s[0:1], 0x34
+; SDAG-NEXT:    s_load_dwordx4 s[12:15], s[0:1], 0x54
+; SDAG-NEXT:    v_mov_b32_e32 v12, 0
+; SDAG-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0x24
+; SDAG-NEXT:    s_waitcnt lgkmcnt(0)
+; SDAG-NEXT:    v_mov_b64_e32 v[0:1], s[4:5]
+; SDAG-NEXT:    v_mov_b64_e32 v[2:3], s[6:7]
+; SDAG-NEXT:    v_mov_b64_e32 v[4:5], s[8:9]
+; SDAG-NEXT:    v_mov_b64_e32 v[8:9], s[12:13]
+; SDAG-NEXT:    v_mov_b64_e32 v[6:7], s[10:11]
+; SDAG-NEXT:    v_mov_b64_e32 v[10:11], s[14:15]
+; SDAG-NEXT:    s_nop 1
+; SDAG-NEXT:    v_mfma_f32_16x16x32_bf16 v[0:3], v[0:3], v[4:7], v[8:11]
+; SDAG-NEXT:    s_nop 6
+; SDAG-NEXT:    global_store_dwordx4 v12, v[0:3], s[0:1]
+; SDAG-NEXT:    s_endpgm
+;
+; GISEL-LABEL: test_mfma_f32_16x16x32_bf16_no_agpr__vgprcd:
+; GISEL:       ; %bb.0:
+; GISEL-NEXT:    s_load_dwordx8 s[4:11], s[0:1], 0x34
+; GISEL-NEXT:    s_load_dwordx4 s[12:15], s[0:1], 0x54
+; GISEL-NEXT:    s_waitcnt lgkmcnt(0)
+; GISEL-NEXT:    v_mov_b64_e32 v[0:1], s[4:5]
+; GISEL-NEXT:    v_mov_b64_e32 v[2:3], s[6:7]
+; GISEL-NEXT:    v_mov_b64_e32 v[4:5], s[8:9]
+; GISEL-NEXT:    v_mov_b64_e32 v[8:9], s[12:13]
+; GISEL-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0x24
+; GISEL-NEXT:    v_mov_b64_e32 v[6:7], s[10:11]
+; GISEL-NEXT:    v_mov_b64_e32 v[10:11], s[14:15]
+; GISEL-NEXT:    s_nop 1
+; GISEL-NEXT:    v_mfma_f32_16x16x32_bf16 v[0:3], v[0:3], v[4:7], v[8:11]
+; GISEL-NEXT:    v_mov_b32_e32 v4, 0
+; GISEL-NEXT:    s_waitcnt lgkmcnt(0)
+; GISEL-NEXT:    s_nop 4
+; GISEL-NEXT:    global_store_dwordx4 v4, v[0:3], s[0:1]
+; GISEL-NEXT:    s_endpgm
+  %result = call <4 x float> @llvm.amdgcn.mfma.f32.16x16x32.bf16(<8 x bfloat> %arg0, <8 x bfloat> %arg1, <4 x float> %arg2, i32 0, i32 0, i32 0)
+  store <4 x float> %result, ptr addrspace(1) %out
+  ret void
+}
+
+define amdgpu_kernel void @test_mfma_f32_16x16x32_bf16_no_agpr__vgprcd__flags(ptr addrspace(1) %out, <8 x bfloat> %arg0, <8 x bfloat> %arg1, <4 x float> %arg2) #0 {
+; SDAG-LABEL: test_mfma_f32_16x16x32_bf16_no_agpr__vgprcd__flags:
+; SDAG:       ; %bb.0:
+; SDAG-NEXT:    s_load_dwordx8 s[4:11], s[0:1], 0x34
+; SDAG-NEXT:    s_load_dwordx4 s[12:15], s[0:1], 0x54
+; SDAG-NEXT:    v_mov_b32_e32 v12, 0
+; SDAG-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0x24
+; SDAG-NEXT:    s_waitcnt lgkmcnt(0)
+; SDAG-NEXT:    v_mov_b64_e32 v[0:1], s[4:5]
+; SDAG-NEXT:    v_mov_b64_e32 v[2:3], s[6:7]
+; SDAG-NEXT:    v_mov_b64_e32 v[4:5], s[8:9]
+; SDAG-NEXT:    v_mov_b64_e32 v[8:9], s[12:13]
