[llvm] a782169 - [AMDGPU][GlobalISel] Transform (fsub (fmul x, y), z) -> (fma x, y, -z)
Mirko Brkusanin via llvm-commits
llvm-commits at lists.llvm.org
Mon Nov 29 07:28:28 PST 2021
- Previous message: [llvm] e5e49a0 - [AMDGPU][GlobalISel] Transform (fadd (fma x, y, (fpext (fmul u, v))), z) -> (fma x, y, (fma (fpext u), (fpext v), z))
- Next message: [llvm] 5fe7fcd - [AMDGPU][GlobalISel] Transform (fsub (fneg (fmul, x, y)), z) -> (fma (fneg x), y, (fneg z))
- Messages sorted by:
[ date ]
[ thread ]
[ subject ]
[ author ]
Author: Mirko Brkusanin
Date: 2021-11-29T16:27:22+01:00
New Revision: a7821692708c413d7a2488137dea2fbbfac31ca7
URL: https://github.com/llvm/llvm-project/commit/a7821692708c413d7a2488137dea2fbbfac31ca7
DIFF: https://github.com/llvm/llvm-project/commit/a7821692708c413d7a2488137dea2fbbfac31ca7.diff
LOG: [AMDGPU][GlobalISel] Transform (fsub (fmul x, y), z) -> (fma x, y, -z)
Patch by: Mateja Marjanovic
Differential Revision: https://reviews.llvm.org/D96614
Added:
llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-sub-mul.ll
Modified:
llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h
llvm/include/llvm/Target/GlobalISel/Combine.td
llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
Removed:
################################################################################
diff --git a/llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h b/llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h
index 1597e79dd85b6..1226ab3d41a71 100644
--- a/llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h
+++ b/llvm/include/llvm/CodeGen/GlobalISel/CombinerHelper.h
@@ -674,6 +674,10 @@ class CombinerHelper {
bool matchCombineFAddFpExtFMulToFMadOrFMAAggressive(MachineInstr &MI,
BuildFnTy &MatchInfo);
+ /// Transform (fsub (fmul x, y), z) -> (fma x, y, -z)
+ /// (fsub (fmul x, y), z) -> (fmad x, y, -z)
+ bool matchCombineFSubFMulToFMadOrFMA(MachineInstr &MI, BuildFnTy &MatchInfo);
+
private:
/// Given a non-indexed load or store instruction \p MI, find an offset that
/// can be usefully and legally folded into it as a post-indexing operation.
diff --git a/llvm/include/llvm/Target/GlobalISel/Combine.td b/llvm/include/llvm/Target/GlobalISel/Combine.td
index caee899eee36a..2badc09ff1fa2 100644
--- a/llvm/include/llvm/Target/GlobalISel/Combine.td
+++ b/llvm/include/llvm/Target/GlobalISel/Combine.td
@@ -801,6 +801,15 @@ def combine_fadd_fpext_fma_fmul_to_fmad_or_fma: GICombineRule<
*${root}, ${info}); }]),
(apply [{ Helper.applyBuildFn(*${root}, ${info}); }])>;
+// Transform (fsub (fmul x, y), z) -> (fma x, y, -z)
+// -> (fmad x, y, -z)
+def combine_fsub_fmul_to_fmad_or_fma: GICombineRule<
+ (defs root:$root, build_fn_matchinfo:$info),
+ (match (wip_match_opcode G_FSUB):$root,
+ [{ return Helper.matchCombineFSubFMulToFMadOrFMA(*${root},
+ ${info}); }]),
+ (apply [{ Helper.applyBuildFn(*${root}, ${info}); }])>;
+
// FIXME: These should use the custom predicate feature once it lands.
def undef_combines : GICombineGroup<[undef_to_fp_zero, undef_to_int_zero,
undef_to_negative_one,
@@ -835,7 +844,8 @@ def trivial_combines : GICombineGroup<[copy_prop, mul_to_shl, add_p2i_to_ptradd,
def fma_combines : GICombineGroup<[combine_fadd_fmul_to_fmad_or_fma,
combine_fadd_fpext_fmul_to_fmad_or_fma, combine_fadd_fma_fmul_to_fmad_or_fma,
- combine_fadd_fpext_fma_fmul_to_fmad_or_fma]>;
+ combine_fadd_fpext_fma_fmul_to_fmad_or_fma,
+ combine_fsub_fmul_to_fmad_or_fma]>;
def all_combines : GICombineGroup<[trivial_combines, insert_vec_elt_combines,
extract_vec_elt_combines, combines_for_extload,
diff --git a/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
index 5973c133a54d4..502b07b1a7673 100644
--- a/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
@@ -5147,6 +5147,56 @@ bool CombinerHelper::matchCombineFAddFpExtFMulToFMadOrFMAAggressive(
return false;
}
+bool CombinerHelper::matchCombineFSubFMulToFMadOrFMA(
+ MachineInstr &MI, std::function<void(MachineIRBuilder &)> &MatchInfo) {
+ assert(MI.getOpcode() == TargetOpcode::G_FSUB);
+
+ bool AllowFusionGlobally, HasFMAD, Aggressive;
+ if (!canCombineFMadOrFMA(MI, AllowFusionGlobally, HasFMAD, Aggressive))
+ return false;
+
+ MachineInstr *LHS = MRI.getVRegDef(MI.getOperand(1).getReg());
+ MachineInstr *RHS = MRI.getVRegDef(MI.getOperand(2).getReg());
+ LLT DstTy = MRI.getType(MI.getOperand(0).getReg());
+
+ // If we have two choices trying to fold (fadd (fmul u, v), (fmul x, y)),
+ // prefer to fold the multiply with fewer uses.
