CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
917 lines
41 KiB
LLVM
917 lines
41 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9 %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx900 -fp-contract=fast < %s | FileCheck -check-prefix=GFX9-CONTRACT %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx900 --denormal-fp-math=preserve-sign < %s | FileCheck -check-prefix=GFX9-DENORM %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck -check-prefix=GFX10 %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1010 -fp-contract=fast < %s | FileCheck -check-prefix=GFX10-CONTRACT %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1010 --denormal-fp-math=preserve-sign < %s | FileCheck -check-prefix=GFX10-DENORM %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -fp-contract=fast < %s | FileCheck -check-prefixes=GFX11-CONTRACT,GFX11-CONTRACT-TRUE16 %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -fp-contract=fast < %s | FileCheck -check-prefixes=GFX11-CONTRACT,GFX11-CONTRACT-FAKE16 %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 --denormal-fp-math=preserve-sign < %s | FileCheck -check-prefixes=GFX11-DENORM,GFX11-DENORM-TRUE16 %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 --denormal-fp-math=preserve-sign < %s | FileCheck -check-prefixes=GFX11-DENORM,GFX11-DENORM-FAKE16 %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: 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: 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: v_mad_f32 v0, v0, v1, -v2
|
|
; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-CONTRACT-LABEL: test_f32_sub_mul:
|
|
; GFX11-CONTRACT: ; %bb.0: ; %.entry
|
|
; GFX11-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-CONTRACT-NEXT: v_fma_f32 v0, v0, v1, -v2
|
|
; GFX11-CONTRACT-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-DENORM-LABEL: test_f32_sub_mul:
|
|
; GFX11-DENORM: ; %bb.0: ; %.entry
|
|
; GFX11-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-DENORM-NEXT: v_mul_f32_e32 v0, v0, v1
|
|
; GFX11-DENORM-NEXT: s_delay_alu instid0(VALU_DEP_1)
|
|
; GFX11-DENORM-NEXT: v_sub_f32_e32 v0, v0, v2
|
|
; GFX11-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: 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: 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: v_mad_f32 v0, -v0, v1, v2
|
|
; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-CONTRACT-LABEL: test_f32_sub_mul_rhs:
|
|
; GFX11-CONTRACT: ; %bb.0: ; %.entry
|
|
; GFX11-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-CONTRACT-NEXT: v_fma_f32 v0, -v0, v1, v2
|
|
; GFX11-CONTRACT-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-DENORM-LABEL: test_f32_sub_mul_rhs:
|
|
; GFX11-DENORM: ; %bb.0: ; %.entry
|
|
; GFX11-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-DENORM-NEXT: v_mul_f32_e32 v0, v0, v1
|
|
; GFX11-DENORM-NEXT: s_delay_alu instid0(VALU_DEP_1)
|
|
; GFX11-DENORM-NEXT: v_sub_f32_e32 v0, v2, v0
|
|
; GFX11-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_sub_f16_e32 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_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: v_mul_f16_e32 v0, v0, v1
|
|
; GFX10-NEXT: v_sub_f16_e32 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: 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: v_mul_f16_e32 v0, v0, v1
|
|
; GFX10-DENORM-NEXT: v_sub_f16_e32 v0, v0, v2
|
|
; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-CONTRACT-TRUE16-LABEL: test_half_sub_mul:
|
|
; GFX11-CONTRACT-TRUE16: ; %bb.0: ; %.entry
|
|
; GFX11-CONTRACT-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-CONTRACT-TRUE16-NEXT: v_fma_f16 v0.l, v0.l, v1.l, -v2.l