+; SDAG-NEXT:    v_mov_b64_e32 v[6:7], s[10:11]
+; SDAG-NEXT:    v_mov_b64_e32 v[10:11], s[14:15]
+; SDAG-NEXT:    s_nop 1
+; SDAG-NEXT:    v_mfma_f32_16x16x32_bf16 v[0:3], v[0:3], v[4:7], v[8:11] cbsz:3 abid:2 blgp:1
+; SDAG-NEXT:    s_nop 6
+; SDAG-NEXT:    global_store_dwordx4 v12, v[0:3], s[0:1]
+; SDAG-NEXT:    s_endpgm
+;
+; GISEL-LABEL: test_mfma_f32_16x16x32_bf16_no_agpr__vgprcd__flags:
+; GISEL:       ; %bb.0:
+; GISEL-NEXT:    s_load_dwordx8 s[4:11], s[0:1], 0x34
+; GISEL-NEXT:    s_load_dwordx4 s[12:15], s[0:1], 0x54
+; GISEL-NEXT:    s_waitcnt lgkmcnt(0)
+; GISEL-NEXT:    v_mov_b64_e32 v[0:1], s[4:5]
+; GISEL-NEXT:    v_mov_b64_e32 v[2:3], s[6:7]
+; GISEL-NEXT:    v_mov_b64_e32 v[4:5], s[8:9]
+; GISEL-NEXT:    v_mov_b64_e32 v[8:9], s[12:13]
+; GISEL-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0x24
+; GISEL-NEXT:    v_mov_b64_e32 v[6:7], s[10:11]
+; GISEL-NEXT:    v_mov_b64_e32 v[10:11], s[14:15]
+; GISEL-NEXT:    s_nop 1
+; GISEL-NEXT:    v_mfma_f32_16x16x32_bf16 v[0:3], v[0:3], v[4:7], v[8:11] cbsz:3 abid:2 blgp:1
+; GISEL-NEXT:    v_mov_b32_e32 v4, 0
+; GISEL-NEXT:    s_waitcnt lgkmcnt(0)
+; GISEL-NEXT:    s_nop 4
+; GISEL-NEXT:    global_store_dwordx4 v4, v[0:3], s[0:1]
+; GISEL-NEXT:    s_endpgm
+  %result = call <4 x float> @llvm.amdgcn.mfma.f32.16x16x32.bf16(<8 x bfloat> %arg0, <8 x bfloat> %arg1, <4 x float> %arg2, i32 3, i32 2, i32 1)
+  store <4 x float> %result, ptr addrspace(1) %out
+  ret void
+}
+
 attributes #0 = { "amdgpu-flat-work-group-size"="512,512" }
 attributes #1 = { "amdgpu-flat-work-group-size"="1,64" }
diff --git a/llvm/test/MC/AMDGPU/mai-gfx950.s b/llvm/test/MC/AMDGPU/mai-gfx950.s
index a2ea2ff6f68d0d..919e0a296f7bb2 100644
--- a/llvm/test/MC/AMDGPU/mai-gfx950.s
+++ b/llvm/test/MC/AMDGPU/mai-gfx950.s
@@ -994,3 +994,59 @@ v_mfma_i32_32x32x32_i8 v[0:15], v[0:3], v[0:3], v[0:15] abid:1
 // GFX950: v_mfma_i32_32x32x32_i8 a[0:15], a[0:3], a[0:3], a[0:15] cbsz:3 abid:1 ; encoding: [0x00,0x8b,0xb8,0xd3,0x00,0x01,0x02,0x1c]
 // ERR: :[[@LINE+1]]:{{[0-9]+}}: error: instruction not supported on this GPU
 v_mfma_i32_32x32x32_i8 a[0:15], a[0:3], a[0:3], a[0:15] cbsz:3 abid:1
+
+//===----------------------------------------------------------------------===//
+// v_mfma_f32_16x16x32_bf16
+//===----------------------------------------------------------------------===//
+
+// GFX950: v_mfma_f32_16x16x32_bf16 v[0:3], v[0:3], v[0:3], v[0:3] ; encoding: [0x00,0x00,0xb5,0xd3,0x00,0x01,0x02,0x04]
+// ERR: :[[@LINE+1]]:{{[0-9]+}}: error: instruction not supported on this GPU