+ int FirstMulHasFewerUses = true;
+ if (isContractableFMul(*LHS, AllowFusionGlobally) &&
+ isContractableFMul(*RHS, AllowFusionGlobally) &&
+ hasMoreUses(*LHS, *RHS, MRI))
+ FirstMulHasFewerUses = false;
+
+ unsigned PreferredFusedOpcode =
+ HasFMAD ? TargetOpcode::G_FMAD : TargetOpcode::G_FMA;
+
+ // fold (fsub (fmul x, y), z) -> (fma x, y, -z)
+ if (FirstMulHasFewerUses &&
+ (isContractableFMul(*LHS, AllowFusionGlobally) &&
+ (Aggressive || MRI.hasOneNonDBGUse(LHS->getOperand(0).getReg())))) {
+ MatchInfo = [=, &MI](MachineIRBuilder &B) {
+ Register NegZ = B.buildFNeg(DstTy, RHS->getOperand(0).getReg()).getReg(0);
+ B.buildInstr(
+ PreferredFusedOpcode, {MI.getOperand(0).getReg()},
+ {LHS->getOperand(1).getReg(), LHS->getOperand(2).getReg(), NegZ});
+ };
+ return true;
+ }
+ // fold (fsub x, (fmul y, z)) -> (fma -y, z, x)
+ else if ((isContractableFMul(*RHS, AllowFusionGlobally) &&
+ (Aggressive || MRI.hasOneNonDBGUse(RHS->getOperand(0).getReg())))) {
+ MatchInfo = [=, &MI](MachineIRBuilder &B) {
+ Register NegY = B.buildFNeg(DstTy, RHS->getOperand(1).getReg()).getReg(0);
+ B.buildInstr(
+ PreferredFusedOpcode, {MI.getOperand(0).getReg()},
+ {NegY, RHS->getOperand(2).getReg(), LHS->getOperand(0).getReg()});
+ };
+ return true;
+ }
+
+ return false;
+}
+
bool CombinerHelper::tryCombine(MachineInstr &MI) {
if (tryCombineCopy(MI))
return true;
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-sub-mul.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-sub-mul.ll
new file mode 100644
index 0000000000000..c40b187134789
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-sub-mul.ll
@@ -0,0 +1,760 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -global-isel -march=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9 %s
+; RUN: llc -global-isel -march=amdgcn -mcpu=gfx900 -fp-contract=fast < %s | FileCheck -check-prefix=GFX9-CONTRACT %s
+; RUN: llc -global-isel -march=amdgcn -mcpu=gfx900 --denormal-fp-math=preserve-sign < %s | FileCheck -check-prefix=GFX9-DENORM %s
+; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1010 < %s | FileCheck -check-prefix=GFX10 %s
+; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1010 -fp-contract=fast < %s | FileCheck -check-prefix=GFX10-CONTRACT %s
+; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1010 --denormal-fp-math=preserve-sign < %s | FileCheck -check-prefix=GFX10-DENORM %s
+
+; fold (fsub (fmul x, y), z) -> (fma x, y, (fneg z))
+; fold (fsub x, (fmul y, z)) -> (fma (fneg y), z, x)
+
+define float @test_f32_sub_mul(float %x, float %y, float %z) {
+; GFX9-LABEL: test_f32_sub_mul:
+; GFX9: ; %bb.0: ; %.entry
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_mul_f32_e32 v0, v0, v1
+; GFX9-NEXT: v_sub_f32_e32 v0, v0, v2
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-CONTRACT-LABEL: test_f32_sub_mul:
+; GFX9-CONTRACT: ; %bb.0: ; %.entry
+; GFX9-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-CONTRACT-NEXT: v_fma_f32 v0, v0, v1, -v2
+; GFX9-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-DENORM-LABEL: test_f32_sub_mul:
+; GFX9-DENORM: ; %bb.0: ; %.entry
+; GFX9-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-DENORM-NEXT: v_mad_f32 v0, v0, v1, -v2
+; GFX9-DENORM-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: test_f32_sub_mul:
+; GFX10: ; %bb.0: ; %.entry
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT: v_mul_f32_e32 v0, v0, v1
+; GFX10-NEXT: v_sub_f32_e32 v0, v0, v2
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-CONTRACT-LABEL: test_f32_sub_mul:
+; GFX10-CONTRACT: ; %bb.0: ; %.entry
+; GFX10-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-CONTRACT-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-CONTRACT-NEXT: v_fma_f32 v0, v0, v1, -v2
+; GFX10-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-DENORM-LABEL: test_f32_sub_mul:
+; GFX10-DENORM: ; %bb.0: ; %.entry
+; GFX10-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-DENORM-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-DENORM-NEXT: v_mad_f32 v0, v0, v1, -v2
+; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
+.entry:
+ %a = fmul float %x, %y
+ %b = fsub float %a, %z
+ ret float %b
+}
+
+define float @test_f32_sub_mul_rhs(float %x, float %y, float %z) {
+; GFX9-LABEL: test_f32_sub_mul_rhs:
+; GFX9: ; %bb.0: ; %.entry
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_mul_f32_e32 v0, v0, v1
+; GFX9-NEXT: v_sub_f32_e32 v0, v2, v0
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-CONTRACT-LABEL: test_f32_sub_mul_rhs:
+; GFX9-CONTRACT: ; %bb.0: ; %.entry
+; GFX9-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-CONTRACT-NEXT: v_fma_f32 v0, -v0, v1, v2
+; GFX9-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-DENORM-LABEL: test_f32_sub_mul_rhs:
+; GFX9-DENORM: ; %bb.0: ; %.entry
+; GFX9-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-DENORM-NEXT: v_mad_f32 v0, -v0, v1, v2