|
|
; GFX11-CONTRACT-TRUE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-CONTRACT-FAKE16-LABEL: test_half_sub_mul:
|
|
; GFX11-CONTRACT-FAKE16: ; %bb.0: ; %.entry
|
|
; GFX11-CONTRACT-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-CONTRACT-FAKE16-NEXT: v_fma_f16 v0, v0, v1, -v2
|
|
; GFX11-CONTRACT-FAKE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-DENORM-TRUE16-LABEL: test_half_sub_mul:
|
|
; GFX11-DENORM-TRUE16: ; %bb.0: ; %.entry
|
|
; GFX11-DENORM-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-DENORM-TRUE16-NEXT: v_mul_f16_e32 v0.l, v0.l, v1.l
|
|
; GFX11-DENORM-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1)
|
|
; GFX11-DENORM-TRUE16-NEXT: v_sub_f16_e32 v0.l, v0.l, v2.l
|
|
; GFX11-DENORM-TRUE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-DENORM-FAKE16-LABEL: test_half_sub_mul:
|
|
; GFX11-DENORM-FAKE16: ; %bb.0: ; %.entry
|
|
; GFX11-DENORM-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-DENORM-FAKE16-NEXT: v_mul_f16_e32 v0, v0, v1
|
|
; GFX11-DENORM-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1)
|
|
; GFX11-DENORM-FAKE16-NEXT: v_sub_f16_e32 v0, v0, v2
|
|
; GFX11-DENORM-FAKE16-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_e32 v0, v0, v1
|
|
; GFX9-NEXT: v_sub_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_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: v_mul_f16_e32 v0, v0, v1
|
|
; GFX10-NEXT: v_sub_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: 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: v_mul_f16_e32 v0, v0, v1
|
|
; GFX10-DENORM-NEXT: v_sub_f16_e32 v0, v2, v0
|
|
; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-CONTRACT-TRUE16-LABEL: test_half_sub_mul_rhs:
|
|
; GFX11-CONTRACT-TRUE16: ; %bb.0: ; %.entry
|
|
; GFX11-CONTRACT-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-CONTRACT-TRUE16-NEXT: v_fma_f16 v0.l, -v0.l, v1.l, v2.l
|
|
; GFX11-CONTRACT-TRUE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-CONTRACT-FAKE16-LABEL: test_half_sub_mul_rhs:
|
|
; GFX11-CONTRACT-FAKE16: ; %bb.0: ; %.entry
|
|
; GFX11-CONTRACT-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-CONTRACT-FAKE16-NEXT: v_fma_f16 v0, -v0, v1, v2
|
|
; GFX11-CONTRACT-FAKE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-DENORM-TRUE16-LABEL: test_half_sub_mul_rhs:
|
|
; GFX11-DENORM-TRUE16: ; %bb.0: ; %.entry
|
|
; GFX11-DENORM-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-DENORM-TRUE16-NEXT: v_mul_f16_e32 v0.l, v0.l, v1.l
|
|
; GFX11-DENORM-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1)
|
|
; GFX11-DENORM-TRUE16-NEXT: v_sub_f16_e32 v0.l, v2.l, v0.l
|
|
; GFX11-DENORM-TRUE16-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-DENORM-FAKE16-LABEL: test_half_sub_mul_rhs:
|
|
; GFX11-DENORM-FAKE16: ; %bb.0: ; %.entry
|
|
; GFX11-DENORM-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-DENORM-FAKE16-NEXT: v_mul_f16_e32 v0, v0, v1
|
|
; GFX11-DENORM-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1)
|
|
; GFX11-DENORM-FAKE16-NEXT: v_sub_f16_e32 v0, v2, v0
|
|
; GFX11-DENORM-FAKE16-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: 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: 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: 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]
|
|
;
|
|
; GFX11-CONTRACT-LABEL: test_double_sub_mul:
|
|
; GFX11-CONTRACT: ; %bb.0: ; %.entry
|
|
; GFX11-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-CONTRACT-NEXT: v_fma_f64 v[0:1], v[0:1], v[2:3], -v[4:5]
|
|
; GFX11-CONTRACT-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-DENORM-LABEL: test_double_sub_mul:
|
|
; GFX11-DENORM: ; %bb.0: ; %.entry
|
|
; GFX11-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-DENORM-NEXT: v_mul_f64 v[0:1], v[0:1], v[2:3]
|
|
; GFX11-DENORM-NEXT: s_delay_alu instid0(VALU_DEP_1)
|
|
; GFX11-DENORM-NEXT: v_add_f64 v[0:1], v[0:1], -v[4:5]
|
|
; GFX11-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: 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: 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: 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]
|
|
;
|
|
; GFX11-CONTRACT-LABEL: test_double_sub_mul_rhs:
|
|
; GFX11-CONTRACT: ; %bb.0: ; %.entry
|
|
; GFX11-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-CONTRACT-NEXT: v_fma_f64 v[0:1], -v[0:1], v[2:3], v[4:5]
|
|
; GFX11-CONTRACT-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-DENORM-LABEL: test_double_sub_mul_rhs:
|
|
; GFX11-DENORM: ; %bb.0: ; %.entry
|
|
; GFX11-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-DENORM-NEXT: v_mul_f64 v[0:1], v[0:1], v[2:3]
|
|
; GFX11-DENORM-NEXT: s_delay_alu instid0(VALU_DEP_1)
|
|
; GFX11-DENORM-NEXT: v_add_f64 v[0:1], v[4:5], -v[0:1]
|
|
; GFX11-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: 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: 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: 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]
|
|
;
|
|
; GFX11-CONTRACT-LABEL: test_v4f32_sub_mul:
|
|
; GFX11-CONTRACT: ; %bb.0: ; %.entry
|
|
; GFX11-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-CONTRACT-NEXT: v_fma_f32 v0, v0, v4, -v8
|
|
; GFX11-CONTRACT-NEXT: v_fma_f32 v1, v1, v5, -v9
|
|
; GFX11-CONTRACT-NEXT: v_fma_f32 v2, v2, v6, -v10
|
|
; GFX11-CONTRACT-NEXT: v_fma_f32 v3, v3, v7, -v11
|
|
; GFX11-CONTRACT-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-DENORM-LABEL: test_v4f32_sub_mul:
|
|
; GFX11-DENORM: ; %bb.0: ; %.entry
|
|
; GFX11-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-DENORM-NEXT: v_dual_mul_f32 v0, v0, v4 :: v_dual_mul_f32 v1, v1, v5
|
|
; GFX11-DENORM-NEXT: v_dual_mul_f32 v2, v2, v6 :: v_dual_mul_f32 v3, v3, v7
|
|
; GFX11-DENORM-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
|
|
; GFX11-DENORM-NEXT: v_dual_sub_f32 v0, v0, v8 :: v_dual_sub_f32 v1, v1, v9
|
|
; GFX11-DENORM-NEXT: v_dual_sub_f32 v2, v2, v10 :: v_dual_sub_f32 v3, v3, v11
|
|
; GFX11-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: 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: 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: 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]
|
|
;
|
|
; GFX11-CONTRACT-LABEL: test_v4f32_sub_mul_rhs:
|
|
; GFX11-CONTRACT: ; %bb.0: ; %.entry
|
|
; GFX11-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-CONTRACT-NEXT: v_fma_f32 v0, -v0, v4, v8
|
|
; GFX11-CONTRACT-NEXT: v_fma_f32 v1, -v1, v5, v9
|
|
; GFX11-CONTRACT-NEXT: v_fma_f32 v2, -v2, v6, v10
|
|
; GFX11-CONTRACT-NEXT: v_fma_f32 v3, -v3, v7, v11
|
|
; GFX11-CONTRACT-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-DENORM-LABEL: test_v4f32_sub_mul_rhs:
|
|
; GFX11-DENORM: ; %bb.0: ; %.entry
|
|
; GFX11-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-DENORM-NEXT: v_dual_mul_f32 v0, v0, v4 :: v_dual_mul_f32 v1, v1, v5
|
|
; GFX11-DENORM-NEXT: v_dual_mul_f32 v2, v2, v6 :: v_dual_mul_f32 v3, v3, v7
|
|
; GFX11-DENORM-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
|
|
; GFX11-DENORM-NEXT: v_dual_sub_f32 v0, v8, v0 :: v_dual_sub_f32 v1, v9, v1
|
|
; GFX11-DENORM-NEXT: v_dual_sub_f32 v2, v10, v2 :: v_dual_sub_f32 v3, v11, v3
|
|