+v_mfma_f32_16x16x32_bf16 v[0:3], v[0:3], v[0:3], v[0:3]
+
+// GFX950: v_mfma_f32_16x16x32_bf16 v[0:3], v[0:3], v[0:3], v[0:3] ; encoding: [0x00,0x00,0xb5,0xd3,0x00,0x01,0x02,0x04]
+// ERR: :[[@LINE+1]]:{{[0-9]+}}: error: instruction not supported on this GPU
+v_mfma_f32_16x16x32bf16 v[0:3], v[0:3], v[0:3], v[0:3]
+
+// GFX950: v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] ; encoding: [0x00,0x80,0xb5,0xd3,0x00,0x01,0x02,0x1c]
+// ERR: :[[@LINE+1]]:{{[0-9]+}}: error: instruction not supported on this GPU
+v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3]
+
+// GFX950: v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] ; encoding: [0x00,0x80,0xb5,0xd3,0x00,0x01,0x02,0x1c]
+// ERR: :[[@LINE+1]]:{{[0-9]+}}: error: instruction not supported on this GPU
+v_mfma_f32_16x16x32bf16 a[0:3], a[0:3], a[0:3], a[0:3]
+
+// GFX950: v_mfma_f32_16x16x32_bf16 v[0:3], a[0:3], v[0:3], 1.0 ; encoding: [0x00,0x00,0xb5,0xd3,0x00,0x01,0xca,0x0b]
+// ERR: :[[@LINE+1]]:{{[0-9]+}}: error: instruction not supported on this GPU
+v_mfma_f32_16x16x32_bf16 v[0:3], a[0:3], v[0:3], 1.0
+
+// GFX950: v_mfma_f32_16x16x32_bf16 a[0:3], v[0:3], a[0:3], 1.0 ; encoding: [0x00,0x80,0xb5,0xd3,0x00,0x01,0xca,0x13]
+// ERR: :[[@LINE+1]]:{{[0-9]+}}: error: instruction not supported on this GPU
+v_mfma_f32_16x16x32_bf16 a[0:3], v[0:3], a[0:3], 1.0
+
+// GFX950: v_mfma_f32_16x16x32_bf16 v[0:3], v[0:3], v[0:3], v[0:3] blgp:5 ; encoding: [0x00,0x00,0xb5,0xd3,0x00,0x01,0x02,0xa4]
+// ERR: :[[@LINE+1]]:{{[0-9]+}}: error: instruction not supported on this GPU
+v_mfma_f32_16x16x32_bf16 v[0:3], v[0:3], v[0:3], v[0:3] blgp:5
+
+// GFX950: v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] blgp:1 ; encoding: [0x00,0x80,0xb5,0xd3,0x00,0x01,0x02,0x3c]
+// ERR: :[[@LINE+1]]:{{[0-9]+}}: error: instruction not supported on this GPU
+v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] blgp:1
+
+// GFX950: v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] cbsz:3 ; encoding: [0x00,0x83,0xb5,0xd3,0x00,0x01,0x02,0x1c]
+// ERR: :[[@LINE+1]]:{{[0-9]+}}: error: instruction not supported on this GPU
+v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] cbsz:3
+
+// GFX950:  v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] abid:1 ; encoding: [0x00,0x88,0xb5,0xd3,0x00,0x01,0x02,0x1c]
+// ERR: :[[@LINE+1]]:{{[0-9]+}}: error: instruction not supported on this GPU
+v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] abid:1
+
