From 828573a573553e9c38f0431f0998de8c905f8460 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Fri, 31 Jan 2020 16:44:36 +0100 Subject: [PATCH] Fix TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL handling. The reason for TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL on AMD target is only insn size, as advised in e.g. Software Optimization Guide for the AMD Family 15h Processors [1], section 7.1.2, where it is said: --quote-- 7.1.2 Reduce Instruction SizeOptimization Reduce the size of instructions when possible. Rationale Using smaller instruction sizes improves instruction fetch throughput. Specific examples include the following: *In SIMD code, use the single-precision (PS) form of instructions instead of the double-precision (PD) form. For example, for register to register moves, MOVAPS achieves the same result as MOVAPD, but uses one less byte to encode the instruction and has no prefix byte. Other examples in which single-precision forms can be substituted for double-precision forms include MOVUPS, MOVNTPS, XORPS, ORPS, ANDPS, and SHUFPS. ... --/quote-- Please note that this optimization applies only to non-AVX forms, as demonstrated by: 0: 0f 28 c8 movaps %xmm0,%xmm1 3: 66 0f 28 c8 movapd %xmm0,%xmm1 7: c5 f8 28 d1 vmovaps %xmm1,%xmm2 b: c5 f9 28 d1 vmovapd %xmm1,%xmm2 Also note that MOVDQA is missing in the above optimization. It is harmful to substitute MOVDQA with MOVAPS, as it can (and does) introduce +1 cycle forwarding penalty between FLT (FPA/FPM) and INT (VALU) FP clusters. [1] https://www.amd.com/system/files/TechDocs/47414_15h_sw_opt_guide.pdf --- gcc/ChangeLog | 29 +++++++++++++++ gcc/config/i386/i386.md | 65 +++++++++++++------------------- gcc/config/i386/mmx.md | 6 +-- gcc/config/i386/sse.md | 88 +++++++++++++++++++------------------------- gcc/config/i386/x86-tune.def | 8 ++-- 5 files changed, 98 insertions(+), 98 deletions(-) diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 78a8310..0e99b72 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,32 @@ +2020-01-31 Uroš Bizjak + + * config/i386/i386.md (*movoi_internal_avx): Do not check for + TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL. Remove MODE_V8SF handling. + (*movti_internal): Do not check for + TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL. + (*movtf_internal): Move check for TARGET_SSE2 and size optimization + just after check for TARGET_AVX. + (*movdf_internal): Ditto. + * config/i386/mmx.md (*mov_internal): Do not check for + TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL. + * config/i386/sse.md (mov_internal): Only check + TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL with V2DFmode. Move check + for TARGET_SSE2 and size optimization just after check for TARGET_AVX. + (_andnot3): Move check for + TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL after check for TARGET_AVX. + (3): Ditto. + (*andnot3): Ditto. + (*andnottf3): Ditto. + (*3): Ditto. + (*tf3): Ditto. + (*andnot3): Remove + TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL handling. + (3): Ditto. + (*3): Ditto. + (sse4_1_blendv): Ditto. + * config/i386/x86-tune.def (X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL): + Explain that tune applies to 128bit instructions only. + 2020-01-31 Kwok Cheung Yeung * config/gcn/mkoffload.c (process_asm): Add sgpr_count and vgpr_count diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md index f5c8d55..46b442d 100644 --- a/gcc/config/i386/i386.md +++ b/gcc/config/i386/i386.md @@ -1949,18 +1949,14 @@ if (misaligned_operand (operands[0], OImode) || misaligned_operand (operands[1], OImode)) { - if (get_attr_mode (insn) == MODE_V8SF) - return "vmovups\t{%1, %0|%0, %1}"; - else if (get_attr_mode (insn) == MODE_XI) + if (get_attr_mode (insn) == MODE_XI) return "vmovdqu32\t{%1, %0|%0, %1}"; else return "vmovdqu\t{%1, %0|%0, %1}"; } else { - if (get_attr_mode (insn) == MODE_V8SF) - return "vmovaps\t{%1, %0|%0, %1}"; - else if (get_attr_mode (insn) == MODE_XI) + if (get_attr_mode (insn) == MODE_XI) return "vmovdqa32\t{%1, %0|%0, %1}"; else return "vmovdqa\t{%1, %0|%0, %1}"; @@ -1980,8 +1976,6 @@ (and (eq_attr "alternative" "1") (match_test "TARGET_AVX512VL")) (const_string "XI") - (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") - (const_string "V8SF") ] (const_string "OI")))]) @@ -2060,11 +2054,10 @@ (match_test "TARGET_AVX") (const_string "TI") (ior (not (match_test "TARGET_SSE2")) - (ior (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") - (and (eq_attr "alternative" "5") - (match_test "TARGET_SSE_TYPELESS_STORES")))) + (match_test "optimize_function_for_size_p (cfun)")) (const_string "V4SF") - (match_test "optimize_function_for_size_p (cfun)") + (and (eq_attr "alternative" "5") + (match_test "TARGET_SSE_TYPELESS_STORES")) (const_string "V4SF") ] (const_string "TI"))) @@ -2243,12 +2236,10 @@ (cond [(ior (match_operand 0 "ext_sse_reg_operand") (match_operand 1 "ext_sse_reg_operand")) (const_string "TI") - (ior (not (match_test "TARGET_SSE2")) - (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")) - (const_string "V4SF") (match_test "TARGET_AVX") (const_string "TI") - (match_test "optimize_function_for_size_p (cfun)") + (ior (not (match_test "TARGET_SSE2")) + (match_test "optimize_function_for_size_p (cfun)")) (const_string "V4SF") ] (const_string "TI")) @@ -2453,12 +2444,10 @@ (cond [(ior (match_operand 0 "ext_sse_reg_operand") (match_operand 1 "ext_sse_reg_operand")) (const_string "XI") - (ior (not (match_test "TARGET_SSE2")) - (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")) - (const_string "V4SF") (match_test "TARGET_AVX") (const_string "TI") - (match_test "optimize_function_for_size_p (cfun)") + (ior (not (match_test "TARGET_SSE2")) + (match_test "optimize_function_for_size_p (cfun)")) (const_string "V4SF") ] (const_string "TI")) @@ -3324,14 +3313,14 @@ (const_string "DI") (match_test "TARGET_AVX") (const_string "TI") + (ior (not (match_test "TARGET_SSE2")) + (match_test "optimize_function_for_size_p (cfun)")) + (const_string "V4SF") (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") (const_string "V4SF") (and (eq_attr "alternative" "2") (match_test "TARGET_SSE_TYPELESS_STORES")) (const_string "V4SF") - (ior (not (match_test "TARGET_SSE2")) - (match_test "optimize_function_for_size_p (cfun)")) - (const_string "V4SF") ] (const_string "TI")))]) @@ -3541,14 +3530,13 @@ /* xorps is one byte shorter for non-AVX targets. */ (eq_attr "alternative" "12,16") - (cond [(not (match_test "TARGET_SSE2")) - (const_string "V4SF") - (and (match_test "TARGET_AVX512F") - (not (match_test "TARGET_PREFER_AVX256"))) + (cond [(and (match_test "TARGET_AVX512F") + (not (match_test "TARGET_PREFER_AVX256"))) (const_string "XI") (match_test "TARGET_AVX") (const_string "V2DF") - (match_test "optimize_function_for_size_p (cfun)") + (ior (not (match_test "TARGET_SSE2")) + (match_test "optimize_function_for_size_p (cfun)")) (const_string "V4SF") (match_test "TARGET_SSE_LOAD0_BY_PXOR") (const_string "TI") @@ -3566,15 +3554,15 @@ (ior (match_operand 0 "ext_sse_reg_operand") (match_operand 1 "ext_sse_reg_operand"))) (const_string "V8DF") + (match_test "TARGET_AVX") + (const_string "DF") (ior (not (match_test "TARGET_SSE2")) - (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")) + (match_test "optimize_function_for_size_p (cfun)")) + (const_string "V4SF") + (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") (const_string "V4SF") (match_test "TARGET_SSE_PARTIAL_REG_DEPENDENCY") (const_string "V2DF") - (match_test "TARGET_AVX") - (const_string "DF") - (match_test "optimize_function_for_size_p (cfun)") - (const_string "V4SF") ] (const_string "DF")) @@ -3723,16 +3711,15 @@ (eq_attr "alternative" "11") (const_string "DI") (eq_attr "alternative" "5") - (cond [(not (match_test "TARGET_SSE2")) - (const_string "V4SF") - (and (match_test "TARGET_AVX512F") - (not (match_test "TARGET_PREFER_AVX256"))) + (cond [(and (match_test "TARGET_AVX512F") + (not (match_test "TARGET_PREFER_AVX256"))) (const_string "V16SF") (match_test "TARGET_AVX") (const_string "V4SF") - (match_test "optimize_function_for_size_p (cfun)") + (ior (not (match_test "TARGET_SSE2")) + (match_test "optimize_function_for_size_p (cfun)")) (const_string "V4SF") - (match_test "TARGET_SSE_LOAD0_BY_PXOR") + (match_test "TARGET_SSE_LOAD0_BY_PXOR") (const_string "TI") ] (const_string "V4SF")) diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md index d06e3b1..f695831 100644 --- a/gcc/config/i386/mmx.md +++ b/gcc/config/i386/mmx.md @@ -195,11 +195,7 @@ (match_test "mode == V2SFmode") (const_string "V4SF") (ior (not (match_test "TARGET_SSE2")) - (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")) - (const_string "V4SF") - (match_test "TARGET_AVX") - (const_string "TI") - (match_test "optimize_function_for_size_p (cfun)") + (match_test "optimize_function_for_size_p (cfun)")) (const_string "V4SF") ] (const_string "TI")) diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index f5ff2e9..46f00e3 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -1118,13 +1118,15 @@ (const_string "") (match_test "TARGET_AVX") (const_string "") - (ior (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") - (and (eq_attr "alternative" "3") - (match_test "TARGET_SSE_TYPELESS_STORES"))) - (const_string "") (ior (not (match_test "TARGET_SSE2")) (match_test "optimize_function_for_size_p (cfun)")) (const_string "V4SF") + (and (match_test "mode == V2DFmode") + (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")) + (const_string "V4SF") + (and (eq_attr "alternative" "3") + (match_test "TARGET_SSE_TYPELESS_STORES")) + (const_string "V4SF") (and (eq_attr "alternative" "0") (match_test "TARGET_SSE_LOAD0_BY_PXOR")) (const_string "TI") @@ -3555,16 +3557,14 @@ (const_string "") (eq_attr "alternative" "3") (const_string "") - (and (match_test " == 16") - (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")) - (const_string "") (match_test "TARGET_AVX") (const_string "") (match_test "optimize_function_for_size_p (cfun)") (const_string "V4SF") - ] - (const_string "")))]) - + (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") + (const_string "V4SF") + ] + (const_string "")))]) (define_insn "_andnot3" [(set (match_operand:VF_512 0 "register_operand" "=v") @@ -3673,15 +3673,14 @@ (const_string "") (eq_attr "alternative" "3") (const_string "") - (and (match_test " == 16") - (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")) - (const_string "") (match_test "TARGET_AVX") (const_string "") (match_test "optimize_function_for_size_p (cfun)") (const_string "V4SF") - ] - (const_string "")))]) + (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") + (const_string "V4SF") + ] + (const_string "")))]) (define_insn "*3" [(set (match_operand:VF_512 0 "register_operand" "=v") @@ -3822,15 +3821,14 @@ (if_then_else (match_test "TARGET_AVX512DQ") (const_string "") (const_string "XI")) - (and (match_test " == 16") - (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")) - (const_string "V4SF") (match_test "TARGET_AVX") (const_string "") (match_test "optimize_function_for_size_p (cfun)") (const_string "V4SF") - ] - (const_string "")))]) + (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") + (const_string "V4SF") + ] + (const_string "")))]) (define_insn "*andnottf3" [(set (match_operand:TF 0 "register_operand" "=x,x,v,v") @@ -3879,15 +3877,15 @@ (const_string "TI") (eq_attr "alternative" "3") (const_string "XI") - (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") - (const_string "V4SF") (match_test "TARGET_AVX") (const_string "TI") (ior (not (match_test "TARGET_SSE2")) (match_test "optimize_function_for_size_p (cfun)")) (const_string "V4SF") - ] - (const_string "TI")))]) + (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") + (const_string "V4SF") + ] + (const_string "TI")))]) (define_insn "*3" [(set (match_operand:MODEF 0 "register_operand" "=x,x,v,v") @@ -3946,15 +3944,14 @@ (if_then_else (match_test "TARGET_AVX512DQ") (const_string "") (const_string "XI")) - (and (match_test " == 16") - (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")) - (const_string "V4SF") (match_test "TARGET_AVX") (const_string "") (match_test "optimize_function_for_size_p (cfun)") (const_string "V4SF") - ] - (const_string "")))]) + (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") + (const_string "V4SF") + ] + (const_string "")))]) (define_expand "tf3" [(set (match_operand:TF 0 "register_operand") @@ -4011,15 +4008,15 @@ (const_string "TI") (eq_attr "alternative" "3") (const_string "QI") - (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") - (const_string "V4SF") (match_test "TARGET_AVX") (const_string "TI") (ior (not (match_test "TARGET_SSE2")) (match_test "optimize_function_for_size_p (cfun)")) (const_string "V4SF") - ] - (const_string "TI")))]) + (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") + (const_string "V4SF") + ] + (const_string "TI")))]) ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;; ;; @@ -13007,10 +13004,7 @@ (const_string "*"))) (set_attr "prefix" "orig,vex,evex") (set (attr "mode") - (cond [(and (match_test " == 16") - (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")) - (const_string "") - (match_test "TARGET_AVX2") + (cond [(match_test "TARGET_AVX2") (const_string "") (match_test "TARGET_AVX") (if_then_else @@ -13148,10 +13142,7 @@ (const_string "*"))) (set_attr "prefix" ",evex") (set (attr "mode") - (cond [(and (match_test " == 16") - (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")) - (const_string "") - (match_test "TARGET_AVX2") + (cond [(match_test "TARGET_AVX2") (const_string "") (match_test "TARGET_AVX") (if_then_else @@ -13244,10 +13235,7 @@ (const_string "*"))) (set_attr "prefix" "orig,vex,evex") (set (attr "mode") - (cond [(and (match_test " == 16") - (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL")) - (const_string "") - (match_test "TARGET_AVX2") + (cond [(match_test "TARGET_AVX2") (const_string "") (match_test "TARGET_AVX") (if_then_else @@ -17190,14 +17178,14 @@ (set_attr "prefix" "orig,orig,vex") (set_attr "btver2_decode" "vector,vector,vector") (set (attr "mode") - (cond [(match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") - (const_string "V4SF") - (match_test "TARGET_AVX") + (cond [(match_test "TARGET_AVX") (const_string "") (match_test "optimize_function_for_size_p (cfun)") (const_string "V4SF") - ] - (const_string "")))]) + (match_test "TARGET_SSE_PACKED_SINGLE_INSN_OPTIMAL") + (const_string "V4SF") + ] + (const_string "")))]) (define_insn_and_split "*_blendv_lt" [(set (match_operand:VF_128_256 0 "register_operand" "=Yr,*x,x") diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def index 2125474..41b3d52 100644 --- a/gcc/config/i386/x86-tune.def +++ b/gcc/config/i386/x86-tune.def @@ -366,15 +366,15 @@ DEF_TUNE (X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL, "sse_unaligned_load_optimal", | m_INTEL | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_AMDFAM10 | m_BDVER | m_BTVER | m_ZNVER | m_GENERIC) -/* X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL: Use movups for misaligned stores instead - of a sequence loading registers by parts. */ +/* X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL: Use movups for misaligned stores + instead of a sequence loading registers by parts. */ DEF_TUNE (X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL, "sse_unaligned_store_optimal", m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_SILVERMONT | m_KNL | m_KNM | m_INTEL | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_BDVER | m_ZNVER | m_GENERIC) -/* Use packed single precision instructions where posisble. I.e. movups instead - of movupd. */ +/* X86_TUNE_SSE_PACKED_SINGLE_INSN_OPTIMAL: Use packed single + precision 128bit instructions instead of double where possible. */ DEF_TUNE (X86_TUNE_SSE_PACKED_SINGLE_INSN_OPTIMAL, "sse_packed_single_insn_optimal", m_BDVER | m_ZNVER) -- 2.7.4