; GFX11-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_pk_add_f16 v0, v0, v4 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX9-NEXT: v_pk_add_f16 v1, v1, v5 neg_lo:[0,1] neg_hi:[0,1]
|
|
; 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_pk_add_f16 v0, v0, v4 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX9-DENORM-NEXT: v_pk_add_f16 v1, v1, v5 neg_lo:[0,1] neg_hi:[0,1]
|
|
; 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: v_pk_mul_f16 v0, v0, v2
|
|
; GFX10-NEXT: v_pk_mul_f16 v1, v1, v3
|
|
; GFX10-NEXT: v_pk_add_f16 v0, v0, v4 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX10-NEXT: v_pk_add_f16 v1, v1, v5 neg_lo:[0,1] neg_hi:[0,1]
|
|
; 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: 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: v_pk_mul_f16 v0, v0, v2
|
|
; GFX10-DENORM-NEXT: v_pk_mul_f16 v1, v1, v3
|
|
; GFX10-DENORM-NEXT: v_pk_add_f16 v0, v0, v4 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX10-DENORM-NEXT: v_pk_add_f16 v1, v1, v5 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-CONTRACT-LABEL: test_v4f16_sub_mul:
|
|
; GFX11-CONTRACT: ; %bb.0: ; %.entry
|
|
; GFX11-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-CONTRACT-NEXT: v_pk_fma_f16 v0, v0, v2, v4 neg_lo:[0,0,1] neg_hi:[0,0,1]
|
|
; GFX11-CONTRACT-NEXT: v_pk_fma_f16 v1, v1, v3, v5 neg_lo:[0,0,1] neg_hi:[0,0,1]
|
|
; GFX11-CONTRACT-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-DENORM-LABEL: test_v4f16_sub_mul:
|
|
; GFX11-DENORM: ; %bb.0: ; %.entry
|
|
; GFX11-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-DENORM-NEXT: v_pk_mul_f16 v0, v0, v2
|
|
; GFX11-DENORM-NEXT: v_pk_mul_f16 v1, v1, v3
|
|
; GFX11-DENORM-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
|
|
; GFX11-DENORM-NEXT: v_pk_add_f16 v0, v0, v4 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX11-DENORM-NEXT: v_pk_add_f16 v1, v1, v5 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX11-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 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX9-NEXT: v_pk_mul_f16 v1, v1, v3 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX9-NEXT: v_pk_add_f16 v0, v4, v0
|
|
; GFX9-NEXT: v_pk_add_f16 v1, v5, 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 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX9-DENORM-NEXT: v_pk_mul_f16 v1, v1, v3 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX9-DENORM-NEXT: v_pk_add_f16 v0, v4, v0
|
|
; GFX9-DENORM-NEXT: v_pk_add_f16 v1, v5, 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: v_pk_mul_f16 v0, v0, v2 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX10-NEXT: v_pk_mul_f16 v1, v1, v3 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX10-NEXT: v_pk_add_f16 v0, v4, v0
|
|
; GFX10-NEXT: v_pk_add_f16 v1, v5, 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: 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: v_pk_mul_f16 v0, v0, v2 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX10-DENORM-NEXT: v_pk_mul_f16 v1, v1, v3 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX10-DENORM-NEXT: v_pk_add_f16 v0, v4, v0
|
|
; GFX10-DENORM-NEXT: v_pk_add_f16 v1, v5, v1
|
|
; GFX10-DENORM-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-CONTRACT-LABEL: test_v4f16_sub_mul_rhs:
|
|
; GFX11-CONTRACT: ; %bb.0: ; %.entry
|
|
; GFX11-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-CONTRACT-NEXT: v_pk_fma_f16 v0, v0, v2, v4 neg_lo:[1,0,0] neg_hi:[1,0,0]
|
|
; GFX11-CONTRACT-NEXT: v_pk_fma_f16 v1, v1, v3, v5 neg_lo:[1,0,0] neg_hi:[1,0,0]
|
|
; GFX11-CONTRACT-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-DENORM-LABEL: test_v4f16_sub_mul_rhs:
|
|
; GFX11-DENORM: ; %bb.0: ; %.entry