+; GFX9-DENORM-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: test_f32_sub_mul_rhs:
+; GFX10: ; %bb.0: ; %.entry
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT: v_mul_f32_e32 v0, v0, v1
+; GFX10-NEXT: v_sub_f32_e32 v0, v2, v0
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-CONTRACT-LABEL: test_f32_sub_mul_rhs:
+; GFX10-CONTRACT: ; %bb.0: ; %.entry
+; GFX10-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-CONTRACT-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-CONTRACT-NEXT: v_fma_f32 v0, -v0, v1, v2
+; GFX10-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-DENORM-LABEL: test_f32_sub_mul_rhs:
+; GFX10-DENORM: ; %bb.0: ; %.entry
+; GFX10-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-DENORM-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-DENORM-NEXT: v_mad_f32 v0, -v0, v1, v2
+; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
+.entry:
+ %a = fmul float %x, %y
+ %b = fsub float %z, %a
+ ret float %b
+}
+
+define half @test_half_sub_mul(half %x, half %y, half %z) {
+; GFX9-LABEL: test_half_sub_mul:
+; GFX9: ; %bb.0: ; %.entry
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_mul_f16_e32 v0, v0, v1
+; GFX9-NEXT: v_add_f16_e64 v0, v0, -v2
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-CONTRACT-LABEL: test_half_sub_mul:
+; GFX9-CONTRACT: ; %bb.0: ; %.entry
+; GFX9-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-CONTRACT-NEXT: v_xor_b32_e32 v2, 0x8000, v2
+; GFX9-CONTRACT-NEXT: v_fma_f16 v0, v0, v1, v2
+; GFX9-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-DENORM-LABEL: test_half_sub_mul:
+; GFX9-DENORM: ; %bb.0: ; %.entry
+; GFX9-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-DENORM-NEXT: v_mad_legacy_f16 v0, v0, v1, -v2
+; GFX9-DENORM-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: test_half_sub_mul:
+; GFX10: ; %bb.0: ; %.entry
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT: v_mul_f16_e32 v0, v0, v1
+; GFX10-NEXT: v_add_f16_e64 v0, v0, -v2
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-CONTRACT-LABEL: test_half_sub_mul:
+; GFX10-CONTRACT: ; %bb.0: ; %.entry
+; GFX10-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-CONTRACT-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-CONTRACT-NEXT: v_xor_b32_e32 v2, 0x8000, v2
+; GFX10-CONTRACT-NEXT: v_fma_f16 v0, v0, v1, v2
+; GFX10-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-DENORM-LABEL: test_half_sub_mul:
+; GFX10-DENORM: ; %bb.0: ; %.entry
+; GFX10-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-DENORM-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-DENORM-NEXT: v_mul_f16_e32 v0, v0, v1
+; GFX10-DENORM-NEXT: v_add_f16_e64 v0, v0, -v2
+; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
+.entry:
+ %a = fmul half %x, %y
+ %b = fsub half %a, %z
+ ret half %b
+}
+
+define half @test_half_sub_mul_rhs(half %x, half %y, half %z) {
+; GFX9-LABEL: test_half_sub_mul_rhs:
+; GFX9: ; %bb.0: ; %.entry
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_mul_f16_e64 v0, v0, -v1
+; GFX9-NEXT: v_add_f16_e32 v0, v2, v0
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-CONTRACT-LABEL: test_half_sub_mul_rhs:
+; GFX9-CONTRACT: ; %bb.0: ; %.entry
+; GFX9-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-CONTRACT-NEXT: v_xor_b32_e32 v0, 0x8000, v0
+; GFX9-CONTRACT-NEXT: v_fma_f16 v0, v0, v1, v2
+; GFX9-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-DENORM-LABEL: test_half_sub_mul_rhs:
+; GFX9-DENORM: ; %bb.0: ; %.entry
+; GFX9-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-DENORM-NEXT: v_mad_legacy_f16 v0, v0, -v1, v2
+; GFX9-DENORM-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: test_half_sub_mul_rhs:
+; GFX10: ; %bb.0: ; %.entry
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT: v_mul_f16_e64 v0, v0, -v1
+; GFX10-NEXT: v_add_f16_e32 v0, v2, v0
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-CONTRACT-LABEL: test_half_sub_mul_rhs:
+; GFX10-CONTRACT: ; %bb.0: ; %.entry
+; GFX10-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-CONTRACT-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-CONTRACT-NEXT: v_xor_b32_e32 v0, 0x8000, v0
+; GFX10-CONTRACT-NEXT: v_fma_f16 v0, v0, v1, v2
+; GFX10-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-DENORM-LABEL: test_half_sub_mul_rhs:
+; GFX10-DENORM: ; %bb.0: ; %.entry
+; GFX10-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-DENORM-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-DENORM-NEXT: v_mul_f16_e64 v0, v0, -v1
+; GFX10-DENORM-NEXT: v_add_f16_e32 v0, v2, v0
+; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
+.entry:
+ %a = fmul half %x, %y
+ %b = fsub half %z, %a
+ ret half %b
+}
+
+define double @test_double_sub_mul(double %x, double %y, double %z) {
+; GFX9-LABEL: test_double_sub_mul:
+; GFX9: ; %bb.0: ; %.entry
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_mul_f64 v[0:1], v[0:1], v[2:3]
+; GFX9-NEXT: v_add_f64 v[0:1], v[0:1], -v[4:5]
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-CONTRACT-LABEL: test_double_sub_mul:
+; GFX9-CONTRACT: ; %bb.0: ; %.entry
+; GFX9-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-CONTRACT-NEXT: v_fma_f64 v[0:1], v[0:1], v[2:3], -v[4:5]
+; GFX9-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-DENORM-LABEL: test_double_sub_mul:
+; GFX9-DENORM: ; %bb.0: ; %.entry
+; GFX9-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-DENORM-NEXT: v_mul_f64 v[0:1], v[0:1], v[2:3]
+; GFX9-DENORM-NEXT: v_add_f64 v[0:1], v[0:1], -v[4:5]
+; GFX9-DENORM-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: test_double_sub_mul:
+; GFX10: ; %bb.0: ; %.entry
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT: v_mul_f64 v[0:1], v[0:1], v[2:3]
+; GFX10-NEXT: v_add_f64 v[0:1], v[0:1], -v[4:5]
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-CONTRACT-LABEL: test_double_sub_mul:
+; GFX10-CONTRACT: ; %bb.0: ; %.entry
+; GFX10-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-CONTRACT-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-CONTRACT-NEXT: v_fma_f64 v[0:1], v[0:1], v[2:3], -v[4:5]
+; GFX10-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-DENORM-LABEL: test_double_sub_mul:
+; GFX10-DENORM: ; %bb.0: ; %.entry
+; GFX10-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-DENORM-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-DENORM-NEXT: v_mul_f64 v[0:1], v[0:1], v[2:3]
+; GFX10-DENORM-NEXT: v_add_f64 v[0:1], v[0:1], -v[4:5]
+; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
+.entry:
+ %a = fmul double %x, %y
+ %b = fsub double %a, %z
+ ret double %b
+}
+
+define double @test_double_sub_mul_rhs(double %x, double %y, double %z) {
+; GFX9-LABEL: test_double_sub_mul_rhs:
+; GFX9: ; %bb.0: ; %.entry
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_mul_f64 v[0:1], v[0:1], v[2:3]
+; GFX9-NEXT: v_add_f64 v[0:1], v[4:5], -v[0:1]
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-CONTRACT-LABEL: test_double_sub_mul_rhs:
+; GFX9-CONTRACT: ; %bb.0: ; %.entry
+; GFX9-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-CONTRACT-NEXT: v_fma_f64 v[0:1], -v[0:1], v[2:3], v[4:5]
+; GFX9-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-DENORM-LABEL: test_double_sub_mul_rhs:
+; GFX9-DENORM: ; %bb.0: ; %.entry
+; GFX9-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-DENORM-NEXT: v_mul_f64 v[0:1], v[0:1], v[2:3]
+; GFX9-DENORM-NEXT: v_add_f64 v[0:1], v[4:5], -v[0:1]
+; GFX9-DENORM-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: test_double_sub_mul_rhs:
+; GFX10: ; %bb.0: ; %.entry
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT: v_mul_f64 v[0:1], v[0:1], v[2:3]
+; GFX10-NEXT: v_add_f64 v[0:1], v[4:5], -v[0:1]
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-CONTRACT-LABEL: test_double_sub_mul_rhs:
+; GFX10-CONTRACT: ; %bb.0: ; %.entry
+; GFX10-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-CONTRACT-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-CONTRACT-NEXT: v_fma_f64 v[0:1], -v[0:1], v[2:3], v[4:5]
+; GFX10-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-DENORM-LABEL: test_double_sub_mul_rhs:
+; GFX10-DENORM: ; %bb.0: ; %.entry
+; GFX10-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-DENORM-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-DENORM-NEXT: v_mul_f64 v[0:1], v[0:1], v[2:3]
+; GFX10-DENORM-NEXT: v_add_f64 v[0:1], v[4:5], -v[0:1]
+; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
+.entry:
+ %a = fmul double %x, %y
+ %b = fsub double %z, %a
+ ret double %b
+}
+
+define <4 x float> @test_v4f32_sub_mul(<4 x float> %x, <4 x float> %y, <4 x float> %z) {
+; GFX9-LABEL: test_v4f32_sub_mul:
+; GFX9: ; %bb.0: ; %.entry
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_mul_f32_e32 v0, v0, v4
+; GFX9-NEXT: v_mul_f32_e32 v1, v1, v5
+; GFX9-NEXT: v_mul_f32_e32 v2, v2, v6
+; GFX9-NEXT: v_mul_f32_e32 v3, v3, v7
+; GFX9-NEXT: v_sub_f32_e32 v0, v0, v8
+; GFX9-NEXT: v_sub_f32_e32 v1, v1, v9
+; GFX9-NEXT: v_sub_f32_e32 v2, v2, v10
+; GFX9-NEXT: v_sub_f32_e32 v3, v3, v11
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-CONTRACT-LABEL: test_v4f32_sub_mul:
+; GFX9-CONTRACT: ; %bb.0: ; %.entry
+; GFX9-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-CONTRACT-NEXT: v_fma_f32 v0, v0, v4, -v8
+; GFX9-CONTRACT-NEXT: v_fma_f32 v1, v1, v5, -v9
+; GFX9-CONTRACT-NEXT: v_fma_f32 v2, v2, v6, -v10
+; GFX9-CONTRACT-NEXT: v_fma_f32 v3, v3, v7, -v11
+; GFX9-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-DENORM-LABEL: test_v4f32_sub_mul:
+; GFX9-DENORM: ; %bb.0: ; %.entry
+; GFX9-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-DENORM-NEXT: v_mad_f32 v0, v0, v4, -v8
+; GFX9-DENORM-NEXT: v_mad_f32 v1, v1, v5, -v9
+; GFX9-DENORM-NEXT: v_mad_f32 v2, v2, v6, -v10
+; GFX9-DENORM-NEXT: v_mad_f32 v3, v3, v7, -v11
+; GFX9-DENORM-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: test_v4f32_sub_mul:
+; GFX10: ; %bb.0: ; %.entry
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT: v_mul_f32_e32 v0, v0, v4
+; GFX10-NEXT: v_mul_f32_e32 v1, v1, v5
+; GFX10-NEXT: v_mul_f32_e32 v2, v2, v6
+; GFX10-NEXT: v_mul_f32_e32 v3, v3, v7
+; GFX10-NEXT: v_sub_f32_e32 v0, v0, v8
+; GFX10-NEXT: v_sub_f32_e32 v1, v1, v9
+; GFX10-NEXT: v_sub_f32_e32 v2, v2, v10
+; GFX10-NEXT: v_sub_f32_e32 v3, v3, v11
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-CONTRACT-LABEL: test_v4f32_sub_mul:
+; GFX10-CONTRACT: ; %bb.0: ; %.entry
+; GFX10-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-CONTRACT-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-CONTRACT-NEXT: v_fma_f32 v0, v0, v4, -v8
+; GFX10-CONTRACT-NEXT: v_fma_f32 v1, v1, v5, -v9
+; GFX10-CONTRACT-NEXT: v_fma_f32 v2, v2, v6, -v10
+; GFX10-CONTRACT-NEXT: v_fma_f32 v3, v3, v7, -v11
+; GFX10-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-DENORM-LABEL: test_v4f32_sub_mul:
+; GFX10-DENORM: ; %bb.0: ; %.entry
+; GFX10-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-DENORM-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-DENORM-NEXT: v_mad_f32 v0, v0, v4, -v8
+; GFX10-DENORM-NEXT: v_mad_f32 v1, v1, v5, -v9
+; GFX10-DENORM-NEXT: v_mad_f32 v2, v2, v6, -v10
+; GFX10-DENORM-NEXT: v_mad_f32 v3, v3, v7, -v11
+; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
+.entry:
+ %a = fmul <4 x float> %x, %y
+ %b = fsub <4 x float> %a, %z
+ ret <4 x float> %b
+}
+
+define <4 x float> @test_v4f32_sub_mul_rhs(<4 x float> %x, <4 x float> %y, <4 x float> %z) {
+; GFX9-LABEL: test_v4f32_sub_mul_rhs:
+; GFX9: ; %bb.0: ; %.entry
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_mul_f32_e32 v0, v0, v4
+; GFX9-NEXT: v_mul_f32_e32 v1, v1, v5
+; GFX9-NEXT: v_mul_f32_e32 v2, v2, v6
+; GFX9-NEXT: v_mul_f32_e32 v3, v3, v7
+; GFX9-NEXT: v_sub_f32_e32 v0, v8, v0
+; GFX9-NEXT: v_sub_f32_e32 v1, v9, v1
+; GFX9-NEXT: v_sub_f32_e32 v2, v10, v2
+; GFX9-NEXT: v_sub_f32_e32 v3, v11, v3
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-CONTRACT-LABEL: test_v4f32_sub_mul_rhs:
+; GFX9-CONTRACT: ; %bb.0: ; %.entry
+; GFX9-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-CONTRACT-NEXT: v_fma_f32 v0, -v0, v4, v8
+; GFX9-CONTRACT-NEXT: v_fma_f32 v1, -v1, v5, v9
+; GFX9-CONTRACT-NEXT: v_fma_f32 v2, -v2, v6, v10
+; GFX9-CONTRACT-NEXT: v_fma_f32 v3, -v3, v7, v11
+; GFX9-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-DENORM-LABEL: test_v4f32_sub_mul_rhs:
+; GFX9-DENORM: ; %bb.0: ; %.entry
+; GFX9-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-DENORM-NEXT: v_mad_f32 v0, -v0, v4, v8
+; GFX9-DENORM-NEXT: v_mad_f32 v1, -v1, v5, v9
+; GFX9-DENORM-NEXT: v_mad_f32 v2, -v2, v6, v10
+; GFX9-DENORM-NEXT: v_mad_f32 v3, -v3, v7, v11
+; GFX9-DENORM-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: test_v4f32_sub_mul_rhs:
+; GFX10: ; %bb.0: ; %.entry
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT: v_mul_f32_e32 v0, v0, v4
+; GFX10-NEXT: v_mul_f32_e32 v1, v1, v5
+; GFX10-NEXT: v_mul_f32_e32 v2, v2, v6
+; GFX10-NEXT: v_mul_f32_e32 v3, v3, v7
+; GFX10-NEXT: v_sub_f32_e32 v0, v8, v0
+; GFX10-NEXT: v_sub_f32_e32 v1, v9, v1
+; GFX10-NEXT: v_sub_f32_e32 v2, v10, v2
+; GFX10-NEXT: v_sub_f32_e32 v3, v11, v3
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-CONTRACT-LABEL: test_v4f32_sub_mul_rhs:
+; GFX10-CONTRACT: ; %bb.0: ; %.entry
+; GFX10-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-CONTRACT-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-CONTRACT-NEXT: v_fma_f32 v0, -v0, v4, v8
+; GFX10-CONTRACT-NEXT: v_fma_f32 v1, -v1, v5, v9
+; GFX10-CONTRACT-NEXT: v_fma_f32 v2, -v2, v6, v10
+; GFX10-CONTRACT-NEXT: v_fma_f32 v3, -v3, v7, v11
+; GFX10-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-DENORM-LABEL: test_v4f32_sub_mul_rhs:
+; GFX10-DENORM: ; %bb.0: ; %.entry
+; GFX10-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-DENORM-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-DENORM-NEXT: v_mad_f32 v0, -v0, v4, v8
+; GFX10-DENORM-NEXT: v_mad_f32 v1, -v1, v5, v9
+; GFX10-DENORM-NEXT: v_mad_f32 v2, -v2, v6, v10
+; GFX10-DENORM-NEXT: v_mad_f32 v3, -v3, v7, v11
+; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
+.entry:
+ %a = fmul <4 x float> %x, %y
+ %b = fsub <4 x float> %z, %a
+ ret <4 x float> %b
+}
+
+define <4 x half> @test_v4f16_sub_mul(<4 x half> %x, <4 x half> %y, <4 x half> %z) {
+; GFX9-LABEL: test_v4f16_sub_mul:
+; GFX9: ; %bb.0: ; %.entry
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_mul_f16 v0, v0, v2
+; GFX9-NEXT: v_pk_mul_f16 v1, v1, v3
+; GFX9-NEXT: v_add_f16_e64 v2, v0, -v4
+; GFX9-NEXT: v_add_f16_sdwa v0, v0, -v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX9-NEXT: v_add_f16_e64 v3, v1, -v5
+; GFX9-NEXT: v_add_f16_sdwa v1, v1, -v5 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX9-NEXT: v_mov_b32_e32 v4, 0xffff
+; GFX9-NEXT: v_and_or_b32 v0, v2, v4, v0
+; GFX9-NEXT: v_and_or_b32 v1, v3, v4, v1
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-CONTRACT-LABEL: test_v4f16_sub_mul:
+; GFX9-CONTRACT: ; %bb.0: ; %.entry
+; GFX9-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-CONTRACT-NEXT: v_pk_fma_f16 v0, v0, v2, v4 neg_lo:[0,0,1] neg_hi:[0,0,1]
+; GFX9-CONTRACT-NEXT: v_pk_fma_f16 v1, v1, v3, v5 neg_lo:[0,0,1] neg_hi:[0,0,1]
+; GFX9-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-DENORM-LABEL: test_v4f16_sub_mul:
+; GFX9-DENORM: ; %bb.0: ; %.entry
+; GFX9-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-DENORM-NEXT: v_pk_mul_f16 v0, v0, v2
+; GFX9-DENORM-NEXT: v_pk_mul_f16 v1, v1, v3
+; GFX9-DENORM-NEXT: v_add_f16_e64 v2, v0, -v4
+; GFX9-DENORM-NEXT: v_add_f16_sdwa v0, v0, -v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX9-DENORM-NEXT: v_add_f16_e64 v3, v1, -v5
+; GFX9-DENORM-NEXT: v_add_f16_sdwa v1, v1, -v5 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX9-DENORM-NEXT: v_mov_b32_e32 v4, 0xffff
+; GFX9-DENORM-NEXT: v_and_or_b32 v0, v2, v4, v0
+; GFX9-DENORM-NEXT: v_and_or_b32 v1, v3, v4, v1
+; GFX9-DENORM-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: test_v4f16_sub_mul:
+; GFX10: ; %bb.0: ; %.entry
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT: v_pk_mul_f16 v0, v0, v2
+; GFX10-NEXT: v_pk_mul_f16 v1, v1, v3
+; GFX10-NEXT: v_add_f16_e64 v2, v0, -v4
+; GFX10-NEXT: v_add_f16_sdwa v0, v0, -v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX10-NEXT: v_add_f16_e64 v3, v1, -v5
+; GFX10-NEXT: v_mov_b32_e32 v4, 0xffff
+; GFX10-NEXT: v_add_f16_sdwa v1, v1, -v5 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX10-NEXT: v_and_or_b32 v0, v2, v4, v0
+; GFX10-NEXT: v_and_or_b32 v1, v3, v4, v1
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-CONTRACT-LABEL: test_v4f16_sub_mul:
+; GFX10-CONTRACT: ; %bb.0: ; %.entry
+; GFX10-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-CONTRACT-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-CONTRACT-NEXT: v_pk_fma_f16 v0, v0, v2, v4 neg_lo:[0,0,1] neg_hi:[0,0,1]
+; GFX10-CONTRACT-NEXT: v_pk_fma_f16 v1, v1, v3, v5 neg_lo:[0,0,1] neg_hi:[0,0,1]
+; GFX10-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-DENORM-LABEL: test_v4f16_sub_mul:
+; GFX10-DENORM: ; %bb.0: ; %.entry
+; GFX10-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-DENORM-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-DENORM-NEXT: v_pk_mul_f16 v0, v0, v2
+; GFX10-DENORM-NEXT: v_pk_mul_f16 v1, v1, v3
+; GFX10-DENORM-NEXT: v_add_f16_e64 v2, v0, -v4
+; GFX10-DENORM-NEXT: v_add_f16_sdwa v0, v0, -v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX10-DENORM-NEXT: v_add_f16_e64 v3, v1, -v5
+; GFX10-DENORM-NEXT: v_mov_b32_e32 v4, 0xffff
+; GFX10-DENORM-NEXT: v_add_f16_sdwa v1, v1, -v5 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX10-DENORM-NEXT: v_and_or_b32 v0, v2, v4, v0
+; GFX10-DENORM-NEXT: v_and_or_b32 v1, v3, v4, v1
+; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
+.entry:
+ %a = fmul <4 x half> %x, %y
+ %b = fsub <4 x half> %a, %z
+ ret <4 x half> %b
+}
+
+define <4 x half> @test_v4f16_sub_mul_rhs(<4 x half> %x, <4 x half> %y, <4 x half> %z) {
+; GFX9-LABEL: test_v4f16_sub_mul_rhs:
+; GFX9: ; %bb.0: ; %.entry
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_pk_mul_f16 v0, v0, v2
+; GFX9-NEXT: v_pk_mul_f16 v1, v1, v3
+; GFX9-NEXT: v_add_f16_e64 v2, v4, -v0
+; GFX9-NEXT: v_add_f16_sdwa v0, v4, -v0 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX9-NEXT: v_add_f16_e64 v3, v5, -v1
+; GFX9-NEXT: v_add_f16_sdwa v1, v5, -v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX9-NEXT: v_mov_b32_e32 v4, 0xffff
+; GFX9-NEXT: v_and_or_b32 v0, v2, v4, v0
+; GFX9-NEXT: v_and_or_b32 v1, v3, v4, v1
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-CONTRACT-LABEL: test_v4f16_sub_mul_rhs:
+; GFX9-CONTRACT: ; %bb.0: ; %.entry
+; GFX9-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-CONTRACT-NEXT: v_pk_fma_f16 v0, v0, v2, v4 neg_lo:[1,0,0] neg_hi:[1,0,0]
+; GFX9-CONTRACT-NEXT: v_pk_fma_f16 v1, v1, v3, v5 neg_lo:[1,0,0] neg_hi:[1,0,0]
+; GFX9-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-DENORM-LABEL: test_v4f16_sub_mul_rhs:
+; GFX9-DENORM: ; %bb.0: ; %.entry
+; GFX9-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-DENORM-NEXT: v_pk_mul_f16 v0, v0, v2
+; GFX9-DENORM-NEXT: v_pk_mul_f16 v1, v1, v3
+; GFX9-DENORM-NEXT: v_add_f16_e64 v2, v4, -v0
+; GFX9-DENORM-NEXT: v_add_f16_sdwa v0, v4, -v0 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX9-DENORM-NEXT: v_add_f16_e64 v3, v5, -v1
+; GFX9-DENORM-NEXT: v_add_f16_sdwa v1, v5, -v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX9-DENORM-NEXT: v_mov_b32_e32 v4, 0xffff
+; GFX9-DENORM-NEXT: v_and_or_b32 v0, v2, v4, v0
+; GFX9-DENORM-NEXT: v_and_or_b32 v1, v3, v4, v1
+; GFX9-DENORM-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: test_v4f16_sub_mul_rhs:
+; GFX10: ; %bb.0: ; %.entry
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT: v_pk_mul_f16 v0, v0, v2
+; GFX10-NEXT: v_pk_mul_f16 v1, v1, v3
+; GFX10-NEXT: v_add_f16_e64 v2, v4, -v0
+; GFX10-NEXT: v_add_f16_sdwa v0, v4, -v0 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX10-NEXT: v_add_f16_e64 v3, v5, -v1
+; GFX10-NEXT: v_mov_b32_e32 v4, 0xffff
+; GFX10-NEXT: v_add_f16_sdwa v1, v5, -v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX10-NEXT: v_and_or_b32 v0, v2, v4, v0
+; GFX10-NEXT: v_and_or_b32 v1, v3, v4, v1
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-CONTRACT-LABEL: test_v4f16_sub_mul_rhs:
+; GFX10-CONTRACT: ; %bb.0: ; %.entry
+; GFX10-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-CONTRACT-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-CONTRACT-NEXT: v_pk_fma_f16 v0, v0, v2, v4 neg_lo:[1,0,0] neg_hi:[1,0,0]
+; GFX10-CONTRACT-NEXT: v_pk_fma_f16 v1, v1, v3, v5 neg_lo:[1,0,0] neg_hi:[1,0,0]
+; GFX10-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-DENORM-LABEL: test_v4f16_sub_mul_rhs:
+; GFX10-DENORM: ; %bb.0: ; %.entry
+; GFX10-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-DENORM-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-DENORM-NEXT: v_pk_mul_f16 v0, v0, v2
+; GFX10-DENORM-NEXT: v_pk_mul_f16 v1, v1, v3
+; GFX10-DENORM-NEXT: v_add_f16_e64 v2, v4, -v0
+; GFX10-DENORM-NEXT: v_add_f16_sdwa v0, v4, -v0 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX10-DENORM-NEXT: v_add_f16_e64 v3, v5, -v1
+; GFX10-DENORM-NEXT: v_mov_b32_e32 v4, 0xffff
+; GFX10-DENORM-NEXT: v_add_f16_sdwa v1, v5, -v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; GFX10-DENORM-NEXT: v_and_or_b32 v0, v2, v4, v0
+; GFX10-DENORM-NEXT: v_and_or_b32 v1, v3, v4, v1
+; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
+.entry:
+ %a = fmul <4 x half> %x, %y
+ %b = fsub <4 x half> %z, %a
+ ret <4 x half> %b
+}
+
+define <4 x double> @test_v4f64_sub_mul(<4 x double> %x, <4 x double> %y, <4 x double> %z) {
+; GFX9-LABEL: test_v4f64_sub_mul:
+; GFX9: ; %bb.0: ; %.entry
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_mul_f64 v[0:1], v[0:1], v[8:9]
+; GFX9-NEXT: v_mul_f64 v[2:3], v[2:3], v[10:11]
+; GFX9-NEXT: v_mul_f64 v[4:5], v[4:5], v[12:13]
+; GFX9-NEXT: v_mul_f64 v[6:7], v[6:7], v[14:15]
+; GFX9-NEXT: v_add_f64 v[0:1], v[0:1], -v[16:17]
+; GFX9-NEXT: v_add_f64 v[2:3], v[2:3], -v[18:19]
+; GFX9-NEXT: v_add_f64 v[4:5], v[4:5], -v[20:21]
+; GFX9-NEXT: v_add_f64 v[6:7], v[6:7], -v[22:23]
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-CONTRACT-LABEL: test_v4f64_sub_mul:
+; GFX9-CONTRACT: ; %bb.0: ; %.entry
+; GFX9-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-CONTRACT-NEXT: v_fma_f64 v[0:1], v[0:1], v[8:9], -v[16:17]
+; GFX9-CONTRACT-NEXT: v_fma_f64 v[2:3], v[2:3], v[10:11], -v[18:19]
+; GFX9-CONTRACT-NEXT: v_fma_f64 v[4:5], v[4:5], v[12:13], -v[20:21]
+; GFX9-CONTRACT-NEXT: v_fma_f64 v[6:7], v[6:7], v[14:15], -v[22:23]
+; GFX9-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-DENORM-LABEL: test_v4f64_sub_mul:
+; GFX9-DENORM: ; %bb.0: ; %.entry
+; GFX9-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-DENORM-NEXT: v_mul_f64 v[0:1], v[0:1], v[8:9]
+; GFX9-DENORM-NEXT: v_mul_f64 v[2:3], v[2:3], v[10:11]
+; GFX9-DENORM-NEXT: v_mul_f64 v[4:5], v[4:5], v[12:13]
+; GFX9-DENORM-NEXT: v_mul_f64 v[6:7], v[6:7], v[14:15]
+; GFX9-DENORM-NEXT: v_add_f64 v[0:1], v[0:1], -v[16:17]
+; GFX9-DENORM-NEXT: v_add_f64 v[2:3], v[2:3], -v[18:19]
+; GFX9-DENORM-NEXT: v_add_f64 v[4:5], v[4:5], -v[20:21]
+; GFX9-DENORM-NEXT: v_add_f64 v[6:7], v[6:7], -v[22:23]
+; GFX9-DENORM-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: test_v4f64_sub_mul:
+; GFX10: ; %bb.0: ; %.entry
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT: v_mul_f64 v[0:1], v[0:1], v[8:9]
+; GFX10-NEXT: v_mul_f64 v[2:3], v[2:3], v[10:11]
+; GFX10-NEXT: v_mul_f64 v[4:5], v[4:5], v[12:13]
+; GFX10-NEXT: v_mul_f64 v[6:7], v[6:7], v[14:15]
+; GFX10-NEXT: v_add_f64 v[0:1], v[0:1], -v[16:17]
+; GFX10-NEXT: v_add_f64 v[2:3], v[2:3], -v[18:19]
+; GFX10-NEXT: v_add_f64 v[4:5], v[4:5], -v[20:21]
+; GFX10-NEXT: v_add_f64 v[6:7], v[6:7], -v[22:23]
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-CONTRACT-LABEL: test_v4f64_sub_mul:
+; GFX10-CONTRACT: ; %bb.0: ; %.entry
+; GFX10-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-CONTRACT-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-CONTRACT-NEXT: v_fma_f64 v[0:1], v[0:1], v[8:9], -v[16:17]
+; GFX10-CONTRACT-NEXT: v_fma_f64 v[2:3], v[2:3], v[10:11], -v[18:19]
+; GFX10-CONTRACT-NEXT: v_fma_f64 v[4:5], v[4:5], v[12:13], -v[20:21]
+; GFX10-CONTRACT-NEXT: v_fma_f64 v[6:7], v[6:7], v[14:15], -v[22:23]
+; GFX10-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-DENORM-LABEL: test_v4f64_sub_mul:
+; GFX10-DENORM: ; %bb.0: ; %.entry
+; GFX10-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-DENORM-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-DENORM-NEXT: v_mul_f64 v[0:1], v[0:1], v[8:9]
+; GFX10-DENORM-NEXT: v_mul_f64 v[2:3], v[2:3], v[10:11]
+; GFX10-DENORM-NEXT: v_mul_f64 v[4:5], v[4:5], v[12:13]
+; GFX10-DENORM-NEXT: v_mul_f64 v[6:7], v[6:7], v[14:15]
+; GFX10-DENORM-NEXT: v_add_f64 v[0:1], v[0:1], -v[16:17]
+; GFX10-DENORM-NEXT: v_add_f64 v[2:3], v[2:3], -v[18:19]
+; GFX10-DENORM-NEXT: v_add_f64 v[4:5], v[4:5], -v[20:21]
+; GFX10-DENORM-NEXT: v_add_f64 v[6:7], v[6:7], -v[22:23]
+; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
+.entry:
+ %a = fmul <4 x double> %x, %y
+ %b = fsub <4 x double> %a, %z
+ ret <4 x double> %b
+}
+
+define <4 x double> @test_v4f64_sub_mul_rhs(<4 x double> %x, <4 x double> %y, <4 x double> %z) {
+; GFX9-LABEL: test_v4f64_sub_mul_rhs:
+; GFX9: ; %bb.0: ; %.entry
+; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT: v_mul_f64 v[0:1], v[0:1], v[8:9]
+; GFX9-NEXT: v_mul_f64 v[2:3], v[2:3], v[10:11]
+; GFX9-NEXT: v_mul_f64 v[4:5], v[4:5], v[12:13]
+; GFX9-NEXT: v_mul_f64 v[6:7], v[6:7], v[14:15]
+; GFX9-NEXT: v_add_f64 v[0:1], v[16:17], -v[0:1]
+; GFX9-NEXT: v_add_f64 v[2:3], v[18:19], -v[2:3]
+; GFX9-NEXT: v_add_f64 v[4:5], v[20:21], -v[4:5]
+; GFX9-NEXT: v_add_f64 v[6:7], v[22:23], -v[6:7]
+; GFX9-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-CONTRACT-LABEL: test_v4f64_sub_mul_rhs:
+; GFX9-CONTRACT: ; %bb.0: ; %.entry
+; GFX9-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-CONTRACT-NEXT: v_fma_f64 v[0:1], -v[0:1], v[8:9], v[16:17]
+; GFX9-CONTRACT-NEXT: v_fma_f64 v[2:3], -v[2:3], v[10:11], v[18:19]
+; GFX9-CONTRACT-NEXT: v_fma_f64 v[4:5], -v[4:5], v[12:13], v[20:21]
+; GFX9-CONTRACT-NEXT: v_fma_f64 v[6:7], -v[6:7], v[14:15], v[22:23]
+; GFX9-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX9-DENORM-LABEL: test_v4f64_sub_mul_rhs:
+; GFX9-DENORM: ; %bb.0: ; %.entry
+; GFX9-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-DENORM-NEXT: v_mul_f64 v[0:1], v[0:1], v[8:9]
+; GFX9-DENORM-NEXT: v_mul_f64 v[2:3], v[2:3], v[10:11]
+; GFX9-DENORM-NEXT: v_mul_f64 v[4:5], v[4:5], v[12:13]
+; GFX9-DENORM-NEXT: v_mul_f64 v[6:7], v[6:7], v[14:15]
+; GFX9-DENORM-NEXT: v_add_f64 v[0:1], v[16:17], -v[0:1]
+; GFX9-DENORM-NEXT: v_add_f64 v[2:3], v[18:19], -v[2:3]
+; GFX9-DENORM-NEXT: v_add_f64 v[4:5], v[20:21], -v[4:5]
+; GFX9-DENORM-NEXT: v_add_f64 v[6:7], v[22:23], -v[6:7]
+; GFX9-DENORM-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-LABEL: test_v4f64_sub_mul_rhs:
+; GFX10: ; %bb.0: ; %.entry
+; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT: v_mul_f64 v[0:1], v[0:1], v[8:9]
+; GFX10-NEXT: v_mul_f64 v[2:3], v[2:3], v[10:11]
+; GFX10-NEXT: v_mul_f64 v[4:5], v[4:5], v[12:13]
+; GFX10-NEXT: v_mul_f64 v[6:7], v[6:7], v[14:15]
+; GFX10-NEXT: v_add_f64 v[0:1], v[16:17], -v[0:1]
+; GFX10-NEXT: v_add_f64 v[2:3], v[18:19], -v[2:3]
+; GFX10-NEXT: v_add_f64 v[4:5], v[20:21], -v[4:5]
+; GFX10-NEXT: v_add_f64 v[6:7], v[22:23], -v[6:7]
+; GFX10-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-CONTRACT-LABEL: test_v4f64_sub_mul_rhs:
+; GFX10-CONTRACT: ; %bb.0: ; %.entry
+; GFX10-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-CONTRACT-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-CONTRACT-NEXT: v_fma_f64 v[0:1], -v[0:1], v[8:9], v[16:17]
+; GFX10-CONTRACT-NEXT: v_fma_f64 v[2:3], -v[2:3], v[10:11], v[18:19]
+; GFX10-CONTRACT-NEXT: v_fma_f64 v[4:5], -v[4:5], v[12:13], v[20:21]
+; GFX10-CONTRACT-NEXT: v_fma_f64 v[6:7], -v[6:7], v[14:15], v[22:23]
+; GFX10-CONTRACT-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX10-DENORM-LABEL: test_v4f64_sub_mul_rhs:
+; GFX10-DENORM: ; %bb.0: ; %.entry
+; GFX10-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-DENORM-NEXT: s_waitcnt_vscnt null, 0x0
+; GFX10-DENORM-NEXT: v_mul_f64 v[0:1], v[0:1], v[8:9]
+; GFX10-DENORM-NEXT: v_mul_f64 v[2:3], v[2:3], v[10:11]
+; GFX10-DENORM-NEXT: v_mul_f64 v[4:5], v[4:5], v[12:13]
+; GFX10-DENORM-NEXT: v_mul_f64 v[6:7], v[6:7], v[14:15]
+; GFX10-DENORM-NEXT: v_add_f64 v[0:1], v[16:17], -v[0:1]
+; GFX10-DENORM-NEXT: v_add_f64 v[2:3], v[18:19], -v[2:3]
+; GFX10-DENORM-NEXT: v_add_f64 v[4:5], v[20:21], -v[4:5]
+; GFX10-DENORM-NEXT: v_add_f64 v[6:7], v[22:23], -v[6:7]
+; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
+.entry:
+ %a = fmul <4 x double> %x, %y
+ %b = fsub <4 x double> %z, %a
+ ret <4 x double> %b
+}
- Previous message: [llvm] e5e49a0 - [AMDGPU][GlobalISel] Transform (fadd (fma x, y, (fpext (fmul u, v))), z) -> (fma x, y, (fma (fpext u), (fpext v), z))
- Next message: [llvm] 5fe7fcd - [AMDGPU][GlobalISel] Transform (fsub (fneg (fmul, x, y)), z) -> (fma (fneg x), y, (fneg z))
- Messages sorted by:
[ date ]
[ thread ]
[ subject ]
[ author ]
More information about the llvm-commits
mailing list