+// GFX950:  v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] cbsz:3 abid:1 ; encoding: [0x00,0x8b,0xb5,0xd3,0x00,0x01,0x02,0x1c]
+// ERR: :[[@LINE+1]]:{{[0-9]+}}: error: instruction not supported on this GPU
+v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] cbsz:3 abid:1
+
+// GFX950: v_mfma_f32_16x16x32_bf16 a[0:3], v[0:3], v[0:3], a[4:7] ; encoding: [0x00,0x80,0xb5,0xd3,0x00,0x01,0x12,0x04]
+// ERR: :[[@LINE+1]]:{{[0-9]+}}: error: instruction not supported on this GPU
+v_mfma_f32_16x16x32_bf16 a[0:3], v[0:3], v[0:3], a[4:7]
+
+// GFX950: v_mfma_f32_16x16x32_bf16 v[0:3], a[0:3], a[0:3], v[4:7] ; encoding: [0x00,0x00,0xb5,0xd3,0x00,0x01,0x12,0x1c]
+// ERR: :[[@LINE+1]]:{{[0-9]+}}: error: instruction not supported on this GPU
+v_mfma_f32_16x16x32_bf16 v[0:3], a[0:3], a[0:3], v[4:7]
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx950_mai.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx950_mai.txt
index 88bf255a0637aa..f564c2ffb29a05 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx950_mai.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx950_mai.txt
@@ -630,3 +630,37 @@
 
 # GFX950:   v_mfma_i32_32x32x32_i8 v[0:15], v[0:3], v[0:3], v[0:15] cbsz:3 ; encoding: [0x00,0x03,0xb8,0xd3,0x00,0x01,0x02,0x04]
 0x00,0x03,0xb8,0xd3,0x00,0x01,0x02,0x04
+
+
+# GFX950:   v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] ; encoding: [0x00,0x80,0xb5,0xd3,0x00,0x01,0x02,0x1c]
+0x00,0x80,0xb5,0xd3,0x00,0x01,0x02,0x1c
+
+# GFX950:   v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] abid:1 ; encoding: [0x00,0x88,0xb5,0xd3,0x00,0x01,0x02,0x1c]
+0x00,0x88,0xb5,0xd3,0x00,0x01,0x02,0x1c
+
+# GFX950:   v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] blgp:1 ; encoding: [0x00,0x80,0xb5,0xd3,0x00,0x01,0x02,0x3c]
+0x00,0x80,0xb5,0xd3,0x00,0x01,0x02,0x3c
+
+# GFX950:   v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] cbsz:3 ; encoding: [0x00,0x83,0xb5,0xd3,0x00,0x01,0x02,0x1c]
+0x00,0x83,0xb5,0xd3,0x00,0x01,0x02,0x1c
+
+# GFX950:   v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] cbsz:3 abid:1 ; encoding: [0x00,0x8b,0xb5,0xd3,0x00,0x01,0x02,0x1c]
+0x00,0x8b,0xb5,0xd3,0x00,0x01,0x02,0x1c
+
+# GFX950:   v_mfma_f32_16x16x32_bf16 a[0:3], v[0:3], a[0:3], 1.0 ; encoding: [0x00,0x80,0xb5,0xd3,0x00,0x01,0xca,0x13]
+0x00,0x80,0xb5,0xd3,0x00,0x01,0xca,0x13
+
+# GFX950:   v_mfma_f32_16x16x32_bf16 a[0:3], v[0:3], v[0:3], a[4:7] ; encoding: [0x00,0x80,0xb5,0xd3,0x00,0x01,0x12,0x04]
+0x00,0x80,0xb5,0xd3,0x00,0x01,0x12,0x04
+
+# GFX950:   v_mfma_f32_16x16x32_bf16 v[0:3], a[0:3], a[0:3], v[4:7] ; encoding: [0x00,0x00,0xb5,0xd3,0x00,0x01,0x12,0x1c]
+0x00,0x00,0xb5,0xd3,0x00,0x01,0x12,0x1c
+
+# GFX950:   v_mfma_f32_16x16x32_bf16 v[0:3], a[0:3], v[0:3], 1.0 ; encoding: [0x00,0x00,0xb5,0xd3,0x00,0x01,0xca,0x0b]
+0x00,0x00,0xb5,0xd3,0x00,0x01,0xca,0x0b
+
+# GFX950:   v_mfma_f32_16x16x32_bf16 v[0:3], v[0:3], v[0:3], v[0:3] ; encoding: [0x00,0x00,0xb5,0xd3,0x00,0x01,0x02,0x04]
+0x00,0x00,0xb5,0xd3,0x00,0x01,0x02,0x04
+
+# GFX950:   v_mfma_f32_16x16x32_bf16 v[0:3], v[0:3], v[0:3], v[0:3] blgp:5 ; encoding: [0x00,0x00,0xb5,0xd3,0x00,0x01,0x02,0xa4]
+0x00,0x00,0xb5,0xd3,0x00,0x01,0x02,0xa4
diff --git a/llvm/test/tools/llvm-mca/AMDGPU/gfx950.s b/llvm/test/tools/llvm-mca/AMDGPU/gfx950.s
index 760a20731e2166..cdb96dd717e94c 100644
--- a/llvm/test/tools/llvm-mca/AMDGPU/gfx950.s
+++ b/llvm/test/tools/llvm-mca/AMDGPU/gfx950.s
@@ -1,9 +1,9 @@
 # RUN: llvm-mca -mtriple=amdgcn -mcpu=gfx950 --timeline --iterations=1 --timeline-max-cycles=0 < %s | FileCheck %s
 
 # CHECK: Iterations:        1
-# CHECK: Instructions:      13
-# CHECK: Total Cycles:      48
-# CHECK: Total uOps:        13
+# CHECK: Instructions:      15
+# CHECK: Total Cycles:      60
+# CHECK: Total uOps:        15
 
 v_mfma_ld_scale_b32 v0, v0
 v_mfma_f32_16x16x128_f8f6f4 v[0:3], v[4:11], v[4:11], v[0:3]
@@ -20,6 +20,8 @@ v_mfma_i32_16x16x64_i8 a[0:3], a[0:3], a[0:3], a[0:3] blgp:1
 v_mfma_i32_16x16x64_i8 a[0:3], v[0:3], v[0:3], a[4:7]
 v_mfma_i32_32x32x32_i8 v[0:15], v[0:3], v[0:3], v[0:15]
 v_mfma_i32_32x32x32_i8 a[0:15], a[0:3], a[0:3], a[0:15] blgp:2
+v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] blgp:1
+v_mfma_f32_16x16x32_bf16 a[0:3], v[0:3], v[0:3], a[4:7]
 
 
 # CHECK:     [0]    [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
@@ -36,3 +38,5 @@ v_mfma_i32_32x32x32_i8 a[0:15], a[0:3], a[0:3], a[0:15] blgp:2
 # CHECK-NEXT: -      -      -      -     1.00    -      -    v_mfma_i32_16x16x64_i8 a[0:3], v[0:3], v[0:3], a[4:7]
 # CHECK-NEXT: -      -      -      -     1.00    -      -    v_mfma_i32_32x32x32_i8 v[0:15], v[0:3], v[0:3], v[0:15]
 # CHECK-NEXT: -      -      -      -     1.00    -      -    v_mfma_i32_32x32x32_i8 a[0:15], a[0:3], a[0:3], a[0:15] blgp:2
+# CHECK-NEXT: -      -      -      -      -      -     4.00  v_mfma_f32_16x16x32_bf16 a[0:3], a[0:3], a[0:3], a[0:3] blgp:1
+# CHECK-NEXT: -      -      -      -      -      -     4.00  v_mfma_f32_16x16x32_bf16 a[0:3], v[0:3], v[0:3], a[4:7]



More information about the llvm-commits mailing list