|
|
; GFX11-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-DENORM-NEXT: v_pk_mul_f16 v0, v0, v2 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX11-DENORM-NEXT: v_pk_mul_f16 v1, v1, v3 neg_lo:[0,1] neg_hi:[0,1]
|
|
; GFX11-DENORM-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
|
|
; GFX11-DENORM-NEXT: v_pk_add_f16 v0, v4, v0
|
|
; GFX11-DENORM-NEXT: v_pk_add_f16 v1, v5, v1
|
|
; GFX11-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: 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: 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: 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]
|
|
;
|
|
; GFX11-CONTRACT-LABEL: test_v4f64_sub_mul:
|
|
; GFX11-CONTRACT: ; %bb.0: ; %.entry
|
|
; GFX11-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-CONTRACT-NEXT: v_fma_f64 v[0:1], v[0:1], v[8:9], -v[16:17]
|
|
; GFX11-CONTRACT-NEXT: v_fma_f64 v[2:3], v[2:3], v[10:11], -v[18:19]
|
|
; GFX11-CONTRACT-NEXT: v_fma_f64 v[4:5], v[4:5], v[12:13], -v[20:21]
|
|
; GFX11-CONTRACT-NEXT: v_fma_f64 v[6:7], v[6:7], v[14:15], -v[22:23]
|
|
; GFX11-CONTRACT-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-DENORM-LABEL: test_v4f64_sub_mul:
|
|
; GFX11-DENORM: ; %bb.0: ; %.entry
|
|
; GFX11-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-DENORM-NEXT: v_mul_f64 v[0:1], v[0:1], v[8:9]
|
|
; GFX11-DENORM-NEXT: v_mul_f64 v[2:3], v[2:3], v[10:11]
|
|
; GFX11-DENORM-NEXT: v_mul_f64 v[4:5], v[4:5], v[12:13]
|
|
; GFX11-DENORM-NEXT: v_mul_f64 v[6:7], v[6:7], v[14:15]
|
|
; GFX11-DENORM-NEXT: s_delay_alu instid0(VALU_DEP_4) | instskip(NEXT) | instid1(VALU_DEP_4)
|
|
; GFX11-DENORM-NEXT: v_add_f64 v[0:1], v[0:1], -v[16:17]
|
|
; GFX11-DENORM-NEXT: v_add_f64 v[2:3], v[2:3], -v[18:19]
|
|
; GFX11-DENORM-NEXT: s_delay_alu instid0(VALU_DEP_4) | instskip(NEXT) | instid1(VALU_DEP_4)
|
|
; GFX11-DENORM-NEXT: v_add_f64 v[4:5], v[4:5], -v[20:21]
|
|
; GFX11-DENORM-NEXT: v_add_f64 v[6:7], v[6:7], -v[22:23]
|
|
; GFX11-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: 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: 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: 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]
|
|
;
|
|
; GFX11-CONTRACT-LABEL: test_v4f64_sub_mul_rhs:
|
|
; GFX11-CONTRACT: ; %bb.0: ; %.entry
|
|
; GFX11-CONTRACT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-CONTRACT-NEXT: v_fma_f64 v[0:1], -v[0:1], v[8:9], v[16:17]
|
|
; GFX11-CONTRACT-NEXT: v_fma_f64 v[2:3], -v[2:3], v[10:11], v[18:19]
|
|
; GFX11-CONTRACT-NEXT: v_fma_f64 v[4:5], -v[4:5], v[12:13], v[20:21]
|
|
; GFX11-CONTRACT-NEXT: v_fma_f64 v[6:7], -v[6:7], v[14:15], v[22:23]
|
|
; GFX11-CONTRACT-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-DENORM-LABEL: test_v4f64_sub_mul_rhs:
|
|
; GFX11-DENORM: ; %bb.0: ; %.entry
|
|
; GFX11-DENORM-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-DENORM-NEXT: v_mul_f64 v[0:1], v[0:1], v[8:9]
|
|
; GFX11-DENORM-NEXT: v_mul_f64 v[2:3], v[2:3], v[10:11]
|
|
; GFX11-DENORM-NEXT: v_mul_f64 v[4:5], v[4:5], v[12:13]
|
|
; GFX11-DENORM-NEXT: v_mul_f64 v[6:7], v[6:7], v[14:15]
|
|
; GFX11-DENORM-NEXT: s_delay_alu instid0(VALU_DEP_4) | instskip(NEXT) | instid1(VALU_DEP_4)
|
|
; GFX11-DENORM-NEXT: v_add_f64 v[0:1], v[16:17], -v[0:1]
|
|
; GFX11-DENORM-NEXT: v_add_f64 v[2:3], v[18:19], -v[2:3]
|
|
; GFX11-DENORM-NEXT: s_delay_alu instid0(VALU_DEP_4) | instskip(NEXT) | instid1(VALU_DEP_4)
|
|
; GFX11-DENORM-NEXT: v_add_f64 v[4:5], v[20:21], -v[4:5]
|
|
; GFX11-DENORM-NEXT: v_add_f64 v[6:7], v[22:23], -v[6:7]
|
|
; GFX11-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
|
|
